{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/task-planning","name":"Task Planning","slug":"task-planning","description_markdown":null,"categories":[{"name":"Reasoning","url":"/area/reasoning"},{"name":"Robots","url":"/area/robots"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":344,"papers_with_code":100,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":1,"subtasks":0,"parent_tasks":1},"benchmarks":[],"datasets":[{"url":"/dataset/plancraft","name":"Plancraft","full_name":"","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[{"url":"/task/robot-task-planning","name":"Robot Task Planning"}],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":4,"rows_per_page":100,"shown":100,"of":344,"of_with_code":100,"tagged_in_all":344,"counts":{"archive_papers_tagged":344,"with_a_code_link":100,"where_syntology_ran_a_sample":35,"not_listed_spam_title":0,"listed":344,"listed_where_code_ran":35,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":25,"every_run_a_failure_of_syntologys_instrument":10,"listed_with_a_run_with_no_instrument_failure":25,"listed_every_run_a_failure_of_syntologys_instrument":10,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/nyu-ctf-dataset-a-scalable-open-source","slug":"nyu-ctf-dataset-a-scalable-open-source","title":"NYU CTF Bench: A Scalable Open-Source Benchmark Dataset for Evaluating LLMs in Offensive Security","date":"2024-06-08","arxiv_id":"2406.05590","repositories_listed":5,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":1,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":4,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/nyu-ctf-dataset-a-scalable-open-source#ran","syntology_url":"https://syntology.ai/paper/2406.05590","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.05590"}},"official":{"repos":["nyu-llm-ctf/llm_ctf_automation","nyu-llm-ctf/llm_ctf_database","nyu-llm-ctf/nyu_ctf_bench"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/prismatic-vlms-investigating-the-design-space","slug":"prismatic-vlms-investigating-the-design-space","title":"Prismatic VLMs: Investigating the Design Space of Visually-Conditioned Language Models","date":"2024-02-12","arxiv_id":"2402.07865","repositories_listed":3,"syntology":{"n":5,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/prismatic-vlms-investigating-the-design-space#ran","syntology_url":"https://syntology.ai/paper/2402.07865","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.07865"}},"official":{"repos":["tri-ml/prismatic-vlms","tri-ml/vlm-evaluation"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/a-comparison-of-prompt-engineering-techniques","slug":"a-comparison-of-prompt-engineering-techniques","title":"A Comparison of Prompt Engineering Techniques for Task Planning and Execution in Service Robotics","date":"2024-10-30","arxiv_id":"2410.22997","repositories_listed":2,"syntology":null},{"url":"/paper/riskawarebench-towards-evaluating-physical","slug":"riskawarebench-towards-evaluating-physical","title":"EARBench: Towards Evaluating Physical Risk Awareness for Task Planning of Foundation Model-based Embodied AI Agents","date":"2024-08-08","arxiv_id":"2408.04449","repositories_listed":2,"syntology":{"n":11,"n_ran":6,"n_constructed":0,"n_ran_checked":4,"n_instrument":2,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":1,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/riskawarebench-towards-evaluating-physical#ran","syntology_url":"https://syntology.ai/paper/2408.04449","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.04449"}},"official":{"repos":["zihao-ai/eairiskbench","zihao-ai/earbench"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/personal-llm-agents-insights-and-survey-about","slug":"personal-llm-agents-insights-and-survey-about","title":"Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security","date":"2024-01-10","arxiv_id":"2401.05459","repositories_listed":2,"syntology":null},{"url":"/paper/kinematic-aware-prompting-for-generalizable","slug":"kinematic-aware-prompting-for-generalizable","title":"Kinematic-aware Prompting for Generalizable Articulated Object Manipulation with LLMs","date":"2023-11-06","arxiv_id":"2311.02847","repositories_listed":2,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/kinematic-aware-prompting-for-generalizable#ran","syntology_url":"https://syntology.ai/paper/2311.02847","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.02847"}},"official":{"repos":["gewu-lab/llm_articulated_object_manipulation","xwinks/llm_articulated_object_manipulation"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/isr-llm-iterative-self-refined-large-language","slug":"isr-llm-iterative-self-refined-large-language","title":"ISR-LLM: Iterative Self-Refined Large Language Model for Long-Horizon Sequential Task Planning","date":"2023-08-26","arxiv_id":"2308.13724","repositories_listed":2,"syntology":null},{"url":"/paper/plansys2-a-planning-system-framework-for-ros2","slug":"plansys2-a-planning-system-framework-for-ros2","title":"PlanSys2: A Planning System Framework for ROS2","date":"2021-07-01","arxiv_id":"2107.00376","repositories_listed":2,"syntology":null},{"url":"/paper/gta1-gui-test-time-scaling-agent","slug":"gta1-gui-test-time-scaling-agent","title":"GTA1: GUI Test-time Scaling Agent","date":"2025-07-08","arxiv_id":"2507.05791","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":3,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/gta1-gui-test-time-scaling-agent#ran","syntology_url":"https://syntology.ai/paper/2507.05791","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2507.05791"}},"official":{"repos":["yan98/gta1"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/a-comprehensive-survey-of-deep-research","slug":"a-comprehensive-survey-of-deep-research","title":"A Comprehensive Survey of Deep Research: Systems, Methodologies, and Applications","date":"2025-06-14","arxiv_id":"2506.12594","repositories_listed":1,"syntology":null},{"url":"/paper/prime-the-search-using-large-language-models","slug":"prime-the-search-using-large-language-models","title":"Prime the search: Using large language models for guiding geometric task and motion planning by warm-starting tree search","date":"2025-06-08","arxiv_id":"2506.07062","repositories_listed":1,"syntology":null},{"url":"/paper/flysearch-exploring-how-vision-language","slug":"flysearch-exploring-how-vision-language","title":"FlySearch: Exploring how vision-language models explore","date":"2025-06-03","arxiv_id":"2506.02896","repositories_listed":1,"syntology":null},{"url":"/paper/bedi-a-comprehensive-benchmark-for-evaluating","slug":"bedi-a-comprehensive-benchmark-for-evaluating","title":"BEDI: A Comprehensive Benchmark for Evaluating Embodied Agents on UAVs","date":"2025-05-23","arxiv_id":"2505.18229","repositories_listed":1,"syntology":null},{"url":"/paper/craken-cybersecurity-llm-agent-with-knowledge","slug":"craken-cybersecurity-llm-agent-with-knowledge","title":"CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Execution","date":"2025-05-21","arxiv_id":"2505.17107","repositories_listed":1,"syntology":null},{"url":"/paper/apex-empowering-llms-with-physics-based-task","slug":"apex-empowering-llms-with-physics-based-task","title":"APEX: Empowering LLMs with Physics-Based Task Planning for Real-time Insight","date":"2025-05-20","arxiv_id":"2505.13921","repositories_listed":1,"syntology":null},{"url":"/paper/achieving-scalable-robot-autonomy-via","slug":"achieving-scalable-robot-autonomy-via","title":"Achieving Scalable Robot Autonomy via neurosymbolic planning using lightweight local LLM","date":"2025-05-13","arxiv_id":"2505.08492","repositories_listed":1,"syntology":null},{"url":"/paper/llm-empowered-embodied-agent-for-memory","slug":"llm-empowered-embodied-agent-for-memory","title":"LLM-Empowered Embodied Agent for Memory-Augmented Task Planning in Household Robotics","date":"2025-04-30","arxiv_id":"2504.21716","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/llm-empowered-embodied-agent-for-memory#ran","syntology_url":"https://syntology.ai/paper/2504.21716","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.21716"}},"official":{"repos":["marc1198/chat-hsr"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/enhancing-llm-based-agents-via-global","slug":"enhancing-llm-based-agents-via-global","title":"Enhancing LLM-Based Agents via Global Planning and Hierarchical Execution","date":"2025-04-23","arxiv_id":"2504.16563","repositories_listed":1,"syntology":null},{"url":"/paper/agent-s2-a-compositional-generalist","slug":"agent-s2-a-compositional-generalist","title":"Agent S2: A Compositional Generalist-Specialist Framework for Computer Use Agents","date":"2025-04-01","arxiv_id":"2504.00906","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/agent-s2-a-compositional-generalist#ran","syntology_url":"https://syntology.ai/paper/2504.00906","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.00906"}},"official":{"repos":["simular-ai/agent-s"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/data-agnostic-robotic-long-horizon","slug":"data-agnostic-robotic-long-horizon","title":"Data-Agnostic Robotic Long-Horizon Manipulation with Vision-Language-Guided Closed-Loop Feedback","date":"2025-03-27","arxiv_id":"2503.21969","repositories_listed":1,"syntology":null},{"url":"/paper/llm-map-bimanual-robot-task-planning-using","slug":"llm-map-bimanual-robot-task-planning-using","title":"LLM+MAP: Bimanual Robot Task Planning using Large Language Models and Planning Domain Definition Language","date":"2025-03-21","arxiv_id":"2503.17309","repositories_listed":1,"syntology":null},{"url":"/paper/graphormer-guided-task-planning-beyond-static","slug":"graphormer-guided-task-planning-beyond-static","title":"Graphormer-Guided Task Planning: Beyond Static Rules with LLM Safety Perception","date":"2025-03-10","arxiv_id":"2503.06866","repositories_listed":1,"syntology":null},{"url":"/paper/safe-llm-controlled-robots-with-formal","slug":"safe-llm-controlled-robots-with-formal","title":"Safe LLM-Controlled Robots with Formal Guarantees via Reachability Analysis","date":"2025-03-05","arxiv_id":"2503.03911","repositories_listed":1,"syntology":null},{"url":"/paper/clea-closed-loop-embodied-agent-for-enhancing","slug":"clea-closed-loop-embodied-agent-for-enhancing","title":"CLEA: Closed-Loop Embodied Agent for Enhancing Task Execution in Dynamic Environments","date":"2025-03-02","arxiv_id":"2503.00729","repositories_listed":1,"syntology":null},{"url":"/paper/mrbtp-efficient-multi-robot-behavior-tree","slug":"mrbtp-efficient-multi-robot-behavior-tree","title":"MRBTP: Efficient Multi-Robot Behavior Tree Planning and Collaboration","date":"2025-02-25","arxiv_id":"2502.18072","repositories_listed":1,"syntology":null},{"url":"/paper/plan-over-graph-towards-parallelable-llm","slug":"plan-over-graph-towards-parallelable-llm","title":"Plan-over-Graph: Towards Parallelable LLM Agent Schedule","date":"2025-02-20","arxiv_id":"2502.14563","repositories_listed":1,"syntology":null},{"url":"/paper/navrag-generating-user-demand-instructions","slug":"navrag-generating-user-demand-instructions","title":"NavRAG: Generating User Demand Instructions for Embodied Navigation through Retrieval-Augmented LLM","date":"2025-02-16","arxiv_id":"2502.11142","repositories_listed":1,"syntology":null},{"url":"/paper/d-cipher-dynamic-collaborative-intelligent","slug":"d-cipher-dynamic-collaborative-intelligent","title":"D-CIPHER: Dynamic Collaborative Intelligent Multi-Agent System with Planner and Heterogeneous Executors for Offensive Security","date":"2025-02-15","arxiv_id":"2502.10931","repositories_listed":1,"syntology":null},{"url":"/paper/large-language-models-for-multi-robot-systems","slug":"large-language-models-for-multi-robot-systems","title":"Large Language Models for Multi-Robot Systems: A Survey","date":"2025-02-06","arxiv_id":"2502.03814","repositories_listed":1,"syntology":null},{"url":"/paper/robotouille-an-asynchronous-planning","slug":"robotouille-an-asynchronous-planning","title":"Robotouille: An Asynchronous Planning Benchmark for LLM Agents","date":"2025-02-06","arxiv_id":"2502.05227","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/robotouille-an-asynchronous-planning#ran","syntology_url":"https://syntology.ai/paper/2502.05227","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.05227"}},"official":{"repos":["portal-cornell/robotouille"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/vlm-driven-behavior-tree-for-context-aware","slug":"vlm-driven-behavior-tree-for-context-aware","title":"VLM-driven Behavior Tree for Context-aware Task Planning","date":"2025-01-07","arxiv_id":"2501.03968","repositories_listed":1,"syntology":null},{"url":"/paper/vinci-a-real-time-embodied-smart-assistant","slug":"vinci-a-real-time-embodied-smart-assistant","title":"Vinci: A Real-time Embodied Smart Assistant based on Egocentric Vision-Language Model","date":"2024-12-30","arxiv_id":"2412.21080","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/vinci-a-real-time-embodied-smart-assistant#ran","syntology_url":"https://syntology.ai/paper/2412.21080","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.21080"}},"official":{"repos":["opengvlab/vinci"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]}}},{"url":"/paper/multi-modal-grounded-planning-and-efficient","slug":"multi-modal-grounded-planning-and-efficient","title":"Multi-Modal Grounded Planning and Efficient Replanning For Learning Embodied Agents with A Few Examples","date":"2024-12-23","arxiv_id":"2412.17288","repositories_listed":1,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":8,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/multi-modal-grounded-planning-and-efficient#ran","syntology_url":"https://syntology.ai/paper/2412.17288","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.17288"}},"official":{"repos":["snumprlab/flare"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/safeagentbench-a-benchmark-for-safe-task","slug":"safeagentbench-a-benchmark-for-safe-task","title":"SafeAgentBench: A Benchmark for Safe Task Planning of Embodied LLM Agents","date":"2024-12-17","arxiv_id":"2412.13178","repositories_listed":1,"syntology":{"n":11,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":1,"n_no_contract":5,"n_pointer_only":11,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/safeagentbench-a-benchmark-for-safe-task#ran","syntology_url":"https://syntology.ai/paper/2412.13178","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.13178"}},"official":{"repos":["shengyin1224/safeagentbench"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/emma-x-an-embodied-multimodal-action-model","slug":"emma-x-an-embodied-multimodal-action-model","title":"Emma-X: An Embodied Multimodal Action Model with Grounded Chain of Thought and Look-ahead Spatial Reasoning","date":"2024-12-16","arxiv_id":"2412.11974","repositories_listed":1,"syntology":null},{"url":"/paper/robomatrix-a-skill-centric-hierarchical","slug":"robomatrix-a-skill-centric-hierarchical","title":"RoboMatrix: A Skill-centric Hierarchical Framework for Scalable Robot Task Planning and Execution in Open-World","date":"2024-11-29","arxiv_id":"2412.00171","repositories_listed":1,"syntology":null},{"url":"/paper/semantic-geometric-physical-driven-robot","slug":"semantic-geometric-physical-driven-robot","title":"Semantic-Geometric-Physical-Driven Robot Manipulation Skill Transfer via Skill Library and Tactile Representation","date":"2024-11-18","arxiv_id":"2411.11714","repositories_listed":1,"syntology":null},{"url":"/paper/workflowllm-enhancing-workflow-orchestration","slug":"workflowllm-enhancing-workflow-orchestration","title":"WorkflowLLM: Enhancing Workflow Orchestration Capability of Large Language Models","date":"2024-11-08","arxiv_id":"2411.05451","repositories_listed":1,"syntology":null},{"url":"/paper/general-task-optimal-planning-for","slug":"general-task-optimal-planning-for","title":"Optimal planning for heterogeneous autonomous teams with precedence and compatibility constraints and its application on power grid inspection with Unmanned Aerial Vehicles","date":"2024-10-28","arxiv_id":"2410.20849","repositories_listed":1,"syntology":null},{"url":"/paper/agent-s-an-open-agentic-framework-that-uses","slug":"agent-s-an-open-agentic-framework-that-uses","title":"Agent S: An Open Agentic Framework that Uses Computers Like a Human","date":"2024-10-10","arxiv_id":"2410.08164","repositories_listed":1,"syntology":null},{"url":"/paper/closed-loop-long-horizon-robotic-planning-via","slug":"closed-loop-long-horizon-robotic-planning-via","title":"Closed-Loop Long-Horizon Robotic Planning via Equilibrium Sequence Modeling","date":"2024-10-02","arxiv_id":"2410.01440","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/closed-loop-long-horizon-robotic-planning-via#ran","syntology_url":"https://syntology.ai/paper/2410.01440","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.01440"}},"official":{"repos":["singularity0104/equilibrium-planner"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/towards-generalizable-vision-language-robotic","slug":"towards-generalizable-vision-language-robotic","title":"Towards Generalizable Vision-Language Robotic Manipulation: A Benchmark and LLM-guided 3D Policy","date":"2024-10-02","arxiv_id":"2410.01345","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/towards-generalizable-vision-language-robotic#ran","syntology_url":"https://syntology.ai/paper/2410.01345","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.01345"}},"official":{"repos":["vlc-robot/robot-3dlotus"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/selp-generating-safe-and-efficient-task-plans","slug":"selp-generating-safe-and-efficient-task-plans","title":"SELP: Generating Safe and Efficient Task Plans for Robot Agents with Large Language Models","date":"2024-09-28","arxiv_id":"2409.19471","repositories_listed":1,"syntology":null},{"url":"/paper/coherent-collaboration-of-heterogeneous-multi","slug":"coherent-collaboration-of-heterogeneous-multi","title":"COHERENT: Collaboration of Heterogeneous Multi-Robot System with Large Language Models","date":"2024-09-23","arxiv_id":"2409.15146","repositories_listed":1,"syntology":null},{"url":"/paper/epd-long-term-memory-extraction-context","slug":"epd-long-term-memory-extraction-context","title":"EPD: Long-term Memory Extraction, Context-awared Planning and Multi-iteration Decision @ EgoPlan Challenge ICML 2024","date":"2024-07-28","arxiv_id":"2407.19510","repositories_listed":1,"syntology":{"n":4,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 4 unverified","sample_list":"/paper/epd-long-term-memory-extraction-context#ran","syntology_url":"https://syntology.ai/paper/2407.19510","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.19510"}},"official":{"repos":["kkskkkskr/epd"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":[]}}},{"url":"/paper/solving-robotics-problems-in-zero-shot-with","slug":"solving-robotics-problems-in-zero-shot-with","title":"Wonderful Team: Zero-Shot Physical Task Planning with Visual LLMs","date":"2024-07-26","arxiv_id":"2407.19094","repositories_listed":1,"syntology":null},{"url":"/paper/disco-embodied-navigation-and-interaction-via","slug":"disco-embodied-navigation-and-interaction-via","title":"DISCO: Embodied Navigation and Interaction via Differentiable Scene Semantics and Dual-level Control","date":"2024-07-20","arxiv_id":"2407.14758","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/disco-embodied-navigation-and-interaction-via#ran","syntology_url":"https://syntology.ai/paper/2407.14758","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.14758"}},"official":{"repos":["allenxuuu/disco"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/agentpoison-red-teaming-llm-agents-via","slug":"agentpoison-red-teaming-llm-agents-via","title":"AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases","date":"2024-07-17","arxiv_id":"2407.12784","repositories_listed":1,"syntology":{"n":19,"n_ran":16,"n_constructed":0,"n_ran_checked":12,"n_instrument":4,"n_unverified":3,"n_honours":5,"n_violates":1,"n_no_contract":6,"n_pointer_only":1,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 5 honoured, 1 violated, 6 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/agentpoison-red-teaming-llm-agents-via#ran","syntology_url":"https://syntology.ai/paper/2407.12784","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.12784"}},"official":{"repos":["BillChan226/AgentPoison"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/mfe-etp-a-comprehensive-evaluation-benchmark","slug":"mfe-etp-a-comprehensive-evaluation-benchmark","title":"MFE-ETP: A Comprehensive Evaluation Benchmark for Multi-modal Foundation Models on Embodied Task Planning","date":"2024-07-06","arxiv_id":"2407.05047","repositories_listed":1,"syntology":null},{"url":"/paper/diffusion-based-failure-sampling-for-cyber","slug":"diffusion-based-failure-sampling-for-cyber","title":"Diffusion-Based Failure Sampling for Evaluating Safety-Critical Autonomous Systems","date":"2024-06-20","arxiv_id":"2406.14761","repositories_listed":1,"syntology":null},{"url":"/paper/details-make-a-difference-object-state","slug":"details-make-a-difference-object-state","title":"Details Make a Difference: Object State-Sensitive Neurorobotic Task Planning","date":"2024-06-14","arxiv_id":"2406.09988","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/details-make-a-difference-object-state#ran","syntology_url":"https://syntology.ai/paper/2406.09988","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.09988"}},"official":{"repos":["xiao-wen-sun/ossa"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/rs-agent-automating-remote-sensing-tasks","slug":"rs-agent-automating-remote-sensing-tasks","title":"RS-Agent: Automating Remote Sensing Tasks through Intelligent Agent","date":"2024-06-11","arxiv_id":"2406.07089","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/rs-agent-automating-remote-sensing-tasks#ran","syntology_url":"https://syntology.ai/paper/2406.07089","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.07089"}},"official":{"repos":["intellisensing/rs-agent"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/tool-planner-dynamic-solution-tree-planning","slug":"tool-planner-dynamic-solution-tree-planning","title":"Tool-Planner: Task Planning with Clusters across Multiple Tools","date":"2024-06-06","arxiv_id":"2406.03807","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":1,"n_ran_checked":1,"n_instrument":6,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":9,"phrase":"7 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 6 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/tool-planner-dynamic-solution-tree-planning#ran","syntology_url":"https://syntology.ai/paper/2406.03807","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.03807"}},"official":{"repos":["OceannTwT/Tool-Planner"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/can-graph-learning-improve-task-planning","slug":"can-graph-learning-improve-task-planning","title":"Can Graph Learning Improve Planning in LLM-based Agents?","date":"2024-05-29","arxiv_id":"2405.19119","repositories_listed":1,"syntology":{"n":13,"n_ran":10,"n_constructed":0,"n_ran_checked":6,"n_instrument":4,"n_unverified":3,"n_honours":2,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 0 violated, 4 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/can-graph-learning-improve-task-planning#ran","syntology_url":"https://syntology.ai/paper/2405.19119","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.19119"}},"official":{"repos":["wxxshirley/gnn4taskplan"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/tool-learning-with-large-language-models-a","slug":"tool-learning-with-large-language-models-a","title":"Tool Learning with Large Language Models: A Survey","date":"2024-05-28","arxiv_id":"2405.17935","repositories_listed":1,"syntology":null},{"url":"/paper/meta-task-planning-for-language-agents","slug":"meta-task-planning-for-language-agents","title":"Planning with Multi-Constraints via Collaborative Language Agents","date":"2024-05-26","arxiv_id":"2405.16510","repositories_listed":1,"syntology":null},{"url":"/paper/learning-symbolic-task-representation-from-a","slug":"learning-symbolic-task-representation-from-a","title":"Learning Symbolic Task Representation from a Human-Led Demonstration: A Memory to Store, Retrieve, Consolidate, and Forget Experiences","date":"2024-04-16","arxiv_id":"2404.10591","repositories_listed":1,"syntology":null},{"url":"/paper/can-only-llms-do-reasoning-potential-of-small","slug":"can-only-llms-do-reasoning-potential-of-small","title":"Can only LLMs do Reasoning?: Potential of Small Language Models in Task Planning","date":"2024-04-05","arxiv_id":"2404.03891","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-the-general-agent-capabilities-of","slug":"enhancing-the-general-agent-capabilities-of","title":"Enhancing the General Agent Capabilities of Low-Parameter LLMs through Tuning and Multi-Branch Reasoning","date":"2024-03-29","arxiv_id":"2403.19962","repositories_listed":1,"syntology":{"n":4,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/enhancing-the-general-agent-capabilities-of#ran","syntology_url":"https://syntology.ai/paper/2403.19962","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.19962"}},"official":{"repos":["haiv-lab/llm-tmbr"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/llm-3-large-language-model-based-task-and","slug":"llm-3-large-language-model-based-task-and","title":"LLM3:Large Language Model-based Task and Motion Planning with Motion Failure Reasoning","date":"2024-03-18","arxiv_id":"2403.11552","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/llm-3-large-language-model-based-task-and#ran","syntology_url":"https://syntology.ai/paper/2403.11552","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.11552"}},"official":{"repos":["assassinws/llm-tamp"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/rat-retrieval-augmented-thoughts-elicit","slug":"rat-retrieval-augmented-thoughts-elicit","title":"RAT: Retrieval Augmented Thoughts Elicit Context-Aware Reasoning in Long-Horizon Generation","date":"2024-03-08","arxiv_id":"2403.05313","repositories_listed":1,"syntology":null},{"url":"/paper/lota-bench-benchmarking-language-oriented","slug":"lota-bench-benchmarking-language-oriented","title":"LoTa-Bench: Benchmarking Language-oriented Task Planners for Embodied Agents","date":"2024-02-13","arxiv_id":"2402.08178","repositories_listed":1,"syntology":{"n":10,"n_ran":8,"n_constructed":0,"n_ran_checked":2,"n_instrument":6,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":10,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 6 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/lota-bench-benchmarking-language-oriented#ran","syntology_url":"https://syntology.ai/paper/2402.08178","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.08178"}},"official":{"repos":["lbaa2022/llmtaskplanning"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/trustagent-towards-safe-and-trustworthy-llm","slug":"trustagent-towards-safe-and-trustworthy-llm","title":"TrustAgent: Towards Safe and Trustworthy LLM-based Agents","date":"2024-02-02","arxiv_id":"2402.01586","repositories_listed":1,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":4,"n_instrument":2,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":9,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/trustagent-towards-safe-and-trustworthy-llm#ran","syntology_url":"https://syntology.ai/paper/2402.01586","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.01586"}},"official":{"repos":["agiresearch/trustagent"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/remote-sensing-chatgpt-solving-remote-sensing","slug":"remote-sensing-chatgpt-solving-remote-sensing","title":"Remote Sensing ChatGPT: Solving Remote Sensing Tasks with ChatGPT and Visual Models","date":"2024-01-17","arxiv_id":"2401.09083","repositories_listed":1,"syntology":null},{"url":"/paper/small-llms-are-weak-tool-learners-a-multi-llm","slug":"small-llms-are-weak-tool-learners-a-multi-llm","title":"Small LLMs Are Weak Tool Learners: A Multi-LLM Agent","date":"2024-01-14","arxiv_id":"2401.07324","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":1,"n_ran_checked":1,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":6,"phrase":"4 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/small-llms-are-weak-tool-learners-a-multi-llm#ran","syntology_url":"https://syntology.ai/paper/2401.07324","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.07324"}},"official":{"repos":["x-plug/multi-llm-agent"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/egoplan-bench-benchmarking-egocentric","slug":"egoplan-bench-benchmarking-egocentric","title":"EgoPlan-Bench: Benchmarking Multimodal Large Language Models for Human-Level Planning","date":"2023-12-11","arxiv_id":"2312.06722","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":3,"n_instrument":4,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/egoplan-bench-benchmarking-egocentric#ran","syntology_url":"https://syntology.ai/paper/2312.06722","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.06722"}},"official":{"repos":["chenyi99/egoplan"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/planning-as-in-painting-a-diffusion-based","slug":"planning-as-in-painting-a-diffusion-based","title":"Planning as In-Painting: A Diffusion-Based Embodied Task Planning Framework for Environments under Uncertainty","date":"2023-12-02","arxiv_id":"2312.01097","repositories_listed":1,"syntology":{"n":11,"n_ran":6,"n_constructed":0,"n_ran_checked":4,"n_instrument":2,"n_unverified":5,"n_honours":2,"n_violates":0,"n_no_contract":2,"n_pointer_only":11,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/planning-as-in-painting-a-diffusion-based#ran","syntology_url":"https://syntology.ai/paper/2312.01097","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.01097"}},"official":{"repos":["joeyy5588/planning-as-inpainting"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/physical-reasoning-and-object-planning-for","slug":"physical-reasoning-and-object-planning-for","title":"Physical Reasoning and Object Planning for Household Embodied Agents","date":"2023-11-22","arxiv_id":"2311.13577","repositories_listed":1,"syntology":null},{"url":"/paper/a-language-agent-for-autonomous-driving","slug":"a-language-agent-for-autonomous-driving","title":"A Language Agent for Autonomous Driving","date":"2023-11-17","arxiv_id":"2311.10813","repositories_listed":1,"syntology":null},{"url":"/paper/vision-language-interpreter-for-robot-task","slug":"vision-language-interpreter-for-robot-task","title":"Vision-Language Interpreter for Robot Task Planning","date":"2023-11-02","arxiv_id":"2311.00967","repositories_listed":1,"syntology":null},{"url":"/paper/nngtl-neural-network-guided-optimal-temporal","slug":"nngtl-neural-network-guided-optimal-temporal","title":"NNgTL: Neural Network Guided Optimal Temporal Logic Task Planning for Mobile Robots","date":"2023-09-25","arxiv_id":"2309.14050","repositories_listed":1,"syntology":null},{"url":"/paper/recommender-ai-agent-integrating-large","slug":"recommender-ai-agent-integrating-large","title":"Recommender AI Agent: Integrating Large Language Models for Interactive Recommendations","date":"2023-08-31","arxiv_id":"2308.16505","repositories_listed":1,"syntology":null},{"url":"/paper/new-interaction-paradigm-for-complex-eda","slug":"new-interaction-paradigm-for-complex-eda","title":"New Interaction Paradigm for Complex EDA Software Leveraging GPT","date":"2023-07-27","arxiv_id":"2307.14740","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/new-interaction-paradigm-for-complex-eda#ran","syntology_url":"https://syntology.ai/paper/2307.14740","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.14740"}},"official":{"repos":["smarton-empower/smarton-ai"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/getting-pwn-d-by-ai-penetration-testing-with","slug":"getting-pwn-d-by-ai-penetration-testing-with","title":"Getting pwn'd by AI: Penetration Testing with Large Language Models","date":"2023-07-24","arxiv_id":"2308.00121","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/getting-pwn-d-by-ai-penetration-testing-with#ran","syntology_url":"https://syntology.ai/paper/2308.00121","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.00121"}},"official":{"repos":["ipa-lab/hackingBuddyGPT"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/embodied-task-planning-with-large-language","slug":"embodied-task-planning-with-large-language","title":"Embodied Task Planning with Large Language Models","date":"2023-07-04","arxiv_id":"2307.01848","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/embodied-task-planning-with-large-language#ran","syntology_url":"https://syntology.ai/paper/2307.01848","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.01848"}},"official":{"repos":["Gary3410/TaPA"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/skiros2-a-skill-based-robot-control-platform","slug":"skiros2-a-skill-based-robot-control-platform","title":"SkiROS2: A skill-based Robot Control Platform for ROS","date":"2023-06-29","arxiv_id":"2306.17030","repositories_listed":1,"syntology":null},{"url":"/paper/robot-task-planning-based-on-large-language","slug":"robot-task-planning-based-on-large-language","title":"Robot Task Planning Based on Large Language Model Representing Knowledge with Directed Graph Structures","date":"2023-06-08","arxiv_id":"2306.05171","repositories_listed":1,"syntology":null},{"url":"/paper/sheetcopilot-bringing-software-productivity","slug":"sheetcopilot-bringing-software-productivity","title":"SheetCopilot: Bringing Software Productivity to the Next Level through Large Language Models","date":"2023-05-30","arxiv_id":"2305.19308","repositories_listed":1,"syntology":null},{"url":"/paper/integrating-action-knowledge-and-llms-for","slug":"integrating-action-knowledge-and-llms-for","title":"Integrating Action Knowledge and LLMs for Task Planning and Situation Handling in Open Worlds","date":"2023-05-27","arxiv_id":"2305.17590","repositories_listed":1,"syntology":{"n":5,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":5,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/integrating-action-knowledge-and-llms-for#ran","syntology_url":"https://syntology.ai/paper/2305.17590","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.17590"}},"official":{"repos":["yding25/GPT-Planner"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/cross-modality-time-variant-relation-learning","slug":"cross-modality-time-variant-relation-learning","title":"Cross-Modality Time-Variant Relation Learning for Generating Dynamic Scene Graphs","date":"2023-05-15","arxiv_id":"2305.08522","repositories_listed":1,"syntology":null},{"url":"/paper/a-multi-modal-garden-dataset-and-hybrid-3d","slug":"a-multi-modal-garden-dataset-and-hybrid-3d","title":"A Multi-modal Garden Dataset and Hybrid 3D Dense Reconstruction Framework Based on Panoramic Stereo Images for a Trimming Robot","date":"2023-05-10","arxiv_id":"2305.06278","repositories_listed":1,"syntology":null},{"url":"/paper/hugginggpt-solving-ai-tasks-with-chatgpt-and","slug":"hugginggpt-solving-ai-tasks-with-chatgpt-and","title":"HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face","date":"2023-03-30","arxiv_id":"2303.17580","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/hugginggpt-solving-ai-tasks-with-chatgpt-and#ran","syntology_url":"https://syntology.ai/paper/2303.17580","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.17580"}},"official":{"repos":["microsoft/JARVIS"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/a-framework-to-generate-neurosymbolic-pddl","slug":"a-framework-to-generate-neurosymbolic-pddl","title":"A Framework for Neurosymbolic Robot Action Planning using Large Language Models","date":"2023-03-01","arxiv_id":"2303.00438","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/a-framework-to-generate-neurosymbolic-pddl#ran","syntology_url":"https://syntology.ai/paper/2303.00438","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.00438"}},"official":{"repos":["alessiocpt/teriyaki"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/describe-explain-plan-and-select-interactive","slug":"describe-explain-plan-and-select-interactive","title":"Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agents","date":"2023-02-03","arxiv_id":"2302.01560","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/describe-explain-plan-and-select-interactive#ran","syntology_url":"https://syntology.ai/paper/2302.01560","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.01560"}},"official":{"repos":["craftjarvis/mc-planner"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/multimedia-generative-script-learning-for","slug":"multimedia-generative-script-learning-for","title":"Multimedia Generative Script Learning for Task Planning","date":"2022-08-25","arxiv_id":"2208.12306","repositories_listed":1,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/multimedia-generative-script-learning-for#ran","syntology_url":"https://syntology.ai/paper/2208.12306","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.12306"}},"official":{"repos":["EagleW/Multimedia-Generative-Script-Learning-for-Task-Planning"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/taskography-evaluating-robot-task-planning","slug":"taskography-evaluating-robot-task-planning","title":"TASKOGRAPHY: Evaluating robot task planning over large 3D scene graphs","date":"2022-07-11","arxiv_id":"2207.05006","repositories_listed":1,"syntology":null},{"url":"/paper/planning-sequential-tasks-on-contact-graph","slug":"planning-sequential-tasks-on-contact-graph","title":"Sequential Manipulation Planning on Scene Graph","date":"2022-07-10","arxiv_id":"2207.04364","repositories_listed":1,"syntology":null},{"url":"/paper/sornet-spatial-object-centric-representations","slug":"sornet-spatial-object-centric-representations","title":"SORNet: Spatial Object-Centric Representations for Sequential Manipulation","date":"2021-09-08","arxiv_id":"2109.03891","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/sornet-spatial-object-centric-representations#ran","syntology_url":"https://syntology.ai/paper/2109.03891","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.03891"}},"official":{"repos":["wentaoyuan/sornet"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/mptp-motion-planning-aware-task-planning-for","slug":"mptp-motion-planning-aware-task-planning-for","title":"MPTP: Motion-Planning-aware Task Planning for Navigation in Belief Space","date":"2021-04-10","arxiv_id":"2104.04696","repositories_listed":1,"syntology":null},{"url":"/paper/knowledge-based-hierarchical-pomdps-for-task","slug":"knowledge-based-hierarchical-pomdps-for-task","title":"Knowledge-Based Hierarchical POMDPs for Task Planning","date":"2021-03-19","arxiv_id":"2103.10642","repositories_listed":1,"syntology":null},{"url":"/paper/extended-task-and-motion-planning-of-long","slug":"extended-task-and-motion-planning-of-long","title":"Extended Tree Search for Robot Task and Motion Planning","date":"2021-03-09","arxiv_id":"2103.05456","repositories_listed":1,"syntology":null},{"url":"/paper/enabling-visual-action-planning-for-object","slug":"enabling-visual-action-planning-for-object","title":"Enabling Visual Action Planning for Object Manipulation through Latent Space Roadmap","date":"2021-03-03","arxiv_id":"2103.02554","repositories_listed":1,"syntology":null},{"url":"/paper/actionet-an-interactive-end-to-end-platform","slug":"actionet-an-interactive-end-to-end-platform","title":"Actionet: An Interactive End-To-End Platform For Task-Based Data Collection And Augmentation In 3D Environment","date":"2020-10-03","arxiv_id":"2010.01357","repositories_listed":1,"syntology":null},{"url":"/paper/deployment-and-evaluation-of-a-flexible-human","slug":"deployment-and-evaluation-of-a-flexible-human","title":"Deployment and Evaluation of a Flexible Human-Robot Collaboration Model Based on AND/OR Graphs in a Manufacturing Environment","date":"2020-07-13","arxiv_id":"2007.06720","repositories_listed":1,"syntology":null},{"url":"/paper/combining-learned-skills-and-reinforcement","slug":"combining-learned-skills-and-reinforcement","title":"Learning to combine primitive skills: A step towards versatile robotic manipulation","date":"2019-08-02","arxiv_id":"1908.00722","repositories_listed":1,"syntology":null},{"url":"/paper/control-what-you-can-intrinsically-motivated","slug":"control-what-you-can-intrinsically-motivated","title":"Control What You Can: Intrinsically Motivated Task-Planning Agent","date":"2019-06-19","arxiv_id":"1906.08190","repositories_listed":1,"syntology":null},{"url":"/paper/functional-object-oriented-network-1","slug":"functional-object-oriented-network-1","title":"Task Planning with a Weighted Functional Object-Oriented Network","date":"2019-05-01","arxiv_id":"1905.00502","repositories_listed":1,"syntology":null},{"url":"/paper/vrkitchen-an-interactive-3d-virtual","slug":"vrkitchen-an-interactive-3d-virtual","title":"VRKitchen: an Interactive 3D Virtual Environment for Task-oriented Learning","date":"2019-03-13","arxiv_id":"1903.05757","repositories_listed":1,"syntology":null},{"url":"/paper/photo-realistic-blocksworld-dataset","slug":"photo-realistic-blocksworld-dataset","title":"Photo-Realistic Blocksworld Dataset","date":"2018-12-05","arxiv_id":"1812.01818","repositories_listed":1,"syntology":null},{"url":"/paper/visual-robot-task-planning","slug":"visual-robot-task-planning","title":"Visual Robot Task Planning","date":"2018-03-30","arxiv_id":"1804.00062","repositories_listed":1,"syntology":null}],"syntology_records":36,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_where_code_ran":35,"papers_where_code_ran_first_page":"/task/task-planning/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"archive","page":2,"of":4,"url":"/task/task-planning/papers/2","json":"/task/task-planning/papers/2.json","rows":100},{"order":"archive","page":3,"of":4,"url":"/task/task-planning/papers/3","json":"/task/task-planning/papers/3.json","rows":100},{"order":"archive","page":4,"of":4,"url":"/task/task-planning/papers/4","json":"/task/task-planning/papers/4.json","rows":44},{"order":"ran","page":1,"of":1,"url":"/task/task-planning/papers/ran/1","json":"/task/task-planning/papers/ran/1.json","rows":35}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"a00a413ac14babd1a4b93a8db1befa7135b403fa6ed846333f45009b92bc7237","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}