{"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/human-agent-collaboration","name":"Human Agent Collaboration","slug":"human-agent-collaboration","description_markdown":null,"categories":[{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"derived"},"counts":{"papers_tagged":22,"papers_with_code":10,"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":0,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[],"subtasks":[],"parent_tasks":[],"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":1,"rows_per_page":100,"shown":22,"of":22,"of_with_code":10,"tagged_in_all":22,"counts":{"archive_papers_tagged":22,"with_a_code_link":10,"where_syntology_ran_a_sample":2,"not_listed_spam_title":0,"listed":22,"listed_where_code_ran":2,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":2,"listed_every_run_a_failure_of_syntologys_instrument":0,"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/a-survey-on-large-language-model-based-human","slug":"a-survey-on-large-language-model-based-human","title":"A Survey on Large Language Model based Human-Agent Systems","date":"2025-05-01","arxiv_id":"2505.00753","repositories_listed":1,"syntology":null},{"url":"/paper/os-kairos-adaptive-interaction-for-mllm","slug":"os-kairos-adaptive-interaction-for-mllm","title":"OS-Kairos: Adaptive Interaction for MLLM-Powered GUI Agents","date":"2025-02-26","arxiv_id":"2503.16465","repositories_listed":1,"syntology":null},{"url":"/paper/collaborative-gym-a-framework-for-enabling","slug":"collaborative-gym-a-framework-for-enabling","title":"Collaborative Gym: A Framework for Enabling and Evaluating Human-Agent Collaboration","date":"2024-12-20","arxiv_id":"2412.15701","repositories_listed":1,"syntology":null},{"url":"/paper/proactive-agent-shifting-llm-agents-from","slug":"proactive-agent-shifting-llm-agents-from","title":"Proactive Agent: Shifting LLM Agents from Reactive Responses to Active Assistance","date":"2024-10-16","arxiv_id":"2410.12361","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":4,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"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) · 0 unverified","sample_list":"/paper/proactive-agent-shifting-llm-agents-from#ran","syntology_url":"https://syntology.ai/paper/2410.12361","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.12361"}},"official":{"repos":["thunlp/proactiveagent"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/bootstrapping-linear-models-for-fast-online","slug":"bootstrapping-linear-models-for-fast-online","title":"Bootstrapping Linear Models for Fast Online Adaptation in Human-Agent Collaboration","date":"2024-04-16","arxiv_id":"2404.10733","repositories_listed":1,"syntology":null},{"url":"/paper/embodied-llm-agents-learn-to-cooperate-in","slug":"embodied-llm-agents-learn-to-cooperate-in","title":"Embodied LLM Agents Learn to Cooperate in Organized Teams","date":"2024-03-19","arxiv_id":"2403.12482","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":1,"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; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/embodied-llm-agents-learn-to-cooperate-in#ran","syntology_url":"https://syntology.ai/paper/2403.12482","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.12482"}},"official":{"repos":["tobeatraceur/Organized-LLM-Agents"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/large-language-model-based-human-agent","slug":"large-language-model-based-human-agent","title":"Large Language Model-based Human-Agent Collaboration for Complex Task Solving","date":"2024-02-20","arxiv_id":"2402.12914","repositories_listed":1,"syntology":null},{"url":"/paper/causal-inference-for-chatting-handoff","slug":"causal-inference-for-chatting-handoff","title":"Causal Inference for Chatting Handoff","date":"2022-10-06","arxiv_id":"2210.02862","repositories_listed":1,"syntology":null},{"url":"/paper/toward-policy-explanations-for-multi-agent","slug":"toward-policy-explanations-for-multi-agent","title":"Toward Policy Explanations for Multi-Agent Reinforcement Learning","date":"2022-04-26","arxiv_id":"2204.12568","repositories_listed":1,"syntology":null},{"url":"/paper/modeling-human-ad-hoc-coordination","slug":"modeling-human-ad-hoc-coordination","title":"Modeling Human Ad Hoc Coordination","date":"2016-02-11","arxiv_id":"1602.03924","repositories_listed":1,"syntology":null},{"url":null,"slug":"embodied-ai-agents-modeling-the-world","title":"Embodied AI Agents: Modeling the World","date":"2025-06-27","arxiv_id":"2506.22355","repositories_listed":0,"syntology":null},{"url":null,"slug":"videe-visual-and-interactive-decomposition","title":"VIDEE: Visual and Interactive Decomposition, Execution, and Evaluation of Text Analytics with Intelligent Agents","date":"2025-06-17","arxiv_id":"2506.21582","repositories_listed":0,"syntology":null},{"url":null,"slug":"interaction-process-infrastructure-a-unified","title":"Interaction, Process, Infrastructure: A Unified Architecture for Human-Agent Collaboration","date":"2025-06-13","arxiv_id":"2506.11718","repositories_listed":0,"syntology":null},{"url":null,"slug":"facilitating-trustworthy-human-agent","title":"Facilitating Trustworthy Human-Agent Collaboration in LLM-based Multi-Agent System oriented Software Engineering","date":"2025-05-07","arxiv_id":"2505.04251","repositories_listed":0,"syntology":null},{"url":null,"slug":"verila-a-human-centered-evaluation-framework","title":"VeriLA: A Human-Centered Evaluation Framework for Interpretable Verification of LLM Agent Failures","date":"2025-03-16","arxiv_id":"2503.12651","repositories_listed":0,"syntology":null},{"url":null,"slug":"tabletalk-scaffolding-spreadsheet-development","title":"TableTalk: Scaffolding Spreadsheet Development with a Language Agent","date":"2025-02-13","arxiv_id":"2502.09787","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-explainable-goal-recognition-using","title":"Towards Explainable Goal Recognition Using Weight of Evidence (WoE): A Human-Centered Approach","date":"2024-09-18","arxiv_id":"2409.11675","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-human-experience-in-human-agent","title":"Enhancing Human Experience in Human-Agent Collaboration: A Human-Centered Modeling Approach Based on Positive Human Gain","date":"2024-01-28","arxiv_id":"2401.16444","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-abstract-specification-of-voxml-as-an","title":"An Abstract Specification of VoxML as an Annotation Language","date":"2023-05-22","arxiv_id":"2305.13076","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-effective-and-interpretable-human","title":"Towards Effective and Interpretable Human-Agent Collaboration in MOBA Games: A Communication Perspective","date":"2023-04-23","arxiv_id":"2304.11632","repositories_listed":0,"syntology":null},{"url":null,"slug":"i-don-t-think-so-disagreement-based-policy","title":"\"I Don't Think So\": Summarizing Policy Disagreements for Agent Comparison","date":"2021-02-05","arxiv_id":"2102.03064","repositories_listed":0,"syntology":null},{"url":null,"slug":"bayesian-inference-of-self-intention","title":"Bayesian Inference of Self-intention Attributed by Observer","date":"2018-10-12","arxiv_id":"1810.05564","repositories_listed":0,"syntology":null}],"syntology_records":2,"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":2,"papers_where_code_ran_first_page":"/task/human-agent-collaboration/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":"ran","page":1,"of":1,"url":"/task/human-agent-collaboration/papers/ran/1","json":"/task/human-agent-collaboration/papers/ran/1.json","rows":2}],"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":"bc5e3ac06b8f231bc827d787c129b7153cea9b9bd3810db7a4dd54b4e97b092d","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}