{"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/mathematical-problem-solving","name":"Mathematical Problem-Solving","slug":"mathematical-problem-solving","description_markdown":null,"categories":[],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":106,"papers_with_code":55,"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":2,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[{"url":"/dataset/theoremqa","name":"TheoremQA","full_name":"TheoremQA","num_papers_in_archive":40},{"url":"/dataset/asymob","name":"ASyMOB","full_name":"ASyMOB: Algebraic Symbolic Mathematical Operations Benchmark","num_papers_in_archive":1}],"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":2,"rows_per_page":100,"shown":100,"of":106,"of_with_code":55,"tagged_in_all":106,"counts":{"archive_papers_tagged":106,"with_a_code_link":55,"where_syntology_ran_a_sample":25,"not_listed_spam_title":0,"listed":106,"listed_where_code_ran":25,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":16,"every_run_a_failure_of_syntologys_instrument":9,"listed_with_a_run_with_no_instrument_failure":16,"listed_every_run_a_failure_of_syntologys_instrument":9,"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/measuring-mathematical-problem-solving-with","slug":"measuring-mathematical-problem-solving-with","title":"Measuring Mathematical Problem Solving With the MATH Dataset","date":"2021-03-05","arxiv_id":"2103.03874","repositories_listed":5,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"3 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; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/measuring-mathematical-problem-solving-with#ran","syntology_url":"https://syntology.ai/paper/2103.03874","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.03874"}},"official":{"repos":["hendrycks/math"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/hunyuan-large-an-open-source-moe-model-with","slug":"hunyuan-large-an-open-source-moe-model-with","title":"Hunyuan-Large: An Open-Source MoE Model with 52 Billion Activated Parameters by Tencent","date":"2024-11-04","arxiv_id":"2411.02265","repositories_listed":3,"syntology":null},{"url":"/paper/mavis-mathematical-visual-instruction-tuning","slug":"mavis-mathematical-visual-instruction-tuning","title":"MAVIS: Mathematical Visual Instruction Tuning with an Automatic Data Engine","date":"2024-07-11","arxiv_id":"2407.08739","repositories_listed":3,"syntology":null},{"url":"/paper/mathodyssey-benchmarking-mathematical-problem","slug":"mathodyssey-benchmarking-mathematical-problem","title":"MathOdyssey: Benchmarking Mathematical Problem-Solving Skills in Large Language Models Using Odyssey Math Data","date":"2024-06-26","arxiv_id":"2406.18321","repositories_listed":3,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"5 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; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/mathodyssey-benchmarking-mathematical-problem#ran","syntology_url":"https://syntology.ai/paper/2406.18321","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.18321"}},"official":null}},{"url":"/paper/chatglm-math-improving-math-problem-solving","slug":"chatglm-math-improving-math-problem-solving","title":"ChatGLM-Math: Improving Math Problem-Solving in Large Language Models with a Self-Critique Pipeline","date":"2024-04-03","arxiv_id":"2404.02893","repositories_listed":3,"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":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) · 3 unverified","sample_list":"/paper/chatglm-math-improving-math-problem-solving#ran","syntology_url":"https://syntology.ai/paper/2404.02893","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.02893"}},"official":{"repos":["thudm/chatglm-math"],"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/g-llava-solving-geometric-problem-with-multi","slug":"g-llava-solving-geometric-problem-with-multi","title":"G-LLaVA: Solving Geometric Problem with Multi-Modal Large Language Model","date":"2023-12-18","arxiv_id":"2312.11370","repositories_listed":3,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":6,"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) · 2 unverified","sample_list":"/paper/g-llava-solving-geometric-problem-with-multi#ran","syntology_url":"https://syntology.ai/paper/2312.11370","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.11370"}},"official":{"repos":["pipilurj/g-llava"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/solving-inequality-proofs-with-large-language","slug":"solving-inequality-proofs-with-large-language","title":"Solving Inequality Proofs with Large Language Models","date":"2025-06-09","arxiv_id":"2506.07927","repositories_listed":2,"syntology":{"n":10,"n_ran":9,"n_constructed":1,"n_ran_checked":5,"n_instrument":4,"n_unverified":1,"n_honours":0,"n_violates":4,"n_no_contract":1,"n_pointer_only":0,"phrase":"9 ran (of which 1 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 4 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/solving-inequality-proofs-with-large-language#ran","syntology_url":"https://syntology.ai/paper/2506.07927","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.07927"}},"official":{"repos":["lupantech/ineqmath"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":1,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/agent-rl-scaling-law-agent-rl-with","slug":"agent-rl-scaling-law-agent-rl-with","title":"Agent RL Scaling Law: Agent RL with Spontaneous Code Execution for Mathematical Problem Solving","date":"2025-05-12","arxiv_id":"2505.07773","repositories_listed":2,"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/agent-rl-scaling-law-agent-rl-with#ran","syntology_url":"https://syntology.ai/paper/2505.07773","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.07773"}},"official":{"repos":["anonymize-author/agentrl","yyht/openrlhf_async_pipline"],"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/evoagentx-an-automated-framework-for-evolving","slug":"evoagentx-an-automated-framework-for-evolving","title":"EvoAgentX: An Automated Framework for Evolving Agentic Workflows","date":"2025-07-04","arxiv_id":"2507.03616","repositories_listed":1,"syntology":{"n":20,"n_ran":19,"n_constructed":0,"n_ran_checked":11,"n_instrument":8,"n_unverified":1,"n_honours":2,"n_violates":3,"n_no_contract":6,"n_pointer_only":16,"phrase":"19 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 2 honoured, 3 violated, 6 with no contract checked; 8 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/evoagentx-an-automated-framework-for-evolving#ran","syntology_url":"https://syntology.ai/paper/2507.03616","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2507.03616"}},"official":{"repos":["evoagentx/evoagentx"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["found_in_text","official"]}}},{"url":"/paper/locationreasoner-evaluating-llms-on-real","slug":"locationreasoner-evaluating-llms-on-real","title":"LocationReasoner: Evaluating LLMs on Real-World Site Selection Reasoning","date":"2025-06-16","arxiv_id":"2506.13841","repositories_listed":1,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":1,"n_instrument":8,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":11,"phrase":"9 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; 8 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/locationreasoner-evaluating-llms-on-real#ran","syntology_url":"https://syntology.ai/paper/2506.13841","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.13841"}},"official":{"repos":["miho-koda/locationreasoner"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/sws-self-aware-weakness-driven-problem","slug":"sws-self-aware-weakness-driven-problem","title":"SwS: Self-aware Weakness-driven Problem Synthesis in Reinforcement Learning for LLM Reasoning","date":"2025-06-10","arxiv_id":"2506.08989","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/sws-self-aware-weakness-driven-problem#ran","syntology_url":"https://syntology.ai/paper/2506.08989","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.08989"}},"official":{"repos":["mastervito/sws"],"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/2506-06971","slug":"2506-06971","title":"Chain-of-Code Collapse: Reasoning Failures in LLMs via Adversarial Prompting in Code Generation","date":"2025-06-08","arxiv_id":"2506.06971","repositories_listed":1,"syntology":null},{"url":"/paper/morse-500-a-programmatically-controllable","slug":"morse-500-a-programmatically-controllable","title":"MORSE-500: A Programmatically Controllable Video Benchmark to Stress-Test Multimodal Reasoning","date":"2025-06-05","arxiv_id":"2506.05523","repositories_listed":1,"syntology":null},{"url":"/paper/decomposing-elements-of-problem-solving-what","slug":"decomposing-elements-of-problem-solving-what","title":"Decomposing Elements of Problem Solving: What \"Math\" Does RL Teach?","date":"2025-05-28","arxiv_id":"2505.22756","repositories_listed":1,"syntology":null},{"url":"/paper/error-typing-for-smarter-rewards-improving","slug":"error-typing-for-smarter-rewards-improving","title":"Error Typing for Smarter Rewards: Improving Process Reward Models with Error-Aware Hierarchical Supervision","date":"2025-05-26","arxiv_id":"2505.19706","repositories_listed":1,"syntology":null},{"url":"/paper/surrogate-signals-from-format-and-length","slug":"surrogate-signals-from-format-and-length","title":"Surrogate Signals from Format and Length: Reinforcement Learning for Solving Mathematical Problems without Ground Truth Answers","date":"2025-05-26","arxiv_id":"2505.19439","repositories_listed":1,"syntology":null},{"url":"/paper/rader-reasoning-aware-dense-retrieval-models","slug":"rader-reasoning-aware-dense-retrieval-models","title":"RaDeR: Reasoning-aware Dense Retrieval Models","date":"2025-05-23","arxiv_id":"2505.18405","repositories_listed":1,"syntology":null},{"url":"/paper/hardmath2-a-benchmark-for-applied-mathematics","slug":"hardmath2-a-benchmark-for-applied-mathematics","title":"HARDMath2: A Benchmark for Applied Mathematics Built by Students as Part of a Graduate Class","date":"2025-05-17","arxiv_id":"2505.11774","repositories_listed":1,"syntology":null},{"url":"/paper/pt-moe-an-efficient-finetuning-framework-for","slug":"pt-moe-an-efficient-finetuning-framework-for","title":"PT-MoE: An Efficient Finetuning Framework for Integrating Mixture-of-Experts into Prompt Tuning","date":"2025-05-14","arxiv_id":"2505.09519","repositories_listed":1,"syntology":null},{"url":"/paper/exploring-llm-reasoning-through-controlled","slug":"exploring-llm-reasoning-through-controlled","title":"Exploring LLM Reasoning Through Controlled Prompt Variations","date":"2025-04-02","arxiv_id":"2504.02111","repositories_listed":1,"syntology":null},{"url":"/paper/entropy-based-adaptive-weighting-for-self","slug":"entropy-based-adaptive-weighting-for-self","title":"Entropy-Based Adaptive Weighting for Self-Training","date":"2025-03-31","arxiv_id":"2503.23913","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 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; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/entropy-based-adaptive-weighting-for-self#ran","syntology_url":"https://syntology.ai/paper/2503.23913","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.23913"}},"official":{"repos":["mandyyyyii/east"],"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-survey-on-mathematical-reasoning-and","slug":"a-survey-on-mathematical-reasoning-and","title":"A Survey on Mathematical Reasoning and Optimization with Large Language Models","date":"2025-03-22","arxiv_id":"2503.17726","repositories_listed":1,"syntology":null},{"url":"/paper/does-chain-of-thought-reasoning-help-mobile","slug":"does-chain-of-thought-reasoning-help-mobile","title":"Does Chain-of-Thought Reasoning Help Mobile GUI Agent? An Empirical Study","date":"2025-03-21","arxiv_id":"2503.16788","repositories_listed":1,"syntology":null},{"url":"/paper/mathfusion-enhancing-mathematic-problem","slug":"mathfusion-enhancing-mathematic-problem","title":"MathFusion: Enhancing Mathematic Problem-solving of LLM through Instruction Fusion","date":"2025-03-20","arxiv_id":"2503.16212","repositories_listed":1,"syntology":{"n":18,"n_ran":13,"n_constructed":0,"n_ran_checked":4,"n_instrument":9,"n_unverified":5,"n_honours":2,"n_violates":1,"n_no_contract":1,"n_pointer_only":3,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 1 violated, 1 with no contract checked; 9 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/mathfusion-enhancing-mathematic-problem#ran","syntology_url":"https://syntology.ai/paper/2503.16212","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.16212"}},"official":{"repos":["qizhipei/mathfusion"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/mathflow-enhancing-the-perceptual-flow-of","slug":"mathflow-enhancing-the-perceptual-flow-of","title":"MathFlow: Enhancing the Perceptual Flow of MLLMs for Visual Mathematical Problems","date":"2025-03-19","arxiv_id":"2503.16549","repositories_listed":1,"syntology":null},{"url":"/paper/nexus-a-lightweight-and-scalable-multi-agent","slug":"nexus-a-lightweight-and-scalable-multi-agent","title":"Nexus: A Lightweight and Scalable Multi-Agent Framework for Complex Tasks Automation","date":"2025-02-26","arxiv_id":"2502.19091","repositories_listed":1,"syntology":null},{"url":"/paper/forgotten-polygons-multimodal-large-language","slug":"forgotten-polygons-multimodal-large-language","title":"Forgotten Polygons: Multimodal Large Language Models are Shape-Blind","date":"2025-02-21","arxiv_id":"2502.15969","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/forgotten-polygons-multimodal-large-language#ran","syntology_url":"https://syntology.ai/paper/2502.15969","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.15969"}},"official":{"repos":["rsinghlab/shape-blind"],"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","unlocated"]}}},{"url":"/paper/code-vision-evaluating-multimodal-llms-logic","slug":"code-vision-evaluating-multimodal-llms-logic","title":"Code-Vision: Evaluating Multimodal LLMs Logic Understanding and Code Generation Capabilities","date":"2025-02-17","arxiv_id":"2502.11829","repositories_listed":1,"syntology":null},{"url":"/paper/exposing-numeracy-gaps-a-benchmark-to","slug":"exposing-numeracy-gaps-a-benchmark-to","title":"Exposing Numeracy Gaps: A Benchmark to Evaluate Fundamental Numerical Abilities in Large Language Models","date":"2025-02-16","arxiv_id":"2502.11075","repositories_listed":1,"syntology":null},{"url":"/paper/adaptive-graph-of-thoughts-test-time-adaptive","slug":"adaptive-graph-of-thoughts-test-time-adaptive","title":"Adaptive Graph of Thoughts: Test-Time Adaptive Reasoning Unifying Chain, Tree, and Graph Structures","date":"2025-02-07","arxiv_id":"2502.05078","repositories_listed":1,"syntology":null},{"url":"/paper/open-eyes-then-reason-fine-grained-visual","slug":"open-eyes-then-reason-fine-grained-visual","title":"Open Eyes, Then Reason: Fine-grained Visual Mathematical Understanding in MLLMs","date":"2025-01-11","arxiv_id":"2501.06430","repositories_listed":1,"syntology":null},{"url":"/paper/voxeval-benchmarking-the-knowledge","slug":"voxeval-benchmarking-the-knowledge","title":"VoxEval: Benchmarking the Knowledge Understanding Capabilities of End-to-End Spoken Language Models","date":"2025-01-09","arxiv_id":"2501.04962","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"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; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/voxeval-benchmarking-the-knowledge#ran","syntology_url":"https://syntology.ai/paper/2501.04962","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.04962"}},"official":{"repos":["dreamtheater123/voxeval"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/efficiently-serving-llm-reasoning-programs","slug":"efficiently-serving-llm-reasoning-programs","title":"Efficiently Serving LLM Reasoning Programs with Certaindex","date":"2024-12-30","arxiv_id":"2412.20993","repositories_listed":1,"syntology":null},{"url":"/paper/large-language-models-for-mathematical-1","slug":"large-language-models-for-mathematical-1","title":"Large Language Models for Mathematical Analysis","date":"2024-12-28","arxiv_id":"2501.00059","repositories_listed":1,"syntology":null},{"url":"/paper/training-and-evaluating-language-models-with","slug":"training-and-evaluating-language-models-with","title":"Training and Evaluating Language Models with Template-based Data Generation","date":"2024-11-27","arxiv_id":"2411.18104","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":1,"n_honours":0,"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; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/training-and-evaluating-language-models-with#ran","syntology_url":"https://syntology.ai/paper/2411.18104","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.18104"}},"official":{"repos":["iiis-ai/templatemath"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/o1-replication-journey-part-2-surpassing-o1","slug":"o1-replication-journey-part-2-surpassing-o1","title":"O1 Replication Journey -- Part 2: Surpassing O1-preview through Simple Distillation, Big Progress or Bitter Lesson?","date":"2024-11-25","arxiv_id":"2411.16489","repositories_listed":1,"syntology":null},{"url":"/paper/language-model-non-myopic-generation-for","slug":"language-model-non-myopic-generation-for","title":"Non-myopic Generation of Language Models for Reasoning and Planning","date":"2024-10-22","arxiv_id":"2410.17195","repositories_listed":1,"syntology":null},{"url":"/paper/llama-berry-pairwise-optimization-for-o1-like","slug":"llama-berry-pairwise-optimization-for-o1-like","title":"LLaMA-Berry: Pairwise Optimization for O1-like Olympiad-Level Mathematical Reasoning","date":"2024-10-03","arxiv_id":"2410.02884","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":1,"n_instrument":5,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":6,"phrase":"6 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; 5 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/llama-berry-pairwise-optimization-for-o1-like#ran","syntology_url":"https://syntology.ai/paper/2410.02884","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.02884"}},"official":null}},{"url":"/paper/beats-optimizing-llm-mathematical","slug":"beats-optimizing-llm-mathematical","title":"BEATS: Optimizing LLM Mathematical Capabilities with BackVerify and Adaptive Disambiguate based Efficient Tree Search","date":"2024-09-26","arxiv_id":"2409.17972","repositories_listed":1,"syntology":null},{"url":"/paper/benchmarking-large-language-models-for-math","slug":"benchmarking-large-language-models-for-math","title":"Benchmarking Large Language Models for Math Reasoning Tasks","date":"2024-08-20","arxiv_id":"2408.10839","repositories_listed":1,"syntology":null},{"url":"/paper/mathcamps-fine-grained-synthesis-of","slug":"mathcamps-fine-grained-synthesis-of","title":"MathCAMPS: Fine-grained Synthesis of Mathematical Problems From Human Curricula","date":"2024-07-01","arxiv_id":"2407.00900","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":1,"n_instrument":7,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"8 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; 7 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/mathcamps-fine-grained-synthesis-of#ran","syntology_url":"https://syntology.ai/paper/2407.00900","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.00900"}},"official":{"repos":["gpoesia/mathcamps"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/math-llava-bootstrapping-mathematical","slug":"math-llava-bootstrapping-mathematical","title":"Math-LLaVA: Bootstrapping Mathematical Reasoning for Multimodal Large Language Models","date":"2024-06-25","arxiv_id":"2406.17294","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 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; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/math-llava-bootstrapping-mathematical#ran","syntology_url":"https://syntology.ai/paper/2406.17294","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.17294"}},"official":{"repos":["hzq950419/math-llava"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/dart-math-difficulty-aware-rejection-tuning-1","slug":"dart-math-difficulty-aware-rejection-tuning-1","title":"DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving","date":"2024-06-18","arxiv_id":"2407.13690","repositories_listed":1,"syntology":{"n":12,"n_ran":10,"n_constructed":0,"n_ran_checked":2,"n_instrument":8,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"10 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; 8 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/dart-math-difficulty-aware-rejection-tuning-1#ran","syntology_url":"https://syntology.ai/paper/2407.13690","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.13690"}},"official":{"repos":["hkust-nlp/dart-math"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/gw-moe-resolving-uncertainty-in-moe-router","slug":"gw-moe-resolving-uncertainty-in-moe-router","title":"GW-MoE: Resolving Uncertainty in MoE Router with Global Workspace Theory","date":"2024-06-18","arxiv_id":"2406.12375","repositories_listed":1,"syntology":null},{"url":"/paper/mathchat-benchmarking-mathematical-reasoning","slug":"mathchat-benchmarking-mathematical-reasoning","title":"MathChat: Benchmarking Mathematical Reasoning and Instruction Following in Multi-Turn Interactions","date":"2024-05-29","arxiv_id":"2405.19444","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/mathchat-benchmarking-mathematical-reasoning#ran","syntology_url":"https://syntology.ai/paper/2405.19444","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.19444"}},"official":{"repos":["zhenwen-nlp/mathchat"],"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/insights-into-alignment-evaluating-dpo-and","slug":"insights-into-alignment-evaluating-dpo-and","title":"Insights into Alignment: Evaluating DPO and its Variants Across Multiple Tasks","date":"2024-04-23","arxiv_id":"2404.14723","repositories_listed":1,"syntology":null},{"url":"/paper/mathify-evaluating-large-language-models-on","slug":"mathify-evaluating-large-language-models-on","title":"Mathify: Evaluating Large Language Models on Mathematical Problem Solving Tasks","date":"2024-04-19","arxiv_id":"2404.13099","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/mathify-evaluating-large-language-models-on#ran","syntology_url":"https://syntology.ai/paper/2404.13099","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.13099"}},"official":{"repos":["midas-research/mathify"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/can-llms-master-math-investigating-large","slug":"can-llms-master-math-investigating-large","title":"Can LLMs Master Math? Investigating Large Language Models on Math Stack Exchange","date":"2024-03-30","arxiv_id":"2404.00344","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":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) · 3 unverified","sample_list":"/paper/can-llms-master-math-investigating-large#ran","syntology_url":"https://syntology.ai/paper/2404.00344","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.00344"}},"official":{"repos":["gipplab/llm-investig-mathstackexchange"],"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/pctoolkit-a-unified-plug-and-play-prompt","slug":"pctoolkit-a-unified-plug-and-play-prompt","title":"PCToolkit: A Unified Plug-and-Play Prompt Compression Toolkit of Large Language Models","date":"2024-03-26","arxiv_id":"2403.17411","repositories_listed":1,"syntology":null},{"url":"/paper/smalltolarge-s2l-scalable-data-selection-for","slug":"smalltolarge-s2l-scalable-data-selection-for","title":"SmallToLarge (S2L): Scalable Data Selection for Fine-tuning Large Language Models by Summarizing Training Trajectories of Small Models","date":"2024-03-12","arxiv_id":"2403.07384","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"4 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; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/smalltolarge-s2l-scalable-data-selection-for#ran","syntology_url":"https://syntology.ai/paper/2403.07384","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.07384"}},"official":{"repos":["bigml-cs-ucla/s2l"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/data-contamination-through-the-lens-of-time","slug":"data-contamination-through-the-lens-of-time","title":"Data Contamination Through the Lens of Time","date":"2023-10-16","arxiv_id":"2310.10628","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/data-contamination-through-the-lens-of-time#ran","syntology_url":"https://syntology.ai/paper/2310.10628","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.10628"}},"official":{"repos":["abacusai/to-the-cutoff"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/tora-a-tool-integrated-reasoning-agent-for","slug":"tora-a-tool-integrated-reasoning-agent-for","title":"ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving","date":"2023-09-29","arxiv_id":"2309.17452","repositories_listed":1,"syntology":{"n":12,"n_ran":11,"n_constructed":0,"n_ran_checked":5,"n_instrument":6,"n_unverified":1,"n_honours":0,"n_violates":2,"n_no_contract":3,"n_pointer_only":9,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 2 violated, 3 with no contract checked; 6 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/tora-a-tool-integrated-reasoning-agent-for#ran","syntology_url":"https://syntology.ai/paper/2309.17452","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.17452"}},"official":{"repos":["microsoft/tora"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/evaluating-language-models-for-mathematics","slug":"evaluating-language-models-for-mathematics","title":"Evaluating Language Models for Mathematics through Interactions","date":"2023-06-02","arxiv_id":"2306.01694","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":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/evaluating-language-models-for-mathematics#ran","syntology_url":"https://syntology.ai/paper/2306.01694","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.01694"}},"official":{"repos":["collinskatie/checkmate"],"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/a-systematic-study-and-comprehensive","slug":"a-systematic-study-and-comprehensive","title":"A Systematic Study and Comprehensive Evaluation of ChatGPT on Benchmark Datasets","date":"2023-05-29","arxiv_id":"2305.18486","repositories_listed":1,"syntology":null},{"url":"/paper/abstractors-transformer-modules-for-symbolic","slug":"abstractors-transformer-modules-for-symbolic","title":"Abstractors and relational cross-attention: An inductive bias for explicit relational reasoning in Transformers","date":"2023-04-01","arxiv_id":"2304.00195","repositories_listed":1,"syntology":{"n":12,"n_ran":9,"n_constructed":5,"n_ran_checked":6,"n_instrument":3,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":5,"n_pointer_only":12,"phrase":"9 ran (of which 5 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/abstractors-transformer-modules-for-symbolic#ran","syntology_url":"https://syntology.ai/paper/2304.00195","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.00195"}},"official":{"repos":["awni00/abstractor"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":5,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":null,"slug":"telemath-a-benchmark-for-large-language","title":"TeleMath: A Benchmark for Large Language Models in Telecom Mathematical Problem Solving","date":"2025-06-12","arxiv_id":"2506.10674","repositories_listed":0,"syntology":null},{"url":null,"slug":"polar-polar-decomposed-low-rank-adapter","title":"PoLAR: Polar-Decomposed Low-Rank Adapter Representation","date":"2025-06-03","arxiv_id":"2506.03133","repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluation-of-llms-for-mathematical-problem","title":"Evaluation of LLMs for mathematical problem solving","date":"2025-05-30","arxiv_id":"2506.00309","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-reasoning-models-comprehend-mathematical","title":"Can reasoning models comprehend mathematical problems in Chinese ancient texts? An empirical study based on data from Suanjing Shishu","date":"2025-05-22","arxiv_id":"2505.16660","repositories_listed":0,"syntology":null},{"url":null,"slug":"smart-self-generating-and-self-validating","title":"SMART: Self-Generating and Self-Validating Multi-Dimensional Assessment for LLMs' Mathematical Problem Solving","date":"2025-05-22","arxiv_id":"2505.16646","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-spoken-mathematical-reasoning","title":"Towards Spoken Mathematical Reasoning: Benchmarking Speech-based Models over Multi-faceted Math Problems","date":"2025-05-21","arxiv_id":"2505.15000","repositories_listed":0,"syntology":null},{"url":null,"slug":"2505-10937","title":"Reasoning with OmniThought: A Large CoT Dataset with Verbosity and Cognitive Difficulty Annotations","date":"2025-05-16","arxiv_id":"2505.10937","repositories_listed":0,"syntology":null},{"url":null,"slug":"2505-11227","title":"Is PRM Necessary? Problem-Solving RL Implicitly Induces PRM Capability in LLMs","date":"2025-05-16","arxiv_id":"2505.11227","repositories_listed":0,"syntology":null},{"url":null,"slug":"reasoning-models-can-be-effective-without","title":"Reasoning Models Can Be Effective Without Thinking","date":"2025-04-14","arxiv_id":"2504.09858","repositories_listed":0,"syntology":null},{"url":null,"slug":"holistic-capability-preservation-towards","title":"Holistic Capability Preservation: Towards Compact Yet Comprehensive Reasoning Models","date":"2025-04-09","arxiv_id":"2504.07158","repositories_listed":0,"syntology":null},{"url":null,"slug":"learnat-learning-nl2sql-with-ast-guided-task","title":"LearNAT: Learning NL2SQL with AST-guided Task Decomposition for Large Language Models","date":"2025-04-03","arxiv_id":"2504.02327","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-vanishing-variance-in-transformer-length","title":"On Vanishing Variance in Transformer Length Generalization","date":"2025-04-03","arxiv_id":"2504.02827","repositories_listed":0,"syntology":null},{"url":null,"slug":"brains-vs-bytes-evaluating-llm-proficiency-in","title":"Brains vs. Bytes: Evaluating LLM Proficiency in Olympiad Mathematics","date":"2025-04-01","arxiv_id":"2504.01995","repositories_listed":0,"syntology":null},{"url":null,"slug":"mathagent-leveraging-a-mixture-of-math-agent","title":"MathAgent: Leveraging a Mixture-of-Math-Agent Framework for Real-World Multimodal Mathematical Error Detection","date":"2025-03-23","arxiv_id":"2503.18132","repositories_listed":0,"syntology":null},{"url":null,"slug":"performance-comparison-of-large-language-1","title":"Performance Comparison of Large Language Models on Advanced Calculus Problems","date":"2025-03-05","arxiv_id":"2503.03960","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-evolved-preference-optimization-for","title":"Self-Evolved Preference Optimization for Enhancing Mathematical Reasoning in Small Language Models","date":"2025-03-04","arxiv_id":"2503.04813","repositories_listed":0,"syntology":null},{"url":null,"slug":"secura-sigmoid-enhanced-cur-decomposition","title":"SECURA: Sigmoid-Enhanced CUR Decomposition with Uninterrupted Retention and Low-Rank Adaptation in Large Language Models","date":"2025-02-25","arxiv_id":"2502.18168","repositories_listed":0,"syntology":null},{"url":null,"slug":"how-do-large-language-monkeys-get-their-power","title":"How Do Large Language Monkeys Get Their Power (Laws)?","date":"2025-02-24","arxiv_id":"2502.17578","repositories_listed":0,"syntology":null},{"url":null,"slug":"navigating-semantic-relations-challenges-for","title":"Navigating Semantic Relations: Challenges for Language Models in Abstract Common-Sense Reasoning","date":"2025-02-19","arxiv_id":"2502.14086","repositories_listed":0,"syntology":null},{"url":null,"slug":"mathfimer-enhancing-mathematical-reasoning-by","title":"MathFimer: Enhancing Mathematical Reasoning by Expanding Reasoning Steps through Fill-in-the-Middle Task","date":"2025-02-17","arxiv_id":"2502.11684","repositories_listed":0,"syntology":null},{"url":null,"slug":"scaling-autonomous-agents-via-automatic","title":"Scaling Autonomous Agents via Automatic Reward Modeling And Planning","date":"2025-02-17","arxiv_id":"2502.12130","repositories_listed":0,"syntology":null},{"url":null,"slug":"strive-structured-reasoning-for-self","title":"STRIVE: Structured Reasoning for Self-Improvement in Claim Verification","date":"2025-02-17","arxiv_id":"2502.11959","repositories_listed":0,"syntology":null},{"url":null,"slug":"teaching-llms-according-to-their-aptitude","title":"Teaching LLMs According to Their Aptitude: Adaptive Reasoning for Mathematical Problem Solving","date":"2025-02-17","arxiv_id":"2502.12022","repositories_listed":0,"syntology":null},{"url":null,"slug":"advancing-reasoning-in-large-language-models","title":"Advancing Reasoning in Large Language Models: Promising Methods and Approaches","date":"2025-02-05","arxiv_id":"2502.03671","repositories_listed":0,"syntology":null},{"url":null,"slug":"automating-mathematical-proof-generation","title":"Automating Mathematical Proof Generation Using Large Language Model Agents and Knowledge Graphs","date":"2025-02-04","arxiv_id":"2503.11657","repositories_listed":0,"syntology":null},{"url":null,"slug":"token-hungry-yet-precise-deepseek-r1","title":"Token-Hungry, Yet Precise: DeepSeek R1 Highlights the Need for Multi-Step Reasoning Over Speed in MATH","date":"2025-01-30","arxiv_id":"2501.18576","repositories_listed":0,"syntology":null},{"url":null,"slug":"token-by-token-regeneration-and-domain-biases","title":"Token-by-Token Regeneration and Domain Biases: A Benchmark of LLMs on Advanced Mathematical Problem-Solving","date":"2025-01-28","arxiv_id":"2501.17084","repositories_listed":0,"syntology":null},{"url":null,"slug":"kwai-star-transform-llms-into-state","title":"Kwai-STaR: Transform LLMs into State-Transition Reasoners","date":"2024-11-07","arxiv_id":"2411.04799","repositories_listed":0,"syntology":null},{"url":null,"slug":"visaidmath-benchmarking-visual-aided","title":"VisAidMath: Benchmarking Visual-Aided Mathematical Reasoning","date":"2024-10-30","arxiv_id":"2410.22995","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-small-scale-large-language-models","title":"Improving Small-Scale Large Language Models Function Calling for Reasoning Tasks","date":"2024-10-24","arxiv_id":"2410.18890","repositories_listed":0,"syntology":null},{"url":null,"slug":"fine-grained-hallucination-detection-and-2","title":"FG-PRM: Fine-grained Hallucination Detection and Mitigation in Language Model Mathematical Reasoning","date":"2024-10-08","arxiv_id":"2410.06304","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-llms-plan-paths-with-extra-hints-from","title":"Can LLMs plan paths with extra hints from solvers?","date":"2024-10-07","arxiv_id":"2410.05045","repositories_listed":0,"syntology":null},{"url":null,"slug":"personamath-enhancing-math-reasoning-through","title":"PersonaMath: Enhancing Math Reasoning through Persona-Driven Data Augmentation","date":"2024-10-02","arxiv_id":"2410.01504","repositories_listed":0,"syntology":null},{"url":null,"slug":"building-math-agents-with-multi-turn","title":"Building Math Agents with Multi-Turn Iterative Preference Learning","date":"2024-09-04","arxiv_id":"2409.02392","repositories_listed":0,"syntology":null},{"url":null,"slug":"logic-contrastive-reasoning-with-lightweight","title":"Logic Contrastive Reasoning with Lightweight Large Language Model for Math Word Problems","date":"2024-08-29","arxiv_id":"2409.00131","repositories_listed":0,"syntology":null},{"url":null,"slug":"exposing-the-achilles-heel-evaluating-llms","title":"Exposing the Achilles' Heel: Evaluating LLMs Ability to Handle Mistakes in Mathematical Reasoning","date":"2024-06-16","arxiv_id":"2406.10834","repositories_listed":0,"syntology":null},{"url":null,"slug":"3d-properties-identifying-challenges-in-dpo","title":"3D-Properties: Identifying Challenges in DPO and Charting a Path Forward","date":"2024-06-11","arxiv_id":"2406.07327","repositories_listed":0,"syntology":null},{"url":null,"slug":"occamllm-fast-and-exact-language-model","title":"OccamLLM: Fast and Exact Language Model Arithmetic in a Single Step","date":"2024-06-04","arxiv_id":"2406.06576","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-understanding-how-transformer-perform","title":"The Buffer Mechanism for Multi-Step Information Reasoning in Language Models","date":"2024-05-24","arxiv_id":"2405.15302","repositories_listed":0,"syntology":null},{"url":null,"slug":"metacognitive-capabilities-of-llms-an","title":"Metacognitive Capabilities of LLMs: An Exploration in Mathematical Problem Solving","date":"2024-05-20","arxiv_id":"2405.12205","repositories_listed":0,"syntology":null},{"url":null,"slug":"mixture-of-instructions-comprehensive","title":"Mixture-of-Instructions: Comprehensive Alignment of a Large Language Model through the Mixture of Diverse System Prompting Instructions","date":"2024-04-29","arxiv_id":"2404.18410","repositories_listed":0,"syntology":null},{"url":null,"slug":"premise-order-matters-in-reasoning-with-large","title":"Premise Order Matters in Reasoning with Large Language Models","date":"2024-02-14","arxiv_id":"2402.08939","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-language-models-for-mathematical","title":"Large Language Models for Mathematical Reasoning: Progresses and Challenges","date":"2024-01-31","arxiv_id":"2402.00157","repositories_listed":0,"syntology":null},{"url":null,"slug":"three-questions-concerning-the-use-of-large","title":"Three Questions Concerning the Use of Large Language Models to Facilitate Mathematics Learning","date":"2023-10-20","arxiv_id":"2310.13615","repositories_listed":0,"syntology":null},{"url":null,"slug":"sego-sequential-subgoal-optimization-for","title":"SEGO: Sequential Subgoal Optimization for Mathematical Problem-Solving","date":"2023-10-19","arxiv_id":"2310.12960","repositories_listed":0,"syntology":null}],"syntology_records":26,"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":25,"papers_where_code_ran_first_page":"/task/mathematical-problem-solving/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":2,"url":"/task/mathematical-problem-solving/papers/2","json":"/task/mathematical-problem-solving/papers/2.json","rows":6},{"order":"ran","page":1,"of":1,"url":"/task/mathematical-problem-solving/papers/ran/1","json":"/task/mathematical-problem-solving/papers/ran/1.json","rows":25}],"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":"2a2151fcefcaec106e06f11d296bf8c5df7e0d20fce7441741e81fbd24253e87","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}