{"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 (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":55,"tagged_in_all":106,"items":[{"url":"/paper/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_unverified":0,"n_pointer_only":1}},{"url":"/paper/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","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","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":1,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/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_unverified":3,"n_pointer_only":0}},{"url":"/paper/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_unverified":2,"n_pointer_only":6}},{"url":"/paper/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_unverified":1,"n_pointer_only":0}},{"url":"/paper/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_unverified":0,"n_pointer_only":0}},{"url":"/paper/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":0,"n_unverified":20,"n_pointer_only":16}},{"url":"/paper/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":0,"n_unverified":11,"n_pointer_only":11}},{"url":"/paper/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_unverified":0,"n_pointer_only":1}},{"url":"/paper/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","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","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/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/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/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","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","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","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","title":"Entropy-Based Adaptive Weighting for Self-Training","date":"2025-03-31","arxiv_id":"2503.23913","repositories_listed":1,"syntology":{"n":3,"n_ran":0,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/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","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","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":10,"n_unverified":8,"n_pointer_only":0}},{"url":"/paper/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","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","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_unverified":0,"n_pointer_only":2}},{"url":"/paper/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","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","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}],"syntology_records":12,"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"},"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":"2026-09-24T18:15:14+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; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"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"}}