Papers with Code 아카이브
Mathematical Reasoning
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 7
- 평가표
- 11
- 보존된 평가 기록
- 41
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/mario-math-reasoning/mario
공식 코드MARIO: MAth Reasoning with code Interpreter Output -- A Reproducible Pipeline
https://github.com/mathllm/Step-Controlled_DPO
공식 코드Step-Controlled DPO: Leveraging Stepwise Error for Enhanced Mathematical Reasoning
https://github.com/mathllm/mathcoder
공식 코드MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical Reasoning
https://github.com/mathllm/mathcoder2
공식 코드MathCoder2: Better Math Reasoning from Continued Pretraining on Model-translated Mathematical Code
https://github.com/maxwellyaoni/pace
공식 코드PACE: Marrying generalization in PArameter-efficient fine-tuning with Consistency rEgularization
https://github.com/mehdiazarafza/uav-rag
공식 코드https://github.com/menik1126/TRIGO
공식 코드TRIGO: Benchmarking Formal Mathematical Proof Reduction for Generative Language Models
https://github.com/meta-math/MetaMath
공식 코드MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models
https://github.com/mghiasvand1/gap-filling-prompting
공식 코드Gap-Filling Prompting Enhances Code-Assisted Mathematical Reasoning
https://github.com/microsoft/DeBERTa
공식 코드https://github.com/microsoft/LoRA
공식 코드https://github.com/microsoft/MathOctopus
공식 코드Breaking Language Barriers in Multilingual Mathematical Reasoning: Insights and Observations
https://github.com/microsoft/lema
공식 코드https://github.com/microsoft/lmops
공식 코드https://github.com/microsoft/promptcraft-robotics
공식 코드https://github.com/microsoft/tora
공식 코드ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving
https://github.com/microsoft/unilm/tree/master/mathscale
공식 코드MathScale: Scaling Instruction Tuning for Mathematical Reasoning
https://github.com/midas-research/Multilingual-Mathematical-Reasoning
공식 코드Multilingual Mathematical Reasoning: Advancing Open-Source LLMs in Hindi and English
https://github.com/milkthink-lab/routereval
공식 코드RouterEval: A Comprehensive Benchmark for Routing LLMs to Explore Model-level Scaling Up in LLMs
https://github.com/mindhunter01/rmoa
공식 코드RMoA: Optimizing Mixture-of-Agents through Diversity Maximization and Residual Compensation
https://github.com/mingliangzhang2018/PGDP
공식 코드https://github.com/mingliangzhang2018/pgps
공식 코드A Multi-Modal Neural Geometric Solver with Textual Clauses Parsed from Diagram
https://github.com/minkjung/blankcollapse
공식 코드Blank Collapse: Compressing CTC emission for the faster decoding
https://github.com/minnesotanlp/mpo
공식 코드Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models
https://github.com/minwukim/GSM-Ranges
공식 코드https://github.com/mistralai/mistral-src
공식 코드https://github.com/modalminds/mm-prm
공식 코드MM-PRM: Enhancing Multimodal Mathematical Reasoning with Scalable Step-Level Supervision
https://github.com/moonshotai/kimi-vl
공식 코드https://github.com/mrflogs/LoRA-Pro
공식 코드https://github.com/multimodal-art-projection/criticlean
공식 코드CriticLean: Critic-Guided Reinforcement Learning for Mathematical Formalization
https://github.com/nativeatom/frog
공식 코드FRoG: Evaluating Fuzzy Reasoning of Generalized Quantifiers in Large Language Models
https://github.com/naumannaeem/bea_2025
공식 코드https://github.com/netease-youdao/confucius3-math
공식 코드Confucius3-Math: A Lightweight High-Performance Reasoning LLM for Chinese K-12 Mathematics Learning
https://github.com/neulab/gemini-benchmark
공식 코드https://github.com/neurasearch/geometry-diagram-description
공식 코드GOLD: Geometry Problem Solver with Natural Language Description
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.