Papers with Code 아카이브
Mathematical Reasoning
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 7
- 평가표
- 11
- 보존된 평가 기록
- 41
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Unlocking the Potential of Difficulty Prior in RL-based Multimodal Reasoning
AutoMathKG: The automated mathematical knowledge graph based on LLM and vector database
MM-PRM: Enhancing Multimodal Mathematical Reasoning with Scalable Step-Level Supervision
Trust, But Verify: A Self-Verification Approach to Reinforcement Learning with Verifiable Rewards
Guided Search Strategies in Non-Serializable Environments with Applications to Software Engineering Agents
Causal Head Gating: A Framework for Interpreting Roles of Attention Heads in Transformers
SEED-GRPO: Semantic Entropy Enhanced GRPO for Uncertainty-Aware Policy Optimization
DisCO: Reinforcing Large Reasoning Models with Discriminative Constrained Optimization
MARGE: Improving Math Reasoning for LLMs with Guided Exploration
RealMath: A Continuous Benchmark for Evaluating Language Models on Research-Level Mathematics
HARDMath2: A Benchmark for Applied Mathematics Built by Students as Part of a Graduate Class
Group-in-Group Policy Optimization for LLM Agent Training
Scaling Reasoning can Improve Factuality in Large Language Models
Real-Time Verification of Embodied Reasoning for Generative Skill Acquisition
Token-Level Uncertainty Estimation for Large Language Model Reasoning
Reasoning on a Budget: Miniaturizing DeepSeek R1 with SFT-GRPO Alignment for Instruction-Tuned LLMs
ComplexFormer: Disruptively Advancing Transformer Inference Ability via Head-Specific Complex Vector Attention
Are Large Language Models Robust in Understanding Code Against Semantics-Preserving Mutations?
MathCoder-VL: Bridging Vision and Code for Enhanced Multimodal Mathematical Reasoning
Qwen3 Technical Report
DRA-GRPO: Exploring Diversity-Aware Reward Adjustment for R1-Zero-Like Training of Large Language Models
Learning Like Humans: Advancing LLM Reasoning Capabilities via Adaptive Difficulty Curriculum Learning and Expert-Guided Self-Reformulation
Agent-as-a-Service based on Agent Network
Agent RL Scaling Law: Agent RL with Spontaneous Code Execution for Mathematical Problem Solving
Assessing Robustness to Spurious Correlations in Post-Training Language Models
Crosslingual Reasoning through Test-Time Scaling
Absolute Zero: Reinforced Self-play Reasoning with Zero Data
Knowledge Augmented Complex Problem Solving with Large Language Models: A Survey
Optimizing Chain-of-Thought Reasoners via Gradient Variance Minimization in Rejection Sampling and RL
FormalMATH: Benchmarking Formal Mathematical Reasoning of Large Language Models
Rewriting Pre-Training Data Boosts LLM Performance in Math and Code
DeepSeek-Prover-V2: Advancing Formal Mathematical Reasoning via Reinforcement Learning for Subgoal Decomposition
RV-Syn: Rational and Verifiable Mathematical Reasoning Data Synthesis based on Structured Function Library
Reinforcement Learning for Reasoning in Large Language Models with One Training Example
Beyond the Last Answer: Your Reasoning Trace Uncovers More than You Think
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.