CORE: Concept-Oriented Reinforcement for Bridging the Definition-Application Gap in Mathematical Reasoning
cs.AI, cs.LG
Submitted: 2025-12-21
Updated: 2026-11-17
Code: https://github.com/opendatalab/MinerU
Terminology
Sources
- Llemma: An Open Language Model For Mathematics
- Seed-Prover: Deep and Broad Reasoning for Automated Theorem Proving
- Training Verifiers to Solve Math Word Problems
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- BIRD: A Trustworthy Bayesian Inference Framework for Large Language Models
- Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
- Mathematical Proof as a Litmus Test: Revealing Failure Modes of Advanced Large Reasoning Models
- Right Is Not Enough: The Pitfalls of Outcome Supervision in Training LLMs for Math Reasoning
- Measuring Massive Multitask Language Understanding
- Winning Gold at IMO 2025 with a Model-Agnostic Verification-and-Refinement Pipeline
- Solving Quantitative Reasoning Problems with Language Models
- WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct
- A Diverse Corpus for Evaluating and Developing English Math Word Problem Solvers
- GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models
- OpenAI o1 System Card
- Are NLP Models really able to Solve Simple Math Word Problems?
- Decomposing Elements of Problem Solving: What "Math" Does RL Teach?
- Proximal Policy Optimization Algorithms
- HybridFlow: A Flexible and Efficient RLHF Framework
- Reasoning or Memorization? Unreliable Results of Reinforcement Learning Due to Data Contamination
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents