ReSI-Math: Exploring Recoverable Capability Frontiers for Efficient Reasoning Improvement
cs.CL, cs.AI
Submitted: 2026-11-03
Updated: 2026-11-03
Terminology
Sources
- Training Verifiers to Solve Math Word Problems
- Rethinking On-Policy Distillation of Large Language Models II: One Training Example
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems
- Measuring Mathematical Problem Solving With the MATH Dataset
- Large-Scale Data Selection for Instruction Tuning
- LIMR: Less is More for RL Scaling
- Self-Refine: Iterative Refinement with Self-Feedback
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Resource-Efficient Reinforcement for Reasoning Large Language Models via Dynamic One-Shot Policy Refinement
- Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data