Multi-Agent Evolve: LLM Self-Improve through Co-evolution
"推理能力提升" 相关文章
First Try Matters: Revisiting the Role of Reflection in Reasoning Models
MALT: Improving Reasoning with Multi-Agent LLM Training
Distilling Reasoning into Student LLMs: Local Naturalness for Selecting Teacher Data
Expanding Reasoning Potential in Foundation Model by Learning Diverse Chains of Thought Patterns
Learning to Deliberate: Meta-policy Collaboration for Agentic LLMs with Multi-agent Reinforcement Learning
AMFT: Aligning LLM Reasoners by Meta-Learning the Optimal Imitation-Exploration Balance
DOTS: Learning to Reason Dynamically in LLMs via Optimal Reasoning Trajectories Search
Cognitive Loop via In-Situ Optimization: Self-Adaptive Reasoning for Science
AUTO-CEI: A Curriculum and Expert Iteration Approach to Elevate LLMs’ Response Precision and Control Refusal Rates Across Diverse Reasoning Domains
