Metacognitive Self-Correction for Multi-Agent System via Prototype-Guided Next-Execution Reconstruction
"自我校正" 相关文章
AutoLabs: Cognitive Multi-Agent Systems with Self-Correction for Autonomous Chemical Experimentation
AdvChain: Adversarial Chain-of-Thought Tuning for Robust Safety Alignment of Large Reasoning Models
Self-Rewarding Reasoning in LLMs: Enhancing Autonomous Error Detection and Correction for Mathematical Reasoning
Google DeepMind Introduced Self-Correction via Reinforcement Learning (SCoRe): A New AI Method Enhancing Large Language Models’ Accuracy in Complex Mathematical and Coding Tasks
DotaMath: Advancing LLMs’ Mathematical Reasoning Through Decomposition and Self-Correction
