Chain-of-Experience for Continual LLM Improvement

• 类型：arxiv
• 标识：2608.18027
• 链接：https://arxiv.org/abs/2608.18027
• 主分类：llm-infra
• 形态：method
• 被引：0
• 被引来源：Semantic Scholar
• S2被引：0
• 影响力被引：0
• TLDR：This study studies how LLMs learn from iterative experience at test time, a setting the authors refer to as Chain-of-Experience (CoE), where models accumulate experiential traces through iterative interactions with self or environmental feedback to form a continual improvement loop beyond zero-shot inference.
• 待LLM分类：否
• 标题中文：Chain-of-Experience：基于经验链的 LLM 持续改进
• TLDR中文：本文研究 LLM 在测试时从迭代经验中学习的机制，称之为 Chain-of-Experience (CoE)：模型通过与自身或环境反馈的迭代交互积累经验痕迹，形成超越零样本推理的持续改进循环。
• 来源文件：
• /inbox/tom/_candidates/2026-08-21-agent-rag-longcontext-candidates.json
• [S2 enrich]