智能体如何从经验中持续进化？这篇论文提出MemoHarness框架，让Agent学会自我迭代。
arXiv:2607.14159v1 Announce Type: cross Abstract: An agent harness is the external control layer that turns a base LLM into an executable agent by man…
用GPT帮你读论文，N=1的工程案例竟能学到这么多反思。
What GPT Told Me About My Paper — And What I Actually Learned On June 28, I wrote my first paper. It's about G-T-W — a quality framework my creator an…
LLM智能体从经验中积累自然语言技能，但过度依赖自身判断，本文提出区分技能生成与应用的双重角色。
arXiv:2606.15390v1 Announce Type: cross Abstract: LLM agents can improve without weight updates by accumulating natural-language skills from experienc…
新方法TAHOE让Text-to-SQL系统自动从经验中优化提示，显著提升查询准确率。
arXiv:2606.12387v1 Announce Type: cross Abstract: Large Language Models (LLMs) have democratized database access through Text-to-SQL, but moving from …
提出隐式RAG让LLM代理从经验中自主学习，突破传统显式文本检索局限的创新方法。
arXiv:2606.01041v1 Announce Type: new Abstract: Experience learning has achieved promising results in enhancing LLM agent planning and reasoning by in…
创新提出图结构记忆让LLM智能体高效积累经验，与模型无关通用性强。
arXiv:2605.30712v1 Announce Type: new Abstract: Large language model (LLM) agents have shown strong capabilities in reasoning, tool use, and multi-ste…
最新arXiv论文提出语言代理从经验中学习的方法，为AI智能体自主进化提供新思路。
arXiv:2605.20477v1 Announce Type: new Abstract: Language agents can adapt from experience in interactive environments, but current reflection-based me…