发现信息
- 作者:Xunjian Yin, Xinyi Wang, Liangming Pan, Lin Li, Xiaojun Wan, William Yang Wang
- 年份:2025
- 发表源:Proceedings of the conference - Association for Computational Linguistics. Meeting
- OpenAlex ID:https://openalex.org/W4412889810
- DOI:https://doi.org/10.18653/v1/2025.acl-long.1354
- arXiv:待核验
- 检索主题:recursive-improvement
- OpenAlex 引用数快照:108(2026-11-12)
摘要线索
The rapid advancement of large language models (LLMs) has significantly enhanced the capabilities of agents across various tasks.However, existing agentic systems, whether based on fixed pipeline algorithms or pre-defined meta-learning frameworks, cannot search the whole agent design space due to the restriction of human-designed components, and thus might miss the more optimal agent design.In this paper, we introduce Gödel Agent, a selfevolving framework inspired by the Gödel machine, enabling agents to recursively improve themselves without relying on predefined routines or fixed optimization algorithms.Gödel Agent leverages LLMs to dynamically modify its own logic and behavior, guided solely by high-level objectives through prompting.Experimental results on multiple domains demonstrate that implementation of Gödel Agent can achieve continuous self-improvement, surpassing manually crafted agents in performance, efficiency, and generalizability.
核验与筛选
- 当前状态:待筛选、去重和一手来源核验。
- OpenAlex 元数据和引用数只用于发现,不作为正式引文或质量判断。
- 记录正式版本、venue、方法细节、实验协议和局限后,才迁入稳定论文卡片。