arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.01966cs.LG
收藏

自组织式自进化代理

Self-Consolidation for Self-Evolving Agents

UCAS-Terminus AI Lab, University of Chinese Academy of Sciences(中国科学院大学Terminus AI实验室,中国科学院大学);Centre for Artificial Intelligence and Robotics, HKISI-CAS(人工智能与机器人中心,中国科学院香港研究院);School of Computer Science and Engineering, Nanjing University of Science and Technology(南京理工大学计算机科学与工程学院)

Hongzhuo Yu, Fei Zhu, Guo-Sen Xie, Ling Shao

AI总结:

本文提出了一种自组织式自进化框架,通过对比反思和自组织机制,使LLM代理能有效利用历史经验实现长期进化。

摘要:

尽管大型语言模型(LLM)代理在解决问题方面表现出色,但它们通常作为静态系统运行,缺乏通过终身交互进化的能力。现有尝试弥合这一差距的方法主要依赖于检索成功的过去轨迹作为示范。然而,这种范式面临两个关键限制。首先,仅关注成功,代理忽略了失败尝试中蕴含的丰富的教学价值,阻碍了它们识别和避免反复陷阱的能力。第二,持续积累文本经验不仅增加了检索期间的时间消耗,也不可避免地引入噪声,并耗尽当前LLM的最大上下文窗口。为了解决这些挑战,我们提出了一种新的自进化框架,为LLM代理引入了互补的进化机制:首先,引入对比反思策略,以显式总结易出错的模式并捕捉可重用的见解。其次,我们提出了一种自组织机制,将非参数文本经验浓缩为紧凑的可学习参数。这使代理能够将广泛的历史经验直接内化到其潜在空间中。广泛的实验表明,我们的方法在长期代理进化方面具有优势。

英文摘要:

While large language model (LLM) agents have demonstrated impressive problem-solving capabilities, they typically operate as static systems, lacking the ability to evolve through lifelong interaction. Existing attempts to bridge this gap primarily rely on retrieving successful past trajectories as demonstrations. However, this paradigm faces two critical limitations. First, by focusing solely on success, agents overlook the rich pedagogical value embedded in failed attempts, preventing them from identifying and avoiding recurrent pitfalls. Second, continually accumulating textual experiences not only increases the time consumption during retrieval but also inevitably introduces noise and exhausts the largest context window of current LLMs. To address these challenges, we propose a novel self-evolving framework for LLM agents that introduces a complementary evolution mechanism: First, a contrastive reflection strategy is introduced to explicitly summarize error-prone patterns and capture reusable insights. Second, we propose a self-consolidation mechanism that distills non-parametric textual experience into compact learnable parameters. This enables the agent to internalize extensive historical experience directly into its latent space. Extensive experiments demonstrate the advantages of our method in long-term agent evolution.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑