paper-with-me

홈 › Papers

EvolveR: Self-Evolving LLM Agents through an Experience-Driven Lifecycle

2025-10-17 · Rong Wu, Xiaoman Wang, Jianbiao Mei, Pinlong Cai, Daocheng Fu, Cheng Yang, Licheng Wen, Xuemeng Yang, Yufan Shen, Yuxin Wang, Botian Shi arxiv

Current Large Language Model (LLM) agents show strong performance in tool use, but lack the crucial capability to systematically learn from their own experiences. While existing frameworks mainly focus on mitigating external knowledge gaps, they fail to address a more fundamental limitation: the inability to iteratively refine problem-solving strategies. In this work, we introduce EvolveR, a framework designed to enable agent to self-improve through a complete, closed-loop experience lifecycle. This lifecycle comprises two key stages: (1) Offline Self-Distillation, where the agent's interaction trajectories are synthesized into a structured repository of abstract, reusable strategic principles; (2) Online Interaction, where the agent interacts with tasks and actively retrieves distilled principles to guide its decision-making, accumulating a diverse set of behavioral trajectories. This loop employs a policy reinforcement mechanism to iteratively update the agent based on its performance. We demonstrate the effectiveness of EvolveR on complex multi-hop question-answering benchmarks, where it achieves superior performance over strong agentic baselines. Our work presents a comprehensive blueprint for agents that learn not only from external data but also from the consequences of their own actions, paving the way for more autonomous and continuously improving systems. Code is available at https://github.com/Edaizi/EvolveR.

📄 PDF Abstract BibTeX arXiv:2510.16079

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

OPD-Evolver: Cultivating Holistic Agent Evolver via On-Policy Distillation

2026-06-16 · Guibin Zhang, Xun Xu, Yanwei Yue, Zikun Su 외 arxiv

Memory has become a standard substrate for self-evolving agents, yet retaining experience is not the same as learning how to evolve through it. Existing memory agents can store trajectories, retrieve reflections, or accu…

AgentEvolver: Towards Efficient Self-Evolving Agent System

2025-11-13 · Yunpeng Zhai, Shuchang Tao, Cheng Chen, Anni Zou 외 arxiv

Autonomous agents powered by large language models (LLMs) have the potential to significantly enhance human productivity by reasoning, using tools, and executing complex tasks in diverse environments. However, current ap…

Reinforcement Learning

CyberEvolver: Structured Self-Evolution for Cybersecurity Agents On the Fly

2026-05-25 · Yihe Fan, Changyi Li, Lichen Xu, Xudong Pan 외 arxiv

LLM-based agents are increasingly used for cybersecurity tasks, but most existing systems rely on fixed, human-designed scaffolds that struggle to adapt across diverse targets and failure modes. We introduce \textsc{Cybe…

Large Language Model Agents Are Not Always Faithful Self-Evolvers

2026-01-30 · Weixiang Zhao, Yingshuo Wang, Yichen Zhang, Yang Deng 외 arxiv

Self-evolving large language model (LLM) agents continually improve by accumulating and reusing past experience, yet it remains unclear whether they faithfully rely on that experience to guide their behavior. We present …

Experience-Driven Multi-Agent Systems Are Training-free Context-aware Earth Observers

2026-01-30 · Pengyu Dai, Weihao Xuan, Junjue Wang, Hongruixuan Chen 외 arxiv

Recent advances have enabled large language model (LLM) agents to solve complex tasks by orchestrating external tools. However, these agents often struggle in specialized, tool-intensive domains that demand long-horizon …

Spatial Reasoning