paper-with-me

Papers

Building Self-Evolving Agents via Experience-Driven Lifelong Learning: A Framework and Benchmark

2025-08-26 · Yuxuan Cai, Yipeng Hao, Jie Zhou, Hang Yan, Zhikai Lei, Rui Zhen, Zhenhua Han, Yutao Yang, Junsong Li, Qianjun Pan, Tianyu Huai, Qin Chen, Xin Li, Kai Chen, Bo Zhang, Xipeng Qiu, Liang He arxiv

As AI advances toward general intelligence, the focus is shifting from systems optimized for static tasks to creating open-ended agents that learn continuously. In this paper, we introduce Experience-driven Lifelong Learning (ELL), a framework for building self-evolving agents capable of continuous growth through real-world interaction. The framework is built on four core principles: (1) Experience Exploration: Agents learn through continuous, self-motivated interaction with dynamic environments, navigating interdependent tasks and generating rich experiential trajectories. (2) Long-term Memory: Agents preserve and structure historical knowledge, including personal experiences, domain expertise, and commonsense reasoning, into a persistent memory system. (3) Skill Learning: Agents autonomously improve by abstracting recurring patterns from experience into reusable skills, which are actively refined and validated for application in new tasks. (4) Knowledge Internalization: Agents internalize explicit and discrete experiences into implicit and intuitive capabilities as "second nature". We also introduce StuLife, a benchmark dataset for ELL that simulates a student's holistic college journey, from enrollment to academic and personal development, across three core phases and ten detailed sub-scenarios. StuLife is designed around three key paradigm

📄 PDF Abstract BibTeX arXiv:2508.19005

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

On Safety Risks in Experience-Driven Self-Evolving Agents

2026-04-18 · Weixiang Zhao, Yichen Zhang, Yingshuo Wang, Yang Deng 외 arxiv

Experience-driven self-evolution has emerged as a promising paradigm for improving the autonomy of large language model agents, yet its reliance on self-curated experience introduces underexplored safety risks. In this s…

Tree-of-Experience: A Structured Experience-Management Solution for Self-Evolving Agents under Low-Repetition and Implicit-Reward Environments

2026-06-05 · Zihao Deng, Yining Zhu, Leiming Wang, Jingfei Lu 외 arxiv

Experience-based self-evolution is crucial for LLM agents, but existing benchmarks often assume explicit goals, stable task patterns, and clear feedback. We study a more challenging setting: low-repetition tasks with imp…

Evolving-RL: End-to-End Optimization of Experience-Driven Self-Evolving Capability within Agents

2026-05-11 · Zhiyuan Fan, Wenwei Jin, Feng Zhang, Bin Li 외 arxiv

Experience-driven self-evolving agents aim to overcome the static nature of large language models by distilling reusable experience from past interactions, thus enabling adaptation to novel tasks at deployment time. This…

Reinforcement Learning

EXG: Self-Evolving Agents with Experience Graphs

2026-05-18 · Yuxin Jin, Siyuan Zhang, Hanchen Wang, Lu Qin 외 arxiv

Large language model (LLM)-based agents have demonstrated strong capabilities in complex reasoning and problem solving through multi-step interactions, yet most deployed agents remain behaviorally static, with knowledge …

Code Generation

GSEM: Graph-based Self-Evolving Memory for Experience Augmented Clinical Reasoning

2026-03-23 · Xiao Han, Yuzheng Fan, Sendong Zhao, Haochun Wang 외 arxiv

Clinical decision-making agents can benefit from reusing prior decision experience. However, many memory-augmented methods store experiences as independent records without explicit relational structure, which may introdu…