Building Self-Evolving Agents via Experience-Driven Lifelong Learning: A Framework and Benchmark
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914279108640768 |
|---|---|
| author | Cai, Yuxuan Hao, Yipeng Zhou, Jie Yan, Hang Lei, Zhikai Zhen, Rui Han, Zhenhua Yang, Yutao Li, Junsong Pan, Qianjun Huai, Tianyu Chen, Qin Li, Xin Chen, Kai Zhang, Bo Qiu, Xipeng He, Liang |
| author_facet | Cai, Yuxuan Hao, Yipeng Zhou, Jie Yan, Hang Lei, Zhikai Zhen, Rui Han, Zhenhua Yang, Yutao Li, Junsong Pan, Qianjun Huai, Tianyu Chen, Qin Li, Xin Chen, Kai Zhang, Bo Qiu, Xipeng He, Liang |
| contents | 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 |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_19005 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Building Self-Evolving Agents via Experience-Driven Lifelong Learning: A Framework and Benchmark Cai, Yuxuan Hao, Yipeng Zhou, Jie Yan, Hang Lei, Zhikai Zhen, Rui Han, Zhenhua Yang, Yutao Li, Junsong Pan, Qianjun Huai, Tianyu Chen, Qin Li, Xin Chen, Kai Zhang, Bo Qiu, Xipeng He, Liang Artificial Intelligence Computation and Language 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 |
| title | Building Self-Evolving Agents via Experience-Driven Lifelong Learning: A Framework and Benchmark |
| topic | Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2508.19005 |