FLEX: Continuous Agent Evolution via Forward Learning from Experience

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Cai, Zhicheng, Guo, Xinyuan, Pei, Yu, Feng, Jiangtao, Su, Jinsong, Chen, Jiangjie, Zhang, Ya-Qin, Ma, Wei-Ying, Wang, Mingxuan, Zhou, Hao
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911305938501632
author Cai, Zhicheng
Guo, Xinyuan
Pei, Yu
Feng, Jiangtao
Su, Jinsong
Chen, Jiangjie
Zhang, Ya-Qin
Ma, Wei-Ying
Wang, Mingxuan
Zhou, Hao
author_facet Cai, Zhicheng
Guo, Xinyuan
Pei, Yu
Feng, Jiangtao
Su, Jinsong
Chen, Jiangjie
Zhang, Ya-Qin
Ma, Wei-Ying
Wang, Mingxuan
Zhou, Hao
contents Autonomous agents driven by Large Language Models (LLMs) have revolutionized reasoning and problem-solving but remain static after training, unable to grow with experience as intelligent beings do during deployment. We introduce Forward Learning with EXperience (FLEX), a gradient-free learning paradigm that enables LLM agents to continuously evolve through accumulated experience. Specifically, FLEX cultivates scalable and inheritable evolution by constructing a structured experience library through continual reflection on successes and failures during interaction with the environment. FLEX delivers substantial improvements on mathematical reasoning, chemical retrosynthesis, and protein fitness prediction (up to 23% on AIME25, 10% on USPTO50k, and 14% on ProteinGym). We further identify a clear scaling law of experiential growth and the phenomenon of experience inheritance across agents, marking a step toward scalable and inheritable continuous agent evolution. Project Page: https://flex-gensi-thuair.github.io.
format Preprint
id arxiv_https___arxiv_org_abs_2511_06449
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle FLEX: Continuous Agent Evolution via Forward Learning from Experience
Cai, Zhicheng
Guo, Xinyuan
Pei, Yu
Feng, Jiangtao
Su, Jinsong
Chen, Jiangjie
Zhang, Ya-Qin
Ma, Wei-Ying
Wang, Mingxuan
Zhou, Hao
Machine Learning
Artificial Intelligence
Autonomous agents driven by Large Language Models (LLMs) have revolutionized reasoning and problem-solving but remain static after training, unable to grow with experience as intelligent beings do during deployment. We introduce Forward Learning with EXperience (FLEX), a gradient-free learning paradigm that enables LLM agents to continuously evolve through accumulated experience. Specifically, FLEX cultivates scalable and inheritable evolution by constructing a structured experience library through continual reflection on successes and failures during interaction with the environment. FLEX delivers substantial improvements on mathematical reasoning, chemical retrosynthesis, and protein fitness prediction (up to 23% on AIME25, 10% on USPTO50k, and 14% on ProteinGym). We further identify a clear scaling law of experiential growth and the phenomenon of experience inheritance across agents, marking a step toward scalable and inheritable continuous agent evolution. Project Page: https://flex-gensi-thuair.github.io.
title FLEX: Continuous Agent Evolution via Forward Learning from Experience
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2511.06449