paper-with-me

홈 › Papers

FLEX: Continuous Agent Evolution via Forward Learning from Experience

2025-11-09 · Zhicheng Cai, Xinyuan Guo, Yu Pei, Jiangtao Feng, Jinsong Su, Jiangjie Chen, Ya-Qin Zhang, Wei-Ying Ma, Mingxuan Wang, Hao Zhou arxiv

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.

📄 PDF Abstract BibTeX arXiv:2511.06449

Code (0)

등록된 구현이 없습니다.

Tasks

Mathematical Reasoning

Similar Papers 제목 키워드 기반

Empirical-MCTS: Continuous Agent Evolution via Dual-Experience Monte Carlo Tree Search

2026-02-04 · Hao Lu, Haoyuan Huang, Yulin Zhou, Chen Li 외 arxiv

Inference-time scaling strategies, particularly Monte Carlo Tree Search (MCTS), have significantly enhanced the reasoning capabilities of Large Language Models (LLMs). However, current approaches remain predominantly sta…

Learning on the Job: An Experience-Driven Self-Evolving Agent for Long-Horizon Tasks

2025-10-09 · Cheng Yang, Xuemeng Yang, Licheng Wen, Daocheng Fu 외 arxiv

Large Language Models have demonstrated remarkable capabilities across diverse domains, yet significant challenges persist when deploying them as AI agents for real-world long-horizon tasks. Existing LLM agents suffer fr…

TAME: A Trustworthy Test-Time Evolution of Agent Memory with Systematic Benchmarking

2026-02-03 · Yu Cheng, Yongkang Hu, Jiuan Zhou, Yushuo Zhang 외 arxiv

Test-time evolution of agent memory represents a pivotal paradigm for advancing AGI, as it strengthens complex reasoning through experience accumulation without requiring parameter updates. However, even during benign ta…

AgentFactory: A Self-Evolving Framework Through Executable Subagent Accumulation and Reuse

2026-03-18 · Zhang Zhang, Shuqi Lu, Hongjin Qian, Di He 외 arxiv

Building LLM-based agents has become increasingly important. Recent works on LLM-based agent self-evolution primarily record successful experiences as textual prompts or reflections, which cannot reliably guarantee effic…

WikiSkill: Compiling Agent Experience into Persistent Knowledge for Skill Evolution

2026-08-27 · Liyan Tang, Cyrus Rashtchian, Chun-Sung Ferng, Andrew Tomkins 외 hf

Agent skills package specialized knowledge and workflows into reusable resources that extend AI agent capabilities. Recent work automatically discovers such skills from agent experience, which enables agents to progressi…