🛰️ Daily AI Frontier
‹ back to 2026-09-09

Experience Funnel: A State-Policy Alternating Loop for Self-Evolving Agents

arXiv cs.CL LLM Agents Wenbo Gao, Zhaomou Song, Zhiyuan Ji, Renxi Liu, Xing Li, Xianzhi Yu, Xiaoguang Li, James Chung-wai Cheung, Weizhe Lin, Yaoyuan Wang 2026-09-08

TL;DR - Experience Funnel is a self-evolving agent framework that alternates between rapidly updating explicit textual state and slowly consolidating reusable behaviors into model parameters. This aims to preserve fast adaptation while reducing long-term dependence on external context.

  • Distills interaction trajectories into editable textual states, such as skills or agent harnesses, for rapid incorporation and validation of new experience.
  • Selectively transfers state-enabled behaviors that remain useful across revisions into the parametric policy using transition-aware distillation.
  • Repeats rollout generation, state adaptation, and policy consolidation as an iterative improvement loop.
  • Across diverse agent benchmarks, it reportedly outperforms state-only evolution and policy-internalization approaches while progressively internalizing useful experience.

view merged work →