SOURCE-LINKED INTELLIGENCE

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

arXiv · AI, language, vision and robotics · article · Sep 8, 2026 · UTC

Autonomous agents powered by large language models (LLMs) continuously accumulate experience through interaction, creating an opportunity to improve future behavior through self-evolution. A fundamental challenge is how to transform abundant, task-specific interaction experience into reusable model competence without sacrificing the ability to adapt rapidly to newly observed evidence. Explicit textual states, such as skills and agent harnesses, provide fast, human-readable and editable adaptation, but incur persistent dependence on external context; parametric policies provide compact and reus

Read original source ↗ Open in workspace

recordType

paper

region

Global