← all papers · overview

Better Than Your Teacher: LLM Agents That Learn From Privileged AI Feedback

Abstract

While large language models (LLMs) show impressive decision-making abilities, current methods lack a mechanism for automatic self-improvement from errors during task execution. We propose LEAP, an iterative fine-tuning framework that continually improves LLM agents using feedback from AI expert teachers. Our key insight is to equip the expert teachers with a privileged state -- information that is

Related papers

Ranked by semantic similarity — how closely each paper's abstract matches this one (100% = near-identical topic).