Selective Agent Guidance via Entropy: Learning Autonomous Policies from Imperfect VLM Teachers

2026-09-01

AI Summary

本文提出SAGE框架，通过仅在学习者不确定时查询视觉语言模型(VLM)来减少其使用，并将指导融入轻量级强化学习策略，以解决直接使用VLM作为策略成本高且易出错的问题。

Abstract

Vision-Language Models (VLMs) provide useful priors for interactive decision-making, but using them directly as policies is expensive and brittle: they must be queried at every step, do not improve from environment interaction, and can repeat systematic errors. We study how to learn a cheap autonomous policy from an online, expensive, and imperfect but informative VLM teacher. We propose SAGE (Selective Agent Guidance via Entropy), a framework that queries a VLM only when the learner is uncertain, executes the suggested action during training, and distills guidance into a lightweight Reinforcement Learning (RL) policy. Because VLM advice is not always reliable, SAGE can weight teacher-action distillation using environment-derived advantages rather than treating all suggestions as equally useful. Across sparse-reward visual reasoning and navigation tasks, SAGE learns policies that act without VLM guidance at evaluation time and improves over unguided RL in several environments, including settings where the learned policy exceeds its VLM teacher. The results show that selective guidance is most beneficial when the VLM can help the agent discover high-reward trajectories, and less useful when unguided exploration already succeeds or teacher actions do not lead to informative experience. SAGE also reduces VLM usage by prompting the teacher only on a fraction of training steps and requiring no VLM calls at deployment. Overall, our results suggest that VLMs don't need to be used as fixed policies to be useful; they can instead act as temporary, imperfect sources of guidance whose value is tested and internalized through interaction.

Problem

• Vision-Language Models
• autonomous policy
• imperfect teacher
• Reinforcement Learning
• Selective Guidance

Innovation

• Selective Agent Guidance
• Entropy
• Vision-Language Models
• Reinforcement Learning
• Autonomous Policies