Requesting Expert Reasoning: Augmenting LLM Agents with Learned Collaborative Intervention
This work is significant for improving the reliability and performance of LLM agents in specialized domains by learning how to effectively solicit and integrate expert human reasoning, particularly for tasks requiring long-tail knowledge.
This paper addresses the challenge of LLM agents failing in specialized domains due to a lack of long-tail knowledge. The authors introduce AHCE, a framework that uses a learned policy to integrate human expert knowledge, achieving a 32% increase in success rates on normal difficulty tasks and nearly 70% on highly difficult tasks in Minecraft.
Large Language Model (LLM) based agents excel at general reasoning but often fail in specialized domains where success hinges on long-tail knowledge absent from their training data. While human experts can provide this missing knowledge, their guidance is often unstructured and unreliable, making its direct integration into an agent's plan problematic. To address this, we introduce AHCE (Active Human-Augmented Challenge Engagement), a framework for on-demand Human-AI collaboration. At its core, the Human Feedback Module (HFM) employs a learned policy to treat the human expert as an interactive reasoning tool. Extensive experiments in Minecraft demonstrate the framework's effectiveness, increasing task success rates by 32% on normal difficulty tasks and nearly 70% on highly difficult tasks, all with minimal human intervention. Our work demonstrates that successfully augmenting agents requires learning how to request expert reasoning, moving beyond simple requests for help.