让AI学会主动请专家帮忙，显著提升复杂任务成功率。
Requesting Expert Reasoning: Augmenting LLM Agents with Learned Collaborative Intervention
- AI通过学习策略主动向专家请求推理支持，而非被动求助。
- 在Minecraft中，普通任务成功率提升32%，高难度任务提升近70%。
- 只需少量人工干预，即可大幅提升AI在专业领域的表现。
基于大语言模型（LLM）的智能体在通用推理上表现优异，但在依赖长尾知识的特定领域常因训练数据缺失而失败。尽管人类专家可提供这些知识，但其指导往往无结构且不可靠，直接整合到智能体规划中存在困难。为此，我们提出AHCE（主动人机协同挑战参与）框架，核心是人类反馈模块（HFM），采用学习策略将人类专家视为互动式推理工具。在Minecraft中的大量实验表明，该框架使普通难度任务的成功率提升32%，高难度任务提升近70%，且仅需极少的人类介入。研究证明，有效增强智能体的关键在于学会如何请求专家推理，而不仅仅是简单求助。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。