LLM代理在开放世界中易失效，静态训练难应对动态变化。
Can Agents Generalize to the Open World? Unveiling the Fragility of Static Training in Tool Use
- 构建四层环境扰动框架，系统测试代理在开放世界中的表现。
- 监督微调与强化学习训练的代理均在动态环境下性能下降。
- 提出扰动增强微调策略，提升代理在真实场景的鲁棒性。
尽管大型语言模型（LLM）代理在静态基准上表现良好，但其在真实场景中的部署受限于用户查询、工具集和交互动态的不断变化。为解决这一泛化差距，我们提出OpenAgent（开放世界中的工具使用代理）问题设定，其特征在于查询、动作、观测和领域维度上的分布偏移。我们构建一个受控沙盒环境，定义了四层细粒度的环境扰动：感知、交互、推理和内化，并开展全面实验。分析揭示，无论是通过监督微调（SFT）还是强化学习训练的代理，在面对开放环境扰动时均表现出不同程度的性能退化。基于此，我们提出扰动增强微调（Perturbation-Augmented Fine-Tuning），一种基于扰动的干预策略，为提升代理在真实环境中的鲁棒性与实用性奠定基础。代码将开源于：https://github.com/LAMDA-NeSy/OpenAgent。
原文摘要 · Abstract (English)
While Large Language Model (LLM) agents demonstrate proficiency in static benchmarks, their deployment in real-world scenarios is hindered by the dynamic nature of user queries, tool sets, and interaction dynamics. To address this generalization gap, we formalize OpenAgent (Tool-Use Agent in Open-World), a problem setting characterized by distributional shifts across query, action, observation, and domain dimensions. To systematically diagnose its impact, we construct a controlled sandbox environment where we define fine-grained environmental shifts across a four-tier hierarchy, Perception, Interaction, Reasoning, and Internalization, and conduct a comprehensive series of experiments. Our analysis yields a series of key insights, demonstrating that agents trained via both Supervised Fine-Tuning(SFT) and Reinforcement Learning suffer from varying degrees of performance degradation when confronting open environmental shifts. Building on these insights, we propose Perturbation-Augmented Fine-Tuning, a disturbance-based intervention strategy for SFT that lays the foundation for enhancing agent robustness and utility in realistic environments. Our code will be released at: https://github. com/LAMDA-NeSy/OpenAgent.
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。