用语义上下文提升大模型工具调度的效率与适应性
Semantic Context for Tool Orchestration
- 引入语义上下文，基于上下文带宽算法实现动态动作空间下的低遗憾调度
- 在超过10,000个工具的基准上验证，语义上下文显著提升学习效率与鲁棒性
- 提出FiReAct流程，适合构建高效、可扩展的智能工具协同系统
本文证明，语义上下文（SC）通过利用工具描述信息，是实现稳健工具调度的基础。贡献有三：第一，基于上下文带宽理论，提出SC-LinUCB算法，证明其在动态动作空间下具有更低遗憾并能良好自适应；第二，通过大语言模型进行并行实证，表明语义上下文对静态（高效学习）和非平稳（鲁棒适应）场景中的上下文学习至关重要；第三，提出FiReAct管道，在包含超过10,000个工具的基准上，验证基于语义上下文的检索使大模型能够有效协调大规模动作空间。这些发现为构建更样本高效、自适应且可扩展的调度代理提供了全面指导。
原文摘要 · Abstract (English)
This paper demonstrates that Semantic Context (SC), leveraging descriptive tool information, is a foundational component for robust tool orchestration. Our contributions are threefold. First, we provide a theoretical foundation using contextual bandits, introducing SC-LinUCB and proving it achieves lower regret and adapts favourably in dynamic action spaces. Second, we provide parallel empirical validation with Large Language Models, showing that SC is critical for successful in-context learning in both static (efficient learning) and non-stationary (robust adaptation) settings. Third, we propose the FiReAct pipeline, and demonstrate on a benchmark with over 10,000 tools that SC-based retrieval enables an LLM to effectively orchestrate over a large action space. These findings provide a comprehensive guide to building more sample-efficient, adaptive, and scalable orchestration agents.
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。