Semantic Context for Tool Orchestration

2025/07/14 by Robert Müller, Müller, Robert · 1 citation
Business, Management and Accounting · Computer Science · #Artificial Intelligence (cs.AI) #Business Process Modeling and Analysis #FOS: Computer and information sciences #Machine Learning (cs.LG) #Semantic Web and Ontologies #Service-Oriented Architecture and Web Services

paper · pdf · doi:10.48550/arxiv.2507.10820

openalex publication_date 2025/07/14 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

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.

Cited by

• Empowering Real-World: A Survey on the Technology, Practice, and Evaluation of LLM-driven Industry Agents
• A Component-Based Survey of Interactions between Large Language Models and Multi-Armed Bandits

Related

• AutoContext: Instance-Level Context Learning for LLM Agents
• Context as a Tool: Context Management for Long-Horizon SWE-Agents
• PEEK: Context Map as an Orientation Cache for Long-Context LLM Agents
• Dynamic Context Tuning for Retrieval-Augmented Generation: Enhancing Multi-Turn Planning and Tool Adaptation
• Context Tuning for Retrieval Augmented Generation