Semantic Context for Tool Orchestration

Robert Müller

Submission Track: Paper Track (up to 8 pages)

Keywords: RL, Tool Calling, LLM, Orchestration

TL;DR: We analyse the impact of semantic context for orchestration tasks theoretically and empirically.

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.

Camera Ready Modification Summary: Tighten presentation, sharpen notation, remove restated proofs in the appendix, add sec. 5.5 of a larger style exp in which sc helps, reformat prompts and reasoning trace, unify notation

Submission Number: 39