Saved in:
| Main Author: | |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2507.10820 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912482767929344 |
|---|---|
| author | Müller, Robert |
| author_facet | Müller, Robert |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_10820 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Semantic Context for Tool Orchestration Müller, Robert Machine Learning Artificial Intelligence 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. |
| title | Semantic Context for Tool Orchestration |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2507.10820 |