Synapse Compendium Aware Federated Knowledge Exchange for Tool Routed LLMs
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911413557002240 |
|---|---|
| author | Chakraborty, Abhijit De, Sandipan Shah, Yash Dahal, Chahana Gupta, Vivek |
| author_facet | Chakraborty, Abhijit De, Sandipan Shah, Yash Dahal, Chahana Gupta, Vivek |
| contents | Collaborative learning among LLM-based agents under federated learning faces challenges, including communication costs, heterogeneity in data, and tool-usage, limiting their effectiveness. We introduce Synapse, a framework that trains a shared global knowledge model of tool-usage behavior. Client agents with fixed LLMs learn tool-usage patterns locally, and transmit artifacts for federated aggregation through coordinators. A global tool compendium is updated and redistributed, enabling convergence toward stable tool selection. Synapse uses templated representations, embedding retrieval with LLM reranking, and adaptive masking to maintain utility while limiting information leakage. The framework supports heterogeneous data and quantifies performance improvements. Results show that Synapse improves tool-usage effectiveness and reduces communication overhead compared with weight or prompt-sharing approaches in multi-agent LLM systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_00911 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Synapse Compendium Aware Federated Knowledge Exchange for Tool Routed LLMs Chakraborty, Abhijit De, Sandipan Shah, Yash Dahal, Chahana Gupta, Vivek Artificial Intelligence Collaborative learning among LLM-based agents under federated learning faces challenges, including communication costs, heterogeneity in data, and tool-usage, limiting their effectiveness. We introduce Synapse, a framework that trains a shared global knowledge model of tool-usage behavior. Client agents with fixed LLMs learn tool-usage patterns locally, and transmit artifacts for federated aggregation through coordinators. A global tool compendium is updated and redistributed, enabling convergence toward stable tool selection. Synapse uses templated representations, embedding retrieval with LLM reranking, and adaptive masking to maintain utility while limiting information leakage. The framework supports heterogeneous data and quantifies performance improvements. Results show that Synapse improves tool-usage effectiveness and reduces communication overhead compared with weight or prompt-sharing approaches in multi-agent LLM systems. |
| title | Synapse Compendium Aware Federated Knowledge Exchange for Tool Routed LLMs |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2602.00911 |