Synapse Compendium Aware Federated Knowledge Exchange for Tool Routed LLMs

TL;DR

Synapse is a federated learning framework that enhances tool-usage in multi-agent LLM systems by training a shared knowledge base, reducing communication costs, and supporting heterogeneous data, leading to improved effectiveness.

Contribution

The paper introduces Synapse, a novel federated learning approach that builds a global tool compendium to improve tool-usage in LLM agents while minimizing communication overhead.

Findings

Improves tool-usage effectiveness in federated LLM systems.

Reduces communication overhead compared to weight or prompt-sharing methods.

Supports heterogeneous data environments.

Abstract

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.