Synapse: Federated Tool Routing via Typed Compendium Artifacts
The unit of collaboration in federated learning determines what guarantees are even expressible. Flat units like weights, prompts, raw examples, carry no type signature on which privacy, conflict resolution, or cross-model transfer can dispatch as well-defined operations. We propose typed federated artifacts: schema validated objects whose declared field structure makes per field differential privacy, schema aware merging, and cross architectural transfer first-class operations rather than heuristic approximations. We instantiate this as SYNAPSE, a compendium for federated tool routing across clients with frozen, heterogeneous LLMs and no shared data or weights which is a setting flat units cannot handle without either leaking gradients or discarding structure. The compendium admits a typed merge operator with field wise conflict resolution, a formal DP guarantee on numeric metadata, and conditional retrieval distortion and routing-stability results empirically characterized on five distributions, including one where the contraction premise fails. A single compendium transfers across four LLM families (LLaMA 3.18B,LLaMA 3.2-3B, Mistral 7B, GPT 4o) with approximately 2 pt loss, a capability weight-sharing federation cannot provide without architectural matching.
Code (0)
등록된 구현이 없습니다.
Tasks
Federated LearningSimilar Papers 제목 키워드 기반
Federated In-Context LLM Agent Learning
Large Language Models (LLMs) have revolutionized intelligent services by enabling logical reasoning, tool use, and interaction with external systems as agents. The advancement of LLMs is frequently hindered by the scarci…
Federated LearningIn-Context LearningLogical ReasoningPrivacy Preserving+2Compendium Manager: a tool for coordination of workflow management instances for bulk data processing in Python
Compendium Manager is a command-line tool written in Python to automate the provisioning, launch, and evaluation of bioinformatics pipelines. Although workflow management tools such as Snakemake and Nextflow enable users…
ManagementLLM-X: A Scalable Negotiation-Oriented Exchange for Communication Among Personal LLM Agents
We propose a personal-LLM exchange (LLM-X), a scalable negotiation-oriented environment that enables direct, structured communication across populations of personal agents (LLMs), each representing an individual user. Un…
STAR: Failure-Aware Markovian Routing for Multi-Agent Spatiotemporal Reasoning
Compositional spatiotemporal reasoning often requires a system to invoke multiple heterogeneous specialists, such as geometric, temporal, topological, and trajectory agents. A central question is how such a system should…
Internalizing Tools as Morphisms in Graded Transformers
We introduce a graded formulation of internal symbolic computation for transformers. The hidden space is endowed with a grading $V=\bigoplus_{g\in G}V_g$, and symbolic operations are realized as typed block maps (morphis…