mlsanityData to 7 Oct 2026

Synapse: Federated Tool Routing via Typed Compendium Artifacts

arXiv 2602.00911 ↗First posted 31 Jan 2026cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 44 of its 56 references that are in the map. First posted on arXiv 31 Jan 2026.

Builds on

44 of 56 references.

References · 44

  1. 2024The Llama 3 Herd of Modelscited by 14,192
  2. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  3. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
  4. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,064
  5. 2016Deep Learning with Differential Privacycited by 2,682
  6. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,221
  7. 2020Extracting Training Data from Large Language Modelscited by 2,144
  8. 2022Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language modelscited by 1,970
  9. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIscited by 1,880
  10. 2023Gorilla: Large Language Model Connected with Massive APIscited by 1,302
  11. 2024τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domainscited by 1,280
  12. 2019Deep Leakage from Gradientscited by 1,004
32 more
  1. 2020Inverting Gradients -- How easy is it to break privacy in federated learning?cited by 707
  2. 2018Byzantine-Robust Distributed Learning: Towards Optimal Statistical Ratescited by 698
  3. 2019Latent Retrieval for Weakly Supervised Open Domain Question Answeringcited by 691
  4. 2020Ensemble Distillation for Robust Model Fusion in Federated Learningcited by 678
  5. 2020The Future of Digital Health with Federated Learningcited by 625
  6. 2018Split learning for health: Distributed deep learning without sharing raw patient datacited by 391
  7. 2024TextGrad: Automatic "Differentiation" via Textcited by 250
  8. 2024LiveBench: A Challenging, Contamination-Limited LLM Benchmarkcited by 242
  9. 2016Practical Secure Aggregation for Federated Learning on User-Held Datacited by 178
  10. 2023ReWOO: Decoupling Reasoning from Observations for Efficient Augmented Language Modelscited by 174
  11. 2024Improving LoRA in Privacy-preserving Federated Learningcited by 158
  12. 2023FederatedScope-LLM: A Comprehensive Package for Fine-tuning Large Language Models in Federated Learningcited by 146
  13. 2024OpenFedLLM: Training Large Language Models on Decentralized Private Data via Federated Learningcited by 124
  14. 2023Jina Embeddings 2: 8192-Token General-Purpose Text Embeddings for Long Documentscited by 103
  15. 2023Effective Prompt Extraction from Language Modelscited by 83
  16. 2024FedBiOT: LLM Local Fine-tuning in Federated Learning without Full Modelcited by 73
  17. 2023FATE-LLM: A Industrial Grade Federated Learning Framework for Large Language Modelscited by 62
  18. 2025LiveMCPBench: Can Agents Navigate an Ocean of MCP Tools?cited by 47
  19. 2024Extracting Prompts by Inverting LLM Outputscited by 40
  20. 2019Towards Federated Graph Learning for Collaborative Financial Crimes Detectioncited by 33
  21. 2024On the Privacy Risk of In-context Learningcited by 31
  22. 2024C-FedRAG: A Confidential Federated Retrieval-Augmented Generation Systemcited by 19
  23. 2024Federated Recommendation via Hybrid Retrieval Augmented Generationcited by 16
  24. 2025Graph RAG-Tool Fusioncited by 15
  25. 2025Can Textual Gradient Work in Federated Learning?cited by 14
  26. 2023Transparency and Privacy: The Role of Explainable AI and Federated Learning in Financial Fraud Detectioncited by 13
  27. 2024FRAG: Toward Federated Vector Database Management for Collaborative and Secure Retrieval-Augmented Generationcited by 12
  28. 2025Privacy-Preserving Federated Embedding Learning for Localized Retrieval-Augmented Generationcited by 7
  29. 2025Federated In-Context Learning: Iterative Refinement for Improved Answer Qualitycited by 7
  30. 2025Federated Retrieval-Augmented Generation: A Systematic Mapping Studycited by 5
  31. 2025InfoMosaic-Bench: Evaluating Multi-Source Information Seeking in Tool-Augmented Agentscited by 3
  32. 2026Federate the Router: Learning Language Model Routers with Sparse and Decentralized Evaluationscited by 3

Built on by

Not cited yet.