Metraipolis › archive › dc_930ef71eab39

Typed Federated Artifacts for the Agentic Web:Sharing Tool-Routing Knowledge Across Frozen,Heterogeneous LLM Agents — arXiv:2609.06815

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.06815
License (as archived): CC0-1.0
Archived: 2026-10-16T12:45:20.281Z
SHA-256 of the archived text: a06fbc97c8c3e1e26f77b58c9e50abe0bad4a4d3dc27e3822f5993d8fca6ed70
Stable URL of this page: https://metraipolis.com/documento/dc_930ef71eab39

How to cite

Typed Federated Artifacts for the Agentic Web:Sharing Tool-Routing Knowledge Across Frozen,Heterogeneous LLM Agents — arXiv:2609.06815 — arXiv (en), https://arxiv.org/abs/2609.06815 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_930ef71eab39 (Metraipolis archive dc_930ef71eab39, sha256 a06fbc97c8c3e1e26f77b58c9e50abe0bad4a4d3dc27e3822f5993d8fca6ed70)

BibTeX

@misc{dc930ef71eab39,
  title = {Typed Federated Artifacts for the Agentic Web:Sharing Tool-Routing Knowledge Across Frozen,Heterogeneous LLM Agents — arXiv:2609.06815},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.06815},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_930ef71eab39; sha256 a06fbc97c8c3e1e26f77b58c9e50abe0bad4a4d3dc27e3822f5993d8fca6ed70},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.06815. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

An open, networked web will allow agents to run frozen models from multiple vendors, keep their history private, and teach each other which tool to call and when. Flat text (prompts, example pools) makes it difficult for the protocol to distinguish between noise statistics, merging rules, and documentation. Weights and adapters cannot transfer that knowledge between platforms. We suggest sharing typed federated artifacts, schema-validated objects with well-defined fields for per-field privacy (described here, but measured), dispute resolution, and cross-model transfer, and instantiating them as SYNAPSE1, a common tool-routing knowledge. After deleting 192 garbage entries and 1,916 training items that duplicate or almost duplicate test queries, a federated compendium routes within 1.1 points of a centralized one at 20 MB of JSON per client each round on StableToolBench (3,180 tools). The same experience merged and shown to the router as typed fields rather than one flat string is worth 8.5 points on clean data and 7.4 under 60% injected contradiction. Crossing merge and rendering shows the halves are inseparable (the typed merge shown flat is the worst arm), while three conflict policies are indistinguishable, so the conflict log that motivated this work is not the On {\tau}-bench retail, each compendium arm improves GPT-4o agents' per-step tool-call accuracy by at least 6.7 points, attributed to format rather than federated experience. Two cautionary findings conclude the paper: on a topic-labeled math proxy and StableToolBench, a TF-IDF classifier over the same labeled experience beats every LLM routing arm (by 48 and 26 points, mostly retrieval recall) because the benchmark's pool holds labeled queries for every supposedly unseen tool and every test query verbatim before our filter. It cannot measure routing to tools without labels, which routing exists for.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-09 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.06815 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-16T12:30:25.066Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).