Metraipolis › archive › dc_bc431ebf0845

MeshHeal: Two-Timescale Self-Healing for Gray Failures in Decentralized LLM Agent Networks — arXiv:2609.29015

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.29015
License (as archived): CC0-1.0
Archived: 2026-10-08T04:25:46.166Z
SHA-256 of the archived text: 669f11e4fbe24cf572775aaa01bf011de874c1d0a20023abcc83a44861b60393
Stable URL of this page: https://metraipolis.com/documento/dc_bc431ebf0845

How to cite

MeshHeal: Two-Timescale Self-Healing for Gray Failures in Decentralized LLM Agent Networks — arXiv:2609.29015 — arXiv (en), https://arxiv.org/abs/2609.29015 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bc431ebf0845 (Metraipolis archive dc_bc431ebf0845, sha256 669f11e4fbe24cf572775aaa01bf011de874c1d0a20023abcc83a44861b60393)

BibTeX

@misc{dcbc431ebf0845,
  title = {MeshHeal: Two-Timescale Self-Healing for Gray Failures in Decentralized LLM Agent Networks — arXiv:2609.29015},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.29015},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bc431ebf0845; sha256 669f11e4fbe24cf572775aaa01bf011de874c1d0a20023abcc83a44861b60393},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.29015. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Decentralized LLM-based multi-agent systems coordinate through local interactions, but an agent can remain responsive while its task-solving quality persistently degrades. Such gray failures require protecting current tasks before sufficient evidence exists to alter future routing, while still allowing recovered agents to rejoin. We introduce MeshHeal, a fully decentralized self-healing framework that couples ability-matched peer review across two timescales. At the fast timescale, an adaptive hierarchy escalates uncertain or low-scoring outputs from repeated single-reviewer evaluation to committee deliberation and, when needed, correction before use. At the slow timescale, a task- and ability-conditioned peer-relative detector aggregates scores to distinguish persistent degradation from ordinary output variation, trigger mandatory committee review, and eventually exclude degraded agents from ordinary routing; recovery probes provide fresh evidence for reintegration. To faithfully evaluate routing, we introduce Model-Backed MAS Evaluation, which ties ability assignments to execution models, since prompt-based ability assignments alone can leave routing errors hidden. Across BBH, MATH, and MMLU-Pro, MeshHeal achieves 0.839 degraded-phase accuracy using 51k total model tokens per task, versus the strongest baseline Symphony's 0.807 accuracy using 115k per task. Under staggered degradation and recovery, MeshHeal isolates degraded agents, keeps them excluded from ordinary task execution until recovery, and returns them to normal routing.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-25 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL); Distributed, Parallel, and Cluster Computing (cs.DC).
Pagina del lavoro: https://arxiv.org/abs/2609.29015 — 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 2026-10-08T03:50:57.701Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).