# MeshHeal: Two-Timescale Self-Healing for Gray Failures in Decentralized LLM Agent Networks

arXiv: https://arxiv.org/abs/2609.29015 · HTML: https://mlsanity.com/paper/2609.29015/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 28 of its 37 references that are in the map.
- First posted on arXiv 24 Sep 2026.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 28 of 28)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://mlsanity.com/paper/2308.08155/) (2023)
- [MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark](https://mlsanity.com/paper/2406.01574/) (2024)
- [MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework](https://mlsanity.com/paper/2308.00352/) (2023)
- [Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them](https://mlsanity.com/paper/2210.09261/) (2022)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society](https://mlsanity.com/paper/2303.17760/) (2023)
- [ChatDev: Communicative Agents for Software Development](https://mlsanity.com/paper/2307.07924/) (2023)
- [AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors](https://mlsanity.com/paper/2308.10848/) (2023)
- [Mixture-of-Agents Enhances Large Language Model Capabilities](https://mlsanity.com/paper/2406.04692/) (2024)
- [Building Cooperative Embodied Agents Modularly with Large Language Models](https://mlsanity.com/paper/2307.02485/) (2023)
- [Which Agent Causes Task Failures and When? On Automated Failure Attribution of LLM Multi-Agent Systems](https://mlsanity.com/paper/2505.00212/) (2025)
- [More Agents Is All You Need](https://mlsanity.com/paper/2402.05120/) (2024)
- [BIG-Bench Extra Hard](https://mlsanity.com/paper/2502.19187/) (2025)
- [On the Resilience of LLM-Based Multi-Agent Collaboration with Faulty Agents](https://mlsanity.com/paper/2408.00989/) (2024)
- [AgentNet: Decentralized Evolutionary Coordination for LLM-based Multi-Agent Systems](https://mlsanity.com/paper/2504.00587/) (2025)
- [LLM-Powered Decentralized Generative Agents with Adaptive Hierarchical Knowledge Graph for Cooperative Planning](https://mlsanity.com/paper/2502.05453/) (2025)
- [Rethinking the Reliability of Multi-agent System: A Perspective from Byzantine Fault Tolerance](https://mlsanity.com/paper/2511.10400/) (2025)
- [Byzantine-Robust Decentralized Coordination of LLM Agents](https://mlsanity.com/paper/2507.14928/) (2025)
- [Robust Multi-Agent LLMs under Byzantine Faults](https://mlsanity.com/paper/2605.09076/) (2026)
- [HIPO: Instruction Hierarchy via Constrained Reinforcement Learning](https://mlsanity.com/paper/2603.16152/) (2026)
- [Symphony-Coord: Adaptive Routing for Multi-Agent LLM Systems](https://mlsanity.com/paper/2602.00966/) (2026)
- [Towards Adaptive, Scalable, and Robust Coordination of LLM Agents: A Dynamic Ad-Hoc Networking Perspective](https://mlsanity.com/paper/2602.08009/) (2026)
- [RoPoLL: Robust Panel of LLM Judges](https://mlsanity.com/paper/2606.30931/) (2026)
- [Towards Conversational Development Environments: Using Theory-of-Mind and Multi-Agent Architectures for Requirements Refinement](https://mlsanity.com/paper/2505.20973/) (2025)

## Abstract (arXiv)

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.