MeshHeal: Two-Timescale Self-Healing for Gray Failures in Decentralized LLM Agent Networks
cs.AI, cs.CL, cs.DC
Submitted: 2026-09-24
Updated: 2026-09-24
Comments: 31 pages
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- RoPoLL: Robust Panel of LLM Judges
- On the Opportunities and Risks of Foundation Models
- HIPO: Instruction Hierarchy via Constrained Reinforcement Learning
- Towards Conversational Development Environments: Using Theory-of-Mind and Multi-Agent Architectures for Requirements Refinement
- Symphony-Coord: Adaptive Routing for Multi-Agent LLM Systems
- Byzantine-Robust Decentralized Coordination of LLM Agents
- Robust Multi-Agent LLMs under Byzantine Faults
- Towards Adaptive, Scalable, and Robust Coordination of LLM Agents: A Dynamic Ad-Hoc Networking Perspective
- AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation
- LLM-Powered Decentralized Generative Agents with Adaptive Hierarchical Knowledge Graph for Cooperative Planning
- ReAct: Synergizing Reasoning and Acting in Language Models
- Building Cooperative Embodied Agents Modularly with Large Language Models
- Which Agent Causes Task Failures and When? On Automated Failure Attribution of LLM Multi-Agent Systems
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems