Lune

ACL2026Top-tier venue

Taming "Zombie" Agents: A Markov State-Aware Framework for Resilient Multi-Agent Evolution

Taolin Zhang, Pukun Zhao, Qizhou Chen, Jiuheng Wan, Chen Chen, Xiaofeng He, Chengyu Wang, Richang Hong

Abstract

Recent advancements in LLM-based multi-agent systems have demonstrated remarkable collaborative capabilities across complex tasks. To improve overall efficiency, existing methods often rely on aggressive graph evolution among agents (e.g., node or edge pruning), which risks prematurely discarding valuable agents due to transient issues such as hallucinations or temporary knowledge gaps. However, such hard pruning overlooks the potential for zombie''agents to recover and contribute in subsequent discussion rounds. In this paper, we propose AgentRevive, a Markov state-aware framework for resilient multi-agent evolution. Our approach dynamically manages agent collaboration through soft state transitions, implemented via two key components: (1) State-Aware Policy Learning: Agent states are divided into Active'', Standby'', and Terminated''states, selectively propagating messages based on agent memory. The policy employs a risk estimator to optimize agent state transitions by assessing hallucination risk, minimizing the influence of unreliable nodes while safeguarding valuable ones. (2) State-Aware Edge Optimization: Subgraph edges are pruned according to states learned from the policy, permanently removing Terminated''nodes and retaining Standby''nodes for subsequent rounds to assess their potential future contributions. Extensive experiments on general reasoning, domain-specific, and hallucination challenge tasks show that our method consistently outperforms strong baselines and significantly reduces token consumption through state-aware agent scheduling.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Self-Consistency Improves Chain of Thought Reasoning in Language Models cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
  • Chain-of-Thought Prompting Elicits Reasoning in Large Language Models cites Self-Consistency Improves Chain of Thought Reasoning in Language Models
  • TruthfulQA: Measuring How Models Mimic Human Falsehoods cites Measuring Massive Multitask Language Understanding
  • Improving Factuality and Reasoning in Language Models through Multiagent Debate cites Measuring Massive Multitask Language Understanding
  • Improving Factuality and Reasoning in Language Models through Multiagent Debate cites Self-Consistency Improves Chain of Thought Reasoning in Language Models
  • Improving Factuality and Reasoning in Language Models through Multiagent Debate cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
Builds onCited byLeft to right by year; the more cited, the higher.

Builds on15

  1. Chain-of-Thought Prompting Elicits Reasoning in Large Language ModelsJason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma et al.NeurIPS 2022 · 22,562 citations
  2. Measuring Massive Multitask Language UnderstandingDan Hendrycks, Collin Burns, Steven Basart, Andy Zou et al.ICLR 2021 · 7,905 citations
  3. TruthfulQA: Measuring How Models Mimic Human FalsehoodsStephanie Lin, Jacob Hilton, Owain EvansACL 2022 · 3,228 citations
  4. Improving Factuality and Reasoning in Language Models through Multiagent DebateYilun Du, Shuang Li, Antonio Torralba, Joshua B. Tenenbaum et al.ICML 2024 · 1,562 citations
  5. Self-Consistency Improves Chain of Thought Reasoning in Language ModelsXuezhi Wang, Jason Wei, Dale Schuurmans, Quoc V. Le et al.ICLR 2023 · 681 citations

Related papers

  1. LLM-Guided Communication for Cooperative Multi-Agent Reinforcement LearningSangjun Bae, Yisak Park, Sanghyeon Lee, Seungyul HanICML 2026 · 2 citations
  2. When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent SystemsHaowen Xu, Xue Tan, Lei Ma, Zhihao Zhang et al.ICML 2026
  3. AdvEvo-MARL: Shaping Internalized Safety through Adversarial Co-Evolution in Multi-Agent Reinforcement LearningZhenyu Pan, Yiting Zhang, Zhuo Liu, Yolo Tang et al.ICML 2026 · 1 citation
  4. EvoHyper: Evolving Hypergraph Topologies for Unified Collaboration in Multi-Agent CommunicationHeng Zhang, Yihao Zhong, Lubin Gan, Zhihe Chen et al.ACL Findings 2026
  5. Agent Primitives: Reuseable Latent Building Blocks for Multi-Agent SystemsHaibo Jin, Peng Kuang, Ye Yu, Xiaopeng Yuan et al.ICML 2026
Dusk over the sea between two cliffs drawn in fine vertical lines