Robust Multi-Agent LLMs under Byzantine Faults

• URL: http://arxiv.org/abs/2605.09076v1
• Date: Sat, 09 May 2026 17:37:43 GMT
• Title: Robust Multi-Agent LLMs under Byzantine Faults
• Abstract summary: Large language model (LLM) agents increasingly collaborate over peer-to-peer networks to improve their reliability.<n> unreliable or Byzantine agents may sway neighboring agents toward incorrect conclusions and degrade overall system performance.<n>Existing methods rely on leader-based coordination or self-reported confidence, both of which are susceptible to adversarial manipulation.
• Score: 12.778788735297288
• License: http://creativecommons.org/publicdomain/zero/1.0/
• Abstract: Large language model (LLM) agents increasingly collaborate over peer-to-peer networks to improve their reliability. However, these same interactions can also become a source of vulnerability, as unreliable or Byzantine agents may sway neighboring agents toward incorrect conclusions and degrade overall system performance. Existing methods rely on leader-based coordination or self-reported confidence, both of which are susceptible to adversarial manipulation. We study decentralized LLM multi-agent systems (LLM-MAS) and propose Self-Anchored Consensus (SAC), a fully decentralized iterative filter-and-refine protocol in which agents iteratively exchange responses, locally evaluate and filter unreliable messages, and refine their own outputs. We present $(F{+}1)$-robustness conditions for the communication graph that ensure honest agents preserve and propagate reliable information despite Byzantine influence. Experiments on mathematical and commonsense reasoning benchmarks show that SAC effectively suppresses Byzantine influence and consistently improves performance across diverse communication topologies, whereas prior methods degrade under adversarial conditions.

Related papers

• From Sequence to Structure: Relational Uncertainty Propagation for LLM Agents [75.69180947909148]
  We propose a trajectory-level UQ framework for large language model (LLM) agents.<n>RuPA represents an execution history as a directed trajectory graph in which reasoning states, tool interactions, and environment feedback are nodes connected by temporal and semantic dependency edges.<n>We evaluate RUPA on representative agent benchmarks, including $$-2, Terminal-Bench-2, and GAIA, using 6 open-source LLMs spanning multiple model families.
  arXiv  Detail & Related papers  (2026-08-17T01:40:14Z)
• ExComm: Exploration-Stage Communication for Error-Resilient Agentic Test-Time Scaling [57.42714978834704]
  ExComm is a communication protocol for exploration-stage agentic test-time scaling.<n>We show that ExComm consistently outperforms strong test-time scaling baselines.
  arXiv  Detail & Related papers  (2026-05-21T07:38:44Z)
• Taming Actor-Observer Asymmetry in Agents via Dialectical Alignment [59.536125286960186]
  Multi-agent frameworks assigning specialized roles are increasingly adopted to enable self-reflection and mutual auditing.<n>We find it simultaneously induces a human-like cognitive bias known as Actor-Observer Asymmetry.<n>ReTAS guides agents to synthesize conflicting viewpoints into an objective consensus.
  arXiv  Detail & Related papers  (2026-04-21T15:05:58Z)
• DynaTrust: Defending Multi-Agent Systems Against Sleeper Agents via Dynamic Trust Graphs [17.988939054544243]
  We propose DynaTrust, a novel defense method against sleeper agents.<n> DynaTrust treats trust as a continuous, evolving process rather than a static attribute.<n>It dynamically updates the trust of each agent based on its historical behaviors and the confidence of selected expert agents.
  arXiv  Detail & Related papers  (2026-03-09T05:53:16Z)
• Gaming the Judge: Unfaithful Chain-of-Thought Can Undermine Agent Evaluation [76.5533899503582]
  Large language models (LLMs) are increasingly used as judges to evaluate agent performance.<n>We show this paradigm implicitly assumes that the agent's chain-of-thought (CoT) reasoning faithfully reflects both its internal reasoning and the underlying environment state.<n>We demonstrate that manipulated reasoning alone can inflate false positive rates of state-of-the-art VLM judges by up to 90% across 800 trajectories spanning diverse web tasks.
  arXiv  Detail & Related papers  (2026-01-21T06:07:43Z)
• Rethinking the Reliability of Multi-agent System: A Perspective from Byzantine Fault Tolerance [16.514747521376915]
  Large language models (LLMs) have established LLM-based agents as a major branch of multi-agent systems (MAS)<n>In this work, we investigate and quantify the reliability of LLM-based agents from the perspective of Byzantine fault tolerance.<n>We design CP-WBFT, a confidence probe-based weighted Byzantine Fault Tolerant consensus mechanism to enhance the stability of MAS with different topologies.
  arXiv  Detail & Related papers  (2025-11-13T15:20:12Z)
• SAFEFLOW: A Principled Protocol for Trustworthy and Transactional Autonomous Agent Systems [10.393477652794747]
  Recent advances in large language models (LLMs) and vision-language models (VLMs) have enabled powerful autonomous agents capable of complex reasoning and multi-modal tool use.<n>Despite their growing capabilities, today's agent frameworks remain fragile, lacking principled mechanisms for secure information flow, reliability, and multi-agent coordination.<n>We introduce SAFEFLOW, a new protocol-level framework for building trustworthy LLM/VLM-based agents.
  arXiv  Detail & Related papers  (2025-06-09T09:04:37Z)
• Information Retrieval Induced Safety Degradation in AI Agents [52.15553901577888]
  This study investigates how expanding retrieval access affects model reliability, bias propagation, and harmful content generation.<n>Retrieval-enabled agents built on aligned LLMs often behave more unsafely than uncensored models without retrieval.<n>These findings underscore the need for robust mitigation strategies to ensure fairness and reliability in retrieval-enabled and increasingly autonomous AI systems.
  arXiv  Detail & Related papers  (2025-05-20T11:21:40Z)
• Collaborative Value Function Estimation Under Model Mismatch: A Federated Temporal Difference Analysis [55.13545823385091]
  Federated reinforcement learning (FedRL) enables collaborative learning while preserving data privacy by preventing direct data exchange between agents.<n>In real-world applications, each agent may experience slightly different transition dynamics, leading to inherent model mismatches.<n>We show that even moderate levels of information sharing significantly mitigate environment-specific errors.
  arXiv  Detail & Related papers  (2025-03-21T18:06:28Z)
• Trust-based Consensus in Multi-Agent Reinforcement Learning Systems [5.778852464898369]
  This paper investigates the problem of unreliable agents in multi-agent reinforcement learning (MARL) We propose Reinforcement Learning-based Trusted Consensus (RLTC), a decentralized trust mechanism. We empirically demonstrate that our trust mechanism is able to handle unreliable agents effectively, as evidenced by higher consensus success rates.
  arXiv  Detail & Related papers  (2022-05-25T15:58:34Z)
• Gaussian Process Based Message Filtering for Robust Multi-Agent Cooperation in the Presence of Adversarial Communication [5.161531917413708]
  We consider the problem of providing robustness to adversarial communication in multi-agent systems. We propose a communication architecture based on Graph Neural Networks (GNNs) We show that our filtering method is able to reduce the impact that non-cooperative agents cause.
  arXiv  Detail & Related papers  (2020-12-01T14:21:58Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.