Preventing Error Propagation in Multi-Agent AI through Runtime Monitoring

• URL: http://arxiv.org/abs/2606.29026v1
• Date: Sat, 27 Jun 2026 17:44:24 GMT
• Title: Preventing Error Propagation in Multi-Agent AI through Runtime Monitoring
• Abstract summary: We study reliable multi-agent AI communication through reasoning exchange and runtime answer revision.<n>We develop a framework in which agents first answer multiple-choice questions independently, then share reasoning traces and revise their decisions.
• Score: 4.75542422590052
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Multi-agent AI systems can improve answer selection by allowing different language models to exchange reasoning traces, revise initial predictions, and support a final decision. However, such communication may also introduce reliability risks: reasoning from one agent can correct another agent's mistake, but it can also mislead an agent that was initially correct. This paper studies reliable multi-agent AI communication through reasoning exchange and runtime answer revision. We develop a framework in which agents first answer multiple-choice questions independently, then share reasoning traces and revise their decisions. We conduct numerical experiments where we evaluate whether this process improves accuracy, produces more positive than negative answer transitions, and remains effective across domains such as cybersecurity, networking, and general knowledge. The results help identify when multi-agent reasoning improves reliability and when it may propagate errors.

Related papers

• From Diagnosis to Redesign: Using Quantitative Ethnography to Improve Multi-Agent LLM Reasoning [2.3265759805858868]
  Multi-agent large language model (LLM) systems are designed to improve reasoning by decomposing tasks across multiple agents with specialized functions.<n>This paper introduces a quantitative ethnographic (QE) approach for diagnosing and redesigning multi-agent LLM systems based on the discourse produced through agent interactions.
  arXiv  Detail & Related papers  (2026-08-23T19:27:40Z)
• Diverse Evidence, Better Forecasts: Multi-Agent Deliberation Under Information Asymmetry [1.8983854039418835]
  We show that when all agents are given identical evidence, deliberation collapses into herding rather than genuine belief revision.<n>We propose a framework combining relevance-aware evidence routing, rationale-based iterative deliberation, and confidence-weighted aggregation.<n>On PolyGym, a benchmark of 375 binary forecasting questions, InfoDelphi outperforms the strongest single-agent and multi-agent baselines.
  arXiv  Detail & Related papers  (2026-07-02T03:41:25Z)
• Misinformation Propagation in Benign Multi-Agent Systems [11.967259729189388]
  Multi-agent systems are increasingly deployed in high-stakes settings such as medical diagnosis, legal analysis, and forensic decision-making.<n>Their reliability can be at risk when single agents reason from incorrect or misleading context.<n>This work studies this risk by injecting intent-based misinformation into benign single-agent and multi-agent systems.
  arXiv  Detail & Related papers  (2026-06-15T13:40:01Z)
• 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)
• AgentV-RL: Scaling Reward Modeling with Agentic Verifier [63.55502685076245]
  Verifiers have been demonstrated to enhance LLM reasoning via test-time scaling (TTS)<n>We propose Agentic Verifier, a framework that transforms reward modeling into a multi-turn, tool-augmented deliberative process.<n>We show that Agentic Verifier yields consistent performance gains under both parallel and sequential TTS.
  arXiv  Detail & Related papers  (2026-04-17T12:27:36Z)
• Can an Individual Manipulate the Collective Decisions of Multi-Agents? [53.01767232004823]
  M-Spoiler is a framework that simulates agent interactions within a multi-agent system to generate adversarial samples.<n>M-Spoiler introduces a stubborn agent that actively aids in optimizing adversarial samples.<n>Our findings confirm the risks posed by the knowledge of an individual agent in multi-agent systems.
  arXiv  Detail & Related papers  (2025-09-20T01:54:20Z)
• ReAgent: Reversible Multi-Agent Reasoning for Knowledge-Enhanced Multi-Hop QA [29.578079759428014]
  ReAgent is a reversible multi-Agent collaborative framework augmented with explicit backtracking mechanisms.<n>Our system can detect and correct errors mid-reasoning, leading to more robust and interpretable QA outcomes.
  arXiv  Detail & Related papers  (2025-03-10T05:56:46Z)
• When Disagreements Elicit Robustness: Investigating Self-Repair Capabilities under LLM Multi-Agent Disagreements [56.29265568399648]
  We argue that disagreements prevent premature consensus and expand the explored solution space.<n>Disagreements on task-critical steps can derail collaboration depending on the topology of solution paths.
  arXiv  Detail & Related papers  (2025-02-21T02:24:43Z)
• Preventing Rogue Agents Improves Multi-Agent Collaboration [21.955058255432974]
  We propose to monitor agents during action prediction and intervene when a future error is likely to occur.<n>Experiments on WhoDunitEnv, code generation tasks and the GovSim environment for resource sustainability show that our approach leads to substantial performance gains.
  arXiv  Detail & Related papers  (2025-02-09T18:35:08Z)
• DebUnc: Improving Large Language Model Agent Communication With Uncertainty Metrics [52.242449026151846]
  Multi-agent debates have been introduced to improve the accuracy of Large Language Models (LLMs)<n>We propose DebUnc, a debate framework that uses uncertainty metrics to assess agent confidence.
  arXiv  Detail & Related papers  (2024-07-08T22:15:01Z)
• Towards Reasoning in Large Language Models via Multi-Agent Peer Review Collaboration [28.299379264080603]
  Large Language Models (LLMs) have shown remarkable capabilities in general natural language processing tasks but often fall short in complex reasoning tasks. Recent studies have explored human-like problem-solving strategies, such as self-correct, to push further the boundary of single-model reasoning ability. We introduce a multi-agent collaboration strategy that emulates the academic peer review process.
  arXiv  Detail & Related papers  (2023-11-14T13:27:07Z)
• Online Decision Mediation [72.80902932543474]
  Consider learning a decision support assistant to serve as an intermediary between (oracle) expert behavior and (imperfect) human behavior. In clinical diagnosis, fully-autonomous machine behavior is often beyond ethical affordances.
  arXiv  Detail & Related papers  (2023-10-28T05:59:43Z)

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.