Resilient Consensus in Agentic AI

Computer Science > Multiagent Systems [Submitted on 12 Jun 2026] Title:Resilient Consensus in Agentic AI View PDF HTML (experimental)Abstract:Large language model (LLM) agents are increasingly deployed in multi-agent systems where they must coordinate and agree on shared decisions. We ask whether classical resilient consensus theory, developed for deterministic agents, transfers to LLM agents that may behave adversarially. Framing LLM agreement as a Byzantine consensus game, we run controlled experiments on complete and general communication graphs. We find that prompted LLM agents fail to reach agreement that is achievable in principle: consensus can fail even in settings where classical theory guarantees that a convergent algorithm exists, and this failure persists across temperatures and horizons. At the same time, wrapping the agents with classical resilient consensus filters improves agreement. The benefit of filtering depends on how much robustness the underlying topology already provides. Our results suggest that classical resilient consensus theory is a useful lens for the safety of agentic AI. Submission history From: Sribalaji Coimbatore Anand [view email][v1] Fri, 12 Jun 2026 23:41:53 UTC (134 KB) Current browse context: cs.MA References & Citations Loading... Bibliographic and Citation Tools Bibliographic Explorer (What is the Explorer?) Connected Papers (What is Connected Papers?) Litmaps (What is Litmaps?) scite Smart Citations (What are Smart Citations?) Code, Data and Media Associated with this Article alphaXiv (What is alphaXiv?) CatalyzeX Code Finder for Papers (What is CatalyzeX?) DagsHub (What is DagsHub?) Gotit.pub (What is GotitPub?) Hugging Face (What is Huggingface?) ScienceCast (What is ScienceCast?) Demos Recommenders and Search Tools Influence Flower (What are Influence Flowers?) CORE Recommender (What is CORE?) arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

이 뉴스, 독자들은 어떻게 느꼈나요?

공식 발표 ↔ 진영별 보도

'research' 카테고리 뉴스

A Definition of Good Explanations and the Challenges Explaining LLM Outputs

Dr-DCI: Scaling Direct Corpus Interaction via Dynamic Workspace Expansion

Relational Structural Causal Models

arXiv의 다른 기사

Metric Match: A Subset Selection Approach to Evaluating LLM Judge Reliability

OSGuard: A Benchmark for Safety in Computer-Use Agents

Fusion is not one-size-fits-all: Cross-Modal Representation Alignment for Time-to-Event Modeling