Skip to content
Search
paperJune 2026Unreviewed

Resilient Consensus in Agentic AI

Sribalaji C. Anand, George J. Pappas

View resourcePDF

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 princip

Categories

Agentic ThreatsAgent Architecture

Cite

@misc{anand2026resilient,
  title = {{Resilient Consensus in Agentic AI}},
  author = {Sribalaji C. Anand and George J. Pappas},
  year = {2026},
  month = jun,
  eprint = {2606.15024},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2606.15024}
}