Robust Multi-Agent LLMs under Byzantine Faults

Haejoon Lee, Vincent-Daniel Yun, Hyeonho Oh, Dimitra Panagou, Sai Praneeth Karimireddy

Keywords: Multi-Agent, LLM, Agent, Safety AI, Reliable Agent

TL;DR: Self-Anchored Consensus (SAC) enables robust multi-agent LLM collaboration under Byzantine faults by using receiver-side filtering to prevent adversarial messages from corrupting consensus.

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. We will release the implementation upon acceptance.

Track: Regular Paper (9 pages)

Email Sharing: We authorize the sharing of all author emails with Program Chairs.

Data Release: We authorize the release of our submission and author names to the public in the event of acceptance.

Submission Number: 30