A malicious agent in multi-agent LLM consensus systems can be trained via a surrogate world model and RL to reduce consensus rates and prolong disagreement more effectively than direct prompt attacks.
Advances in Neural Information Processing Systems (NeurIPS) , year=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.MA 1years
2026 1verdicts
UNVERDICTED 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Insider Attacks in Multi-Agent LLM Consensus Systems
A malicious agent in multi-agent LLM consensus systems can be trained via a surrogate world model and RL to reduce consensus rates and prolong disagreement more effectively than direct prompt attacks.