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.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
A transition graph model with utility and evidence counts learns behaviors from state history and feedback, showing performance comparable to neural networks on Atari Breakout.
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.
-
Interpretable experiential learning based on state history and global feedback
A transition graph model with utility and evidence counts learns behaviors from state history and feedback, showing performance comparable to neural networks on Atari Breakout.