Adv-PPO and Adv-PPO+MACER raise worst-case success in decentralized MAPF from 2.5% to 77.5% under observation attacks on 8x8 POGEMA maps with four agents, at under 1% clean-performance cost.
International Conference on Learning Representations (ICLR) , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
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.
citing papers explorer
-
Robust Multi-Agent Path Finding under Observation Attacks: A Principled Adversarial-Plus-Smoothing Training Recipe
Adv-PPO and Adv-PPO+MACER raise worst-case success in decentralized MAPF from 2.5% to 77.5% under observation attacks on 8x8 POGEMA maps with four agents, at under 1% clean-performance cost.
-
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.