Evo-MARL jointly trains all task agents with GRPO and an evolutionary attack pool, lowering jailbreak success rates by up to 21 points and modestly raising task accuracy.
Improving retrieval-augmented generation through multi-agent reinforcement learning, 2025
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.AI 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Evo-MARL: Co-Evolutionary Multi-Agent Reinforcement Learning for Internalized Safety
Evo-MARL jointly trains all task agents with GRPO and an evolutionary attack pool, lowering jailbreak success rates by up to 21 points and modestly raising task accuracy.