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.
Not what you’ve signed up for: Compromising real-world llm-integrated ap- plications with indirect prompt injection, 2023
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 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.