2 papers
cs.AI2026
AgenticRed: Evolving Agentic Systems for Red-Teaming
Jiayi Yuan, Jonathan Nöther, Natasha Jaques +1
While recent automated red-teaming methods show promise for systematically exposing model vulnerabilities, most existing approaches rely on human-specified workflows. This dependen…
cs.LG2025
InvestESG: A multi-agent reinforcement learning benchmark for studying climate investment as a social dilemma
Xiaoxuan Hou, Jiayi Yuan, Joel Z. Leibo +1
InvestESG is a novel multi-agent reinforcement learning (MARL) benchmark designed to study the impact of Environmental, Social, and Governance (ESG) disclosure mandates on corporat…