3 papers
cs.CY2026
Prioritization of Risks from Artificial Intelligence: A Delphi Study of 272 International Experts
Alexander K. Saeri, Jess Graham, Michael Noetel +185
Artificial intelligence poses many risks, ranging from familiar present-day harms to unprecedented and potentially catastrophic ones. Effective risk management requires prioritizat…
cs.CL2025
When Two LLMs Debate, Both Think They'll Win
Pradyumna Shyama Prasad, Minh Nhat Nguyen
Can LLMs accurately adjust their confidence when facing opposition? Building on previous studies measuring calibration on static fact-based question-answering tasks, we evaluate La…
cs.LG2025
RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learning
Zihan Wang, Kangrui Wang, Qineng Wang +15
Training large language models (LLMs) as interactive agents presents unique challenges including long-horizon decision making and interacting with stochastic environment feedback.…