作者位次 #2/2NeurIPS 2026Poster· Reinforcement Learning / Deep RL
Learning When to Think: Adaptive Internal Computation for Reinforcement Learning
Rohit Kumar Salla · Simon Stepputtis
强化学习与后训练OpenReview
首次获取该候选人的完整档案及 StartLux 评估共 20 积分；每位用户单独解锁，之后查看免费。主动刷新 20 积分。
实时查找电子邮箱，费用不超过20积分；未找到邮箱不扣费。
Rohit Kumar Salla · Simon Stepputtis
Chandler Squires · Yaqi Xie · Simon Stepputtis · Katia Sycara · Pradeep Ravikumar
Shahab Rahimirad · Guven Gergerli · Lucia Romero · Angela Qian · Matthew Lyle Olson · Simon Stepputtis · Joseph Campbell
Social reasoning—inferring unobservable beliefs and intentions from partial observations of other agents—remains a challenging task for large language models (LLMs). We evaluate the limits of current reasoning language models in the social deduction game Avalon and find that while the largest mod...
Matthew Lyle Olson · Neale Ratzlaff · Musashi Hinck · Tri Nguyen · Vasudev Lal · Joseph Campbell · Simon Stepputtis · Shao-Yen Tseng