To address data selection for RLVR post-training, LearnAlign is proposed—utilizing "gradient alignment" as a representativeness metric and "success rate $V(\xi)=p(1 ...
description [ICML 2026][LLM Agent][主动推理] 针对 LLM agent 在多轮主动推理中"动作选择(AS)"与"信念跟踪(BT)"互相拖累、outcome-only RL ...
While building a simpler model for particle interactions, physicists found a new representation involving pi—not a new value ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results