TIDE: Trajectory-based Diagnostic Evaluation of Test-Time Improvement in LLM Agents Paper β’ 2602.02196 β’ Published Feb 2 β’ 35
$Ο$-Decoding: Adaptive Foresight Sampling for Balanced Inference-Time Exploration and Exploitation Paper β’ 2503.13288 β’ Published Mar 17, 2025 β’ 51
MUR: Momentum Uncertainty guided Reasoning for Large Language Models Paper β’ 2507.14958 β’ Published Jul 20, 2025 β’ 47