Recovering Policy-Induced Errors: Benchmarking and Trajectory Synthesis for Robust GUI Agents Paper • 2605.29447 • Published May 28 • 21
Long Live The Balance: Information Bottleneck Driven Tree-based Policy Optimization Paper • 2605.28109 • Published May 27 • 23
MASQuant: Modality-Aware Smoothing Quantization for Multimodal Large Language Models Paper • 2603.04800 • Published Mar 5 • 25
D-CORE: Incentivizing Task Decomposition in Large Reasoning Models for Complex Tool Use Paper • 2602.02160 • Published Feb 2 • 14
Reasoning or Memorization? Unreliable Results of Reinforcement Learning Due to Data Contamination Paper • 2507.10532 • Published Jul 14, 2025 • 90
Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model? Paper • 2504.13837 • Published Apr 18, 2025 • 141
