LexReward: A Taxonomy-Driven Reward Framework for Legal Language Models Paper • 2609.39071 • Published Sep 30 • 30
WDong/so101-sword-on-stand-clean32-bothtrim-train28-val4-v3 SO-101 • Updated Sep 1 • 32 episodes • 160
WDong/so101-sword-on-stand-clean32-bothtrim-train28-val4-v3 SO-101 • Updated Sep 1 • 32 episodes • 160
From Noisy Traces to Root Causes: Structural Trajectory Analysis and Causal Extraction for Agent Optimization Paper • 2607.07702 • Published Jul 8 • 7