$τ$-Emotion-Bench: Exposing the Interaction Fragility of LLM Agents through Real-World User Emotions Paper • 2610.19560 • Published 1 day ago • 13
CAST: Critique-Aware Supervision for Training Reliable Long-Horizon Tool-Calling Agents Paper • 2608.30147 • Published Aug 31 • 8
τ-Emotion-Bench: Exposing the Interaction Fragility of LLM Agents through Real-World User Emotions Paper • 2610.19560 • Published 1 day ago • 13