arxiv:2608.30147
Amir
sahsaeedi
·
AI & ML interests
NLP, RLHF, Alignment
Recent Activity
authored a paper about 11 hours ago
CAST: Critique-Aware Supervision for Training Reliable Long-Horizon Tool-Calling Agents submitted a paper 2 days ago
CAST: Critique-Aware Supervision for Training Reliable Long-Horizon Tool-Calling Agents