arxiv:2606.20529
Amir
sahsaeedi
·
AI & ML interests
NLP, RLHF, Alignment
Recent Activity
submitted a paper 1 day ago
CAST: Critique-Aware Supervision for Training Reliable Long-Horizon Tool-Calling Agents authored a paper 2 months ago
LedgerAgent: Structured State for Policy-Adherent Tool-Calling Agents