news

04/2026 Presenting our NuRL paper (code) at ICLR 2026 in Brazil! 🇧🇷
04/2026 We release CaOPD — calibration-aware on-policy distillation! Read the paper, check out the code and Hugging Face.
04/2026 2 papers accepted by ACL 2026: From Passive Metric to Active Signal and Don’t Stop Early: Scalable Enterprise Deep Research.
02/2026 2 invited talks on Building Reliable Long-horizon Agents at UCSD EnCORE Workshop and EPFL.
01/2026 1 paper accepted by ICLR 2026: Nudging the Boundaries of LLM Reasoning.
12/2025 Attending NeurIPS 2025 in San Diego! 🇺🇸
10/2025 We published a blog on Towards Trustworthy Enterprise Deep Research at Salesforce.
08/2025 3 papers accepted by EMNLP 2025: R2I-Bench (Oral, Outstanding Paper Nomination), Statistical Factuality Guarantee, and Confidence-Aware Reasoning.
04/2025 2 papers accepted by ACL 2025: SEE and Automatic Prompt Optimization Survey.
03/2025 1 paper accepted by NAACL 2025: Gradient-guided Attention Map Editing.