risk-control

Tag

Cards List
#risk-control

CP-Agent: A Calibrated Risk-Controlled Agent for Feedback-Driven Competitive Programming

arXiv cs.CL · 2026-05-26 Cached

CP-Agent presents a calibrated risk-controlled approach for feedback-driven competitive programming using large language models, achieving significant improvements on benchmarks without parameter updates.

0 favorites 0 likes
#risk-control

Conformal Selective Acting: Anytime-Valid Risk Control for RLVR-Trained LLMs

arXiv cs.LG · 2026-05-21 Cached

Introduces Conformal Selective Acting (CSA), a deployment-time wrapper for RLVR-trained LLMs that provides anytime-valid selective risk control on individual streams, enabling safe deployment in regulated settings without pooling or long-run averages.

0 favorites 0 likes
← Back to home

Submit Feedback