2 papers
cs.LG2026
When Denser Credit Is Not Enough: Evidence-Calibrated Policy Optimization for Long-Horizon LLM Agent Training
Yuanfan Li, Qi Zhou, Wenjing Duan +1
Long-horizon LLM agents require reinforcement learning methods that can assign credit to intermediate decisions under sparse and delayed rewards. Recent group-based methods such as…
cs.CR2026
Fight Poison with Poison: Enhancing Robustness in Few-shot Machine-Generated Text Detection with Adversarial Training
Wenjing Duan, Qi Zhou, Yuanfan Li
Machine-generated text (MGT) detection is critical for regulating online information ecosystems, yet existing detectors often underperform in few-shot settings and remain vulnerabl…