2 papers
cs.AI2026
Uncertainty-Aware Clarification in LLM Agents with Information Gain
Mengyi Deng, Zhiwei Li, Xin Li +4
Large Language Model (LLM) agents often operate under underspecified user instructions, where latent uncertainty over user intent leads to erroneous tool actions. To address this c…
cs.CL2026
Attention Amnesia in Hybrid LLMs: When CoT Fine-Tuning Breaks Long-Range Recall, and How to Fix It
Xinyu Zhou, Boyu Zhu, Yi Xu +4
Chain-of-thought (CoT) supervised fine-tuning (SFT) is widely adopted to improve reasoning ability, yet we find that it systematically degrades long-context recall in hybrid linear…