14 papers
TurnOPD: Making On-Policy Distillation Turn-Aware for Efficient Long-Horizon Agent Training
Yuhang Zhou, Kai Zheng, Haoling Li +3
On-policy distillation (OPD) trains a student policy by matching a stronger teacher on the student's own trajectories, offering a promising framework for language agent training. H…
The Scaling Laws of Skills in LLM Agent Systems
Charles Chen, Qiming Yu, Yuhang Gu +12
As agent systems scale, skills accumulate into large reusable libraries, yet their scaling laws remain poorly understood. Across 15 frontier LLMs, 1,141 real-world skills, and over…
Do Coding Agents Understand Least-Privilege Authorization?
Zheng Yan, Jingxiang Weng, Charles Chen +9
As coding agents gain access to shells, repositories, and user files, least-privilege authorization becomes a prerequisite for safe deployment: an agent should receive enough autho…
Learning the Boundary of Solvability: Aligning LLMs to Detect Unsolvable Problems
Dengyun Peng, Qiguang Chen, Bofei Liu +6
Ensuring large language model (LLM) reliability requires distinguishing objective unsolvability (inherent contradictions) from subjective capability limitations (tasks exceeding mo…
Beware of Reasoning Overconfidence: Pitfalls in the Reasoning Process for Multi-solution Tasks
Jiannan Guan, Qiguang Chen, Libo Qin +5
Large Language Models (LLMs) excel in reasoning tasks requiring a single correct answer, but they perform poorly in multi-solution tasks that require generating comprehensive and d…
The Universal Landscape of Human Reasoning
Qiguang Chen, Jinhao Liu, Libo Qin +14
Understanding how information is dynamically accumulated and transformed in human reasoning has long challenged cognitive psychology, philosophy, and artificial intelligence. Exist…