2 papers
cs.HC2026
InconLens: Interactive Visual Diagnosis of Behavioral Inconsistencies in LLM-based Agentic Systems
Shuo Yan, Xiaolin Wen, Shaolun Ruan +5
Large Language Model (LLM)-based agentic systems have shown growing promise in tackling complex, multi-step tasks through autonomous planning, reasoning, and interaction with exter…
cs.CL2026
Reward Prediction with Factorized World States
Yijun Shen, Delong Chen, Xianming Hu +4
Agents must infer action outcomes and select actions that maximize a reward signal indicating how close the goal is to being reached. Supervised learning of reward models could int…