From the 1 of 6 linked papers with an AI index.
6 papers
When Memory Lies: An Empirical Study of Spatial Memory Staleness in VLM Agents
Yushi Sun, Yanjie Zhang
Memory-augmented VLM agents act on persistent spatial knowledge, yet that knowledge silently goes stale as the environment changes. We ask what happens when an agent must reconcile…
The Personalization Mirage: How LLMs Fabricate User Profiles, and Why Self-Monitoring Misleads
Yushi Sun, Yanjie Zhang, Rui Sheng
Personalized LLMs with persistent memory are increasingly deployed, yet the faithfulness of their user models remains unexamined. We study over-inference (OI): the phenomenon where…
Navigating the Mirage: A Dual-Path Agentic Framework for Robust Misleading Chart Question Answering
Yanjie Zhang, Yafei Li, Rui Sheng +5
The paper introduces ChartCynics, a dual‑path system that separates visual perception and data verification to detect misleading information in charts, using a skeptical reasoning…
AdaPT: Adaptive Lesson Plan Transformer for Cross-Regional and Differentiated Instruction
Yanjie Zhang, Jiajun Zhu, Minyu Wu +2
Due to educational inequality, high-quality lesson plans often mismatch the needs of disparate educational contexts. Teachers typically modify existing lesson plans to fit new cont…
Within the MDT Room: Situated in Multidisciplinary Team-Grounded Agent Debate for Clinical Diagnosis
Peng Kuai, Yukun Yang, Shaolun Ruan +5
Rare disease diagnosis is inherently challenging due to heterogeneous symptoms, limited clinical familiarity, and fragmented evidence across specialties. Recent large language mode…
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…