17 papers
MemoryCPT: An End-to-End Agent Memory Framework for Cost-Performance Trade-off
Songxin Lei, Kun Ouyang, Weilin Ruan +4
Long-horizon LLM agents require memory systems that recover useful evidence from large interaction histories without passing excessive context to downstream models. Existing memory…
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…
MolecularCanvas: LLM-assisted Small-Molecule Drug Discovery via Structure-Guided Constraints
Haoyu Dong, Rui Sheng, Shuhao Zhang +7
Small-molecule drug discovery relies on iterative molecular optimization, where chemists repeatedly modify candidate compounds to balance multiple competing properties such as effi…
Fewer Clarifications, Better Code: Benchmarking Cross-Session Personalized Ambiguity Adaptation in Coding Assistants
Zijian Xu, Wenshuo Zhang, Zisen Qin +4
The paper defines personalized ambiguity adaptation for coding assistants, introduces the CAPA benchmark to evaluate how well models use a user's past resolved sessions to handle r…
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…