ArXiv TLDR

Rui Sheng

2 papers · Latest:

Natural Language Processing

STALE: Can LLM Agents Know When Their Memories Are No Longer Valid?

LLM agents struggle to update invalid memories; STALE benchmark and CUPMem prototype address this critical "Implicit Conflict" failure mode.

2605.06527
Human-Computer Interaction

Figures as Interfaces: Toward LLM-Native Artifacts for Scientific Discovery

This paper introduces LLM-native figures, data-driven artifacts that enable LLMs to interact with and extend scientific visualizations by embedding full provenance.

2604.08491

📬 Weekly AI Paper Digest

Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.