CreativityBench: Evaluating Agent Creative Reasoning via Affordance-Based Tool Repurposing Paper • 2605.02910 • Published 7 days ago • 21
Toward Cognitive Supersensing in Multimodal Large Language Model Paper • 2602.01541 • Published Feb 2 • 16
MedSAM3: Delving into Segment Anything with Medical Concepts Paper • 2511.19046 • Published Nov 24, 2025 • 55
Analyzing and Internalizing Complex Policy Documents for LLM Agents Paper • 2510.11588 • Published Oct 13, 2025 • 1
Multimodal Policy Internalization for Conversational Agents Paper • 2510.09474 • Published Oct 10, 2025 • 5