Externalization in LLM Agents: A Unified Review of Memory, Skills, Protocols and Harness Engineering Paper • 2604.08224 • Published 3 days ago • 33
How Well Do Agentic Skills Work in the Wild: Benchmarking LLM Skill Usage in Realistic Settings Paper • 2604.04323 • Published 6 days ago • 35
FlashPrefill: Instantaneous Pattern Discovery and Thresholding for Ultra-Fast Long-Context Prefilling Paper • 2603.06199 • Published Mar 6 • 9
Dynamic Model Routing and Cascading for Efficient LLM Inference: A Survey Paper • 2603.04445 • Published Feb 23 • 5
PhotoBench: Beyond Visual Matching Towards Personalized Intent-Driven Photo Retrieval Paper • 2603.01493 • Published Mar 2 • 20