DistilVDR: A Compact End-to-End Visual Document Retriever via Dual-Student Distillation Paper • 2608.10636 • Published 3 days ago • 10
HarnessOpt-Bench: Evaluating LLMs at Harness Optimization Paper • 2608.06301 • Published 8 days ago • 34
ContinualSkillBench: Can LLM Agents Truly Evolve Their Capabilities? Paper • 2608.03874 • Published 10 days ago • 14