HarvestBench: Measuring Whether LLM Agents Will Pay to Avoid Killing Animals Paper • 2609.04444 • Published 13 days ago • 5
Repo-To-Skill: Distilling GitHub Repositories Into AI4AI Skills Paper • 2609.02749 • Published 14 days ago • 550
ZimaBlue: Evolving Generalizable World Action Models through Scalable Video Pre-training Paper • 2609.00188 • Published 16 days ago • 53
OmniDelta: Skill-Driven Budget Allocation for Token Compression in OmniLLMs Paper • 2607.25669 • Published Jul 28 • 10