LoopCoder-v2: Only Loop Once for Efficient Test-Time Computation Scaling Paper • 2606.18023 • Published 17 days ago • 209
VisualClaw: A Real-Time, Personalized Agent for the Physical World Paper • 2606.16295 • Published 18 days ago • 28
google/diffusiongemma-26B-A4B-it Image-Text-to-Text • 26B • Updated about 4 hours ago • 1.42M • 1.09k
Harness Updating Is Not Harness Benefit: Disentangling Evolution Capabilities in Self-Evolving LLM Agents Paper • 2605.30621 • Published May 28 • 22
Mistral Medium 3.5 Collection Our first flaship models handling instruction-following, reasoning, and coding in a single set of opened-weights. • 2 items • Updated Apr 29 • 19
AutoMedBench: Towards Medical AutoResearch with Agentic AI Models Paper • 2606.01961 • Published 30 days ago • 28