Harness Updating Is Not Harness Benefit: Disentangling Evolution Capabilities in Self-Evolving LLM Agents Paper • 2605.30621 • Published 17 days ago • 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 • 18
AutoMedBench: Towards Medical AutoResearch with Agentic AI Models Paper • 2606.01961 • Published 11 days ago • 27
AutoResearchClaw: Self-Reinforcing Autonomous Research with Human-AI Collaboration Paper • 2605.20025 • Published 26 days ago • 189