Banger paper from Stanford and Together AI. They show why it might be a good idea to let your agent team learn its own way of working together. (bookmark it) Three models (o3-mini, Claude Sonnet 4 and DeepSeek-V3) averaged 66.7% across five math and physics benchmarks as a self-organizing team. Their strongest member alone scored 48.8%, and a perfect router choosing among the members' independent answers scored 59.0%. On AIME 2026 the team reached 71.2%, 13.4 points above that router. One member reviews the team's earlier exchanges and rewrites the teamwork strategy, covering roles, the order of discussion phases, who participates and how partial answers are combined. The strategies were learned from only 15 AIME 2024 problems and then applied unchanged to held-out AIME 2024 problems and four new benchmarks. Paper:

GLM-5.3 has arrived on Together AI on Day 0 @Zai_org pushed the GLM-5.2 base further with scaled post-training, delivering stronger coding and long-horizon agent performance. Across benchmarks, it nearly matches Fable 5 while costing a fraction as much per task. Try now:

BREAKING: Cathie Wood says SpaceX is severely undervalued. SpaceX brings together AI, robotics and energy storage. But traditional space, cloud and AI analysts work separately, making it harder to understand how these technologies strengthen one another. Wood says firms are now assigning teams of analysts to SpaceX. As they collaborate and compare notes, she expects that undervaluation to clear up.