view post Post 410 multi-agents orchestration is old news by now. Try multi-teams of agents ! that is a whole different nightmare ... This is the real signal about the sparks of AGI. See translation 🔥 1 1 + Reply
The Tasteful Agent: Measuring and Improving Taste in Long-Horizon Tasks Paper • 2609.25804 • Published 19 days ago • 164
The Tasteful Agent: Measuring and Improving Taste in Long-Horizon Tasks Paper • 2609.25804 • Published 19 days ago • 164
Compile by Training: Turning Natural-Language Specifications into Local Neural Functions Paper • 2609.04199 • Published Sep 3 • 332
Interactive Training 2: Auditable Control Plane for Live Model Training Paper • 2607.18314 • Published Jul 17 • 21
Compile by Training: Turning Natural-Language Specifications into Local Neural Functions Paper • 2609.04199 • Published Sep 3 • 332
Control-Data Flow Separation: Stable Prompt Optimization in Multi-Agent LLMs Paper • 2609.00621 • Published Sep 1 • 9
Control-Data Flow Separation: Stable Prompt Optimization in Multi-Agent LLMs Paper • 2609.00621 • Published Sep 1 • 9
PAWBench: How Far Are We from Probabilistically Aligned World Modeling? Paper • 2608.27345 • Published Aug 27 • 62
PAWBench: How Far Are We from Probabilistically Aligned World Modeling? Paper • 2608.27345 • Published Aug 27 • 62
Jais 2: A Family of Arabic-Centric Open Large Language Models Paper • 2608.13580 • Published Jul 7 • 1
Interactive Training 2: Auditable Control Plane for Live Model Training Paper • 2607.18314 • Published Jul 17 • 21
Delineate Anything v2: A Global Foundation Model for Field Delineation Paper • 2607.19069 • Published Jul 21 • 6
Delineate Anything v2: A Global Foundation Model for Field Delineation Paper • 2607.19069 • Published Jul 21 • 6
DynEval: Holistic Evaluations of T2I Generative Models in the Wild Paper • 2607.11199 • Published Jul 13 • 1