Announcing LiteCoder-Terminal: Lightweight Terminal Agents with <1k Synthesized Trajectories 24 minutes ago • 1
Temporal Shadow Cognition: Parallel Timeline Decision-Making in Cognitive Architectures about 4 hours ago
Introducing AutoBench 2.0: Our New Benchmarking Platform is Out Just in Time to Evaluate GPT 5.2. about 20 hours ago • 1
cua-bench: A Framework for Benchmarking, Training Data, and RL Environments for Computer-Use Agents 1 day ago • 4
Nemotron 3 Nano \- A new Standard for Efficient, Open, and Intelligent Agentic Models 3 days ago • 79