Nvidia's SoL-Pi system cuts coding agent token usage nearly in half by optimizing the harness
2 sources 5 min
Capable yet Parsimonious: Extracting and Characterizing Hidden Chain-of-Thought in Frontier Models
SoL-Pi: Recursively Scaling Auto-Research Loops for Efficient Agent Harness
1
Region-Level Policy Optimization for Fine-grained MLLM Perception
Ask HN: How do you manage skills files?
15 min2
Introducing agentic video understanding with Gemini
4 min3