Machine LearningDev6 min reading time

NVIDIA Introduces SoL-Pi: Auto-Research Loops That Cut Coding Agent Token Traffic by Up to 49%

MarkTechPost
Read the full article
NVIDIA, NTU, and MIT researchers released SoL-Pi, an efficiency extension for the Pi coding agent that reduces token traffic by up to 49% and API costs by about 33% while maintaining performance on GPT-5.6 Sol and Opus 5. SoL-Pi automates harness-layer optimizations through auto-research loops and is available as an MIT-licensed GitHub extension compatible with Pi 0.85.1 and Node.js 22.19+.

More in Machine Learning

Machine Learning5 min read

Researchers from Stanford and UC Berkeley Introduce TokenGate: Token-Gated Attention Makes Long-Context Prefill Up to 11.3x Faster

MarkTechPost
Machine Learning2 min read

Jack Dorsey’s Block made an AI model that talks to you like an awkward new friend

Covered by 5 sources
Machine Learning6 min read

AI21 Labs Releases LIFT-Bench to Curb Reward Hacking in RL Training

Unite.AI