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

NVIDIA researchers have released SoL-Pi, a set of 4 harness mechanisms for the open-source Pi coding agent. The mechanisms were discovered by an AI running auto-research loops across 535 environments.

Performance on EdgeBench

On EdgeBench, SoL-Pi delivers the following results:

• Cuts token traffic by 44.7% to 49.0%
• Reduces API cost by roughly 33%
• Keeps about 94% of Pi’s score on GPT-5.6 Sol and Opus 5

The post NVIDIA Introduces SoL-Pi: Auto-Research Loops That Cut Coding Agent Token Traffic by Up to 49% appeared first on MarkTechPost.