---
format: "aidr-story-markdown/v1"
id: "468a3a62054e558ef311b6815b5e94d3d296f8ba87779055d88c5a96928e35fe"
canonical_url: "https://aidr.today/468a3a62?lang=en"
title: "NVIDIA Introduces SoL-Pi: Auto-Research Loops That Cut Coding Agent Token Traffic by Up to 49%"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-09-22T05:04:43.000Z"
category: "Research"
topics: ["nvidia","pi","agent","multi-agent","benchmark","open-source"]
source_urls: ["https://www.marktechpost.com/2026/09/21/nvidia-researchers-have-released-sol-pi/"]
summary: "NVIDIA researchers have released SoL-Pi, 4 harness mechanisms for the open-source Pi coding agent, discovered by an AI running auto-research loops across 535 environments. On EdgeBench, SoL-Pi cuts token traffic by 44.7% to 49.0% and API cost by roughly 33%, while keeping 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 ."
---

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

> [Open the canonical story](<https://aidr.today/468a3a62?lang=en>)

**Published:** 2026-09-22T05:04:43.000Z
**Category:** Research
**Topics:** nvidia, pi, agent, multi\-agent, benchmark, open\-source

## Summary

NVIDIA researchers have released SoL\-Pi, 4 harness mechanisms for the open\-source Pi coding agent, discovered by an AI running auto\-research loops across 535 environments\. On EdgeBench, SoL\-Pi cuts token traffic by 44\.7% to 49\.0% and API cost by roughly 33%, while keeping 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 \.

## Sources

- [Story source](<https://www.marktechpost.com/2026/09/21/nvidia-researchers-have-released-sol-pi/>)