---
format: "aidr-story-markdown/v1"
id: "2c92b152edce7451b3c55521d449d0afb6643acdeac083c8910e20b55133fb56"
canonical_url: "https://aidr.today/2c92b152?lang=en"
title: "Nvidia's SoL-Pi system cuts coding agent token usage nearly in half by optimizing the harness"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-09-26T10:30:32.000Z"
category: "Agents"
topics: ["nvidia","agent"]
source_urls: []
summary: "SoL-Pi cuts coding agents' token usage by up to 49 percent with little change in performance by optimizing the control layer between the model and its environment. A research agent tested 152 approaches across more than 3,000 runs to develop the system, though the gains were smaller on other benchmarks. The article Nvidia's SoL-Pi system cuts coding agent token usage nearly in half by optimizing the harness appeared first on The Decoder ."
---

# Nvidia's SoL\-Pi system cuts coding agent token usage nearly in half by optimizing the harness

> [Open the canonical story](<https://aidr.today/2c92b152?lang=en>)

**Published:** 2026-09-26T10:30:32.000Z
**Category:** Agents
**Topics:** nvidia, agent

## Summary

SoL\-Pi cuts coding agents' token usage by up to 49 percent with little change in performance by optimizing the control layer between the model and its environment\. A research agent tested 152 approaches across more than 3,000 runs to develop the system, though the gains were smaller on other benchmarks\. The article Nvidia's SoL\-Pi system cuts coding agent token usage nearly in half by optimizing the harness appeared first on The Decoder \.

## Sources

_No safe source URL was recorded._