# SoL-Pi — NVIDIA's harness extension cuts coding-agent tokens by about half

> Four efficiency tricks, picked by an automated research loop out of 152 candidates, packaged as a drop-in Pi extension.

- Org: NVIDIA
- Date: 2026-09-17
- Category: tool, repo, algorithm, paper
- Source: https://nvlabs.github.io/SoL-Pi/
- Canonical page: https://ai-tldr.dev/releases/nvlabs-sol-pi/

## In short

SoL-Pi is an MIT-licensed extension for the Pi coding agent from NVIDIA's research lab. It packages four token-saving mechanisms found by an automated research loop, cutting token use 45-49% while keeping about 94% of Pi's EdgeBench score.

## What it is

Four reusable efficiency mechanisms arrive in SoL-Pi, a standalone extension that installs into the Pi coding agent. Action Fusion merges a file edit and the command that follows it into one tool call. ObservationPack archives big tool outputs on disk and leaves a handle plus a short excerpt in context. An Evidence-Preserving Reducer hands log-reading to cheaper agents, and Online Context Compact chooses when to rewrite context.

## How it works

The four mechanisms were not hand-designed. NVIDIA's lab ran an auto-research loop that fanned 152 proposals across independent lineages; each one generated trajectory rollouts, analysed them with map-reduce, implemented a candidate mechanism, passed a separate reviewer, and then faced a fully isolated held-out set. Only 4 proposals survived. No agent inside the loop ever saw the held-out results, so the surviving mechanisms had to generalise rather than fit the training trajectories.

## Why it matters

Token traffic is the bill for running coding agents, and SoL-Pi attacks it at the harness layer rather than by swapping to a weaker model. On EdgeBench it costs about a third less per hour than plain Pi and 50-54% less than the native Codex and Claude Code harnesses, while still returning roughly 94% of Pi's average score. Teams running agents continuously get most of the capability for half the traffic.

## Who it's for

teams running coding agents at scale

## Try it

pi install git:github.com/NVlabs/SoL-Pi

## Quick facts

- Maker: NVIDIA (NVlabs)
- What it is: Extension for the Pi coding agent
- License: MIT
- Requires: Node.js 22.19+, pi-coding-agent 0.85.1
- Evaluated on: EdgeBench, 51 tasks
- Mechanisms: Action Fusion, ObservationPack, Evidence-Preserving Reducer, Online Context Compact
- Paper: arXiv 2609.20519

## FAQ

### Does SoL-Pi work with Claude Code or Codex?

SoL-Pi installs into the Pi coding agent specifically, not into Claude Code or Codex. Those two appear in the paper as the native harnesses SoL-Pi is measured against, where it reports 50-54% lower API cost. The mechanisms are described as reusable, but the shipped package targets Pi 0.85.1 and its extension interface.

### How much money does SoL-Pi actually save per hour?

NVIDIA's lab reports SoL-Pi saving $4.36-$5.71 per hour compared with running plain Pi, and $8.75-$13.50 per hour compared with the native Codex and Claude Code harnesses. Those figures come from the 51-task EdgeBench run, so real savings depend on how closely your workload resembles long-horizon coding tasks.

### Can I turn individual SoL-Pi mechanisms off?

Yes. SoL-Pi reads a sol-pi.json config from either .pi/sol-pi.json in a project or ~/.pi/agent/sol-pi.json for a user. Each of the four mechanisms is its own boolean. The repo suggests a conservative starting configuration that enables Action Fusion and ObservationPack while leaving the Evidence-Preserving Reducer and Online Context Compact switched off.

### What does SoL-Pi give up in exchange for fewer tokens?

About 6% of score. SoL-Pi retains roughly 94% of Pi's average EdgeBench result on both model backends it was tested against, so the trade is a small accuracy drop for 45-49% fewer tokens. Whether that is worth it depends on how often a task failure costs more than the tokens saved.

## Links

- [Project Page](https://nvlabs.github.io/SoL-Pi/)
- [Paper (arXiv)](https://arxiv.org/abs/2609.20519)
- [Code](https://github.com/NVlabs/SoL-Pi)