SoL-Pi: Recursively Scaling Auto-Research Loops for Efficient Agent Harness

Hugging Face Daily Papers Papers
recursive-scaling auto-research agent-harness token-efficiency coding-agents performance-evaluation

Summary

SoL-Pi introduces a method for recursively scaling auto-research loops in coding agents, achieving significant token and cost reductions while maintaining performance on benchmarks.

As coding agents move from supervised code completion to unattended, around-the-clock exploration, their work expands from isolated predictions into long trajectories of reasoning, tool use, and feedback. Token efficiency therefore becomes important for scaling recursive self-improvement. We take an RSI-inspired approach at the harness layer, scaling auto-research loops across increasingly numerous and diverse environments for harness rollouts. At this scale, the process yields reusable improvements that transfer beyond their development setting, moving automated harness discovery toward production-level outcomes. Four mechanisms survive selection and form SoL-Pi, spanning action execution, context compaction, observation handling, and delegated reading. On the 51-task EdgeBench evaluation, SoL-Pi achieves performance comparable to Pi across GPT-5.6 Sol and Opus 5 while reducing recorded token traffic by 44.7-49.0% and API cost by about one third. In other words, estimated hourly savings are \8.75-13.50 relative to native Codex and Claude Code harnesses, and \4.36-5.71 relative to Pi.
Original Article
View Cached Full Text

Cached at: 09/18/26, 03:01 AM

Paper page - SoL-Pi: Recursively Scaling Auto-Research Loops for Efficient Agent Harness

Source: https://huggingface.co/papers/2609.20519 Authors:

,

,

,

,

,

,

,

,

,

,

,

,

Abstract

Ascodingagentsmovefromsupervisedcodecompletiontounattended,around-the-clockexploration,theirworkexpandsfromisolatedpredictionsintolongtrajectoriesofreasoning,tooluse,andfeedback.Tokenefficiencythereforebecomesimportantforscalingrecursiveself-improvement.WetakeanRSI-inspiredapproachattheharnesslayer,scalingauto-researchloopsacrossincreasinglynumerousanddiverseenvironmentsforharnessrollouts.Atthisscale,theprocessyieldsreusableimprovementsthattransferbeyondtheirdevelopmentsetting,movingautomatedharnessdiscoverytowardproduction-leveloutcomes.FourmechanismssurviveselectionandformSoL-Pi,spanningactionexecution,contextcompaction,observationhandling,anddelegatedreading.Onthe51-taskEdgeBenchevaluation,SoL-PiachievesperformancecomparabletoPiacrossGPT-5.6SolandOpus5whilereducingrecordedtokentrafficby44.7-49.0%andAPIcostbyaboutonethird.Inotherwords,estimatedhourlysavingsare\8.75-13.50relativetonativeCodexandClaudeCodeharnesses,and\4.36-5.71relativetoPi.

View arXiv pageView PDFProject pageGitHub2.19kAdd to collection

Get this paper in your agent:

hf papers read 2609\.20519

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2609.20519 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2609.20519 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2609.20519 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles