PluginRSI: Recursive Improvement of Agent Harnesses with Reusable Plugins

PluginRSI evolves agent harnesses via reusable plugins, improving over existing methods and accelerating optimization on unseen tasks.

Yaorui Shi, Yuchun Miao, Yuxin Chen, Jiayuan Zhang, Yueqing Sun, Xierui Song, Xiang Wang, An Zhang

Published Sep 26, 2026▲ 7 on Hugging Face arXiv ↗

80%

OverallMust read

OverallMust readVote to see the scoreThe exact score shows once you've voted, so every vote is your own call. The first half of each home page shelf shows its scores.

Readers

–

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel12/20reviewers recommend it

lenient 5/5

medium 7/10

strict 0/5

AI panel?Vote to see what the 20 AI reviewers said

Panel consensus

PluginRSI delivers measurable harness gains through modular plugin libraries that accelerate optimization and transfer, though its reuse claims remain unverified across architectures and untested at scale.

Abstract

The harness surrounding a language model is a central determinant of agent performance. Recent methods optimize harnesses by searching over complete programs, where individual mechanisms are difficult to isolate and reuse. We introduce PluginRSI, which represents a harness as a composition of atomized plugins and organizes harness evolution around these plugins. Individual plugins are improved independently and accumulated in a shared library, then recombined into new harnesses at each iteration. PluginRSI improves over existing harness optimization methods across software engineering, command-line interaction, and question-answering tasks. The resulting harnesses retain their advantage when transferred to other solver models without further optimization. The evolved plugin library accelerates subsequent optimization from the initial harness, which helps faster and higher convergence on unseen tasks. These results show that accumulating reusable mechanisms provides an effective basis for continued harness improvement.