From 8ebede0efdb69f6b74472fc8ad009f716bb4ca1b Mon Sep 17 00:00:00 2001
From: Yif Yang <yif_yang@qq.com>
Date: Sun, 31 May 2026 18:20:00 +0800
Subject: [PATCH] Refine README for clarity on optimization results

Removed redundant wording about math benchmarks.
---
 README.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/README.md b/README.md
index cae5438..54f9a75 100644
--- a/README.md
+++ b/README.md
@@ -30,7 +30,7 @@ chat, Codex CLI, Claude Code CLI), SkillOpt is best or tied-best on **all
 average no-skill accuracy by **+23.5 points in direct chat, +24.8 inside
 the Codex agentic loop, and +19.1 inside Claude Code**. Optimized skill
 artifacts transfer across model scales, between Codex and Claude Code
-harnesses, and to nearby math benchmarks without further optimization.
+harnesses, and to nearby benchmarks without further optimization.
 
 For the full method, ablations, and per-cell results see the [paper](https://arxiv.org/abs/2605.23904); for a visual walkthrough of the loop see the [project page](https://microsoft.github.io/SkillOpt/); for deeper API / backend / benchmark docs see [`docs/`](docs/).