url/SkillOpt
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Refine README for clarity on optimization results

Browse Source 
Removed redundant wording about math benchmarks.
This commit is contained in:
Yif Yang
2026-05-31 18:20:00 +08:00
committed by GitHub
parent 266fca72ab
commit 8ebede0efd
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+1 -1
View File
@@ -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 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 the Codex agentic loop, and +19.1 inside Claude Code**. Optimized skill
artifacts transfer across model scales, between Codex and Claude Code 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/). 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/).