From 9a5912288b834ef11becd7114e1d388bdd2bb348 Mon Sep 17 00:00:00 2001 From: wehub-resource-sync Date: Mon, 13 Jul 2026 10:14:07 +0000 Subject: [PATCH] docs: make Chinese README the default --- README.md | 69 ++++++++++++++++++++++--------------------------------- 1 file changed, 27 insertions(+), 42 deletions(-) diff --git a/README.md b/README.md index 6f2c6ff..289c716 100644 --- a/README.md +++ b/README.md @@ -1,6 +1,12 @@ -# SkillOpt: Executive Strategy for Self-Evolving Agent Skills + +> [!NOTE] +> 本文档由 WeHub 基于上游 README 翻译整理，属于社区翻译，非官方中文文档。 +> [English](./README.en.md) · [原始项目](https://github.com/microsoft/SkillOpt) · [上游 README](https://github.com/microsoft/SkillOpt/blob/HEAD/README.md) +> 原作者、版权与许可证归属以原始项目及本仓库 LICENSE 文件为准。 -*Train agent skills like you train neural networks — with epochs, (mini-)batchsize, learning rates, and validation gates — but without touching model weights.* +# SkillOpt：自进化 Agent 技能（Agent Skills）的执行策略 + +*像训练神经网络一样训练 agent 技能——使用 epoch、（mini-）batch size、学习率（learning rate）和验证门控（validation gates）——但无需改动模型权重。* [![Project Page](https://img.shields.io/badge/Project%20Page-SkillOpt-8dbb3c)](https://microsoft.github.io/SkillOpt/) [![Paper](https://img.shields.io/badge/Paper-arXiv-b31b1b)](https://arxiv.org/abs/2605.23904) [![Project Video](https://img.shields.io/badge/Project%20Video-Watch%20Demo-ff0000)](https://youtu.be/JUBMDTCiM0M) [![PyPI](https://img.shields.io/badge/PyPI-skillopt-green.svg)](https://pypi.org/project/skillopt/) [![Python 3.10+](https://img.shields.io/badge/Python-3.10%2B-blue.svg)](https://www.python.org/) [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE) @@ -9,52 +15,34 @@ microsoft%2FSkillOpt | Trendshift

-> 📖 **For installation, data preparation, training/eval commands, the full configuration reference, and framework internals, see the [Documentation & Reproduction Guide](https://microsoft.github.io/SkillOpt/docs/guideline.html)** (rendered on GitHub Pages). +> 📖 **有关安装、数据准备、训练/评估命令、完整配置参考及框架内部机制，请参阅 [Documentation & Reproduction Guide](https://microsoft.github.io/SkillOpt/docs/guideline.html)**（在 GitHub Pages 上渲染）。 --- ## News 🔥🔥🔥 -- **[2026-07-02]** 🚀 **SkillOpt [v0.2.0](https://github.com/microsoft/SkillOpt/releases/tag/v0.2.0) is out on [PyPI](https://pypi.org/project/skillopt/)!** Headline feature: **SkillOpt-Sleep**, a nightly offline self-evolution engine (harvest → mine → replay → consolidate, all behind a held-out validation gate) with multi-objective reward, experience replay + dream rollouts, and long-term memory — now shipped as the `skillopt-sleep` CLI. This release also adds cross-tool backends and plugin shells for **Claude, Codex, Copilot, Devin, and OpenClaw**, SearchQA split materialization, Windows robustness, and hardened JSON parsing. See the [release notes](https://github.com/microsoft/SkillOpt/releases/tag/v0.2.0) for the full changelog and contributor acknowledgements. -- **[2026-06-15]** 😴 **SkillOpt-Sleep (preview)** — a nightly offline self-evolution companion for local coding agents (Claude Code / Codex / Copilot): review past sessions, replay recurring tasks, and consolidate validated skills behind a held-out gate. See **[`docs/sleep/README.md`](docs/sleep/README.md)** for what it is, how to use it, and results. -- **[2026-06-03]** 🎉 **[gbrain](https://github.com/garrytan/gbrain), [gbrain-evals](https://github.com/garrytan/gbrain-evals/blob/main/docs/benchmarks/2026-06-03-skillopt.md), and [darwin-skill](https://github.com/alchaincyf/darwin-skill) have all integrated SkillOpt.** -- **[2026-06-02]** 🎉 **SkillOpt [v0.1.0](https://github.com/microsoft/SkillOpt/releases/tag/v0.1.0) is now available on [PyPI](https://pypi.org/project/skillopt/)!** Install with `pip install skillopt`. This initial release includes the full training loop (rollout → reflect → aggregate → select → update → evaluate), multi-backend support (OpenAI / Azure / Claude / Qwen / MiniMax), six built-in benchmarks, and WebUI dashboard. +- **[2026-07-02]** 🚀 **SkillOpt [v0.2.0](https://github.com/microsoft/SkillOpt/releases/tag/v0.2.0) 已发布至 [PyPI](https://pypi.org/project/skillopt/)!** headline 功能：**SkillOpt-Sleep**，一款夜间离线自进化引擎（harvest → mine → replay → consolidate，全程受留出验证门控保护），支持多目标奖励、经验回放（experience replay）+ 梦境 rollout（dream rollouts）以及长期记忆——现已作为 `skillopt-sleep` CLI 交付。本版本还新增跨工具后端及面向 **Claude、Codex、Copilot、Devin 和 OpenClaw** 的插件外壳、SearchQA 划分物化、Windows 稳健性增强，以及加固的 JSON 解析。完整变更日志与贡献者致谢见 [release notes](https://github.com/microsoft/SkillOpt/releases/tag/v0.2.0)。 +- **[2026-06-15]** 😴 **SkillOpt-Sleep（预览版）** —— 面向本地编码 agent（Claude Code / Codex / Copilot）的夜间离线自进化伴侣：回顾过往会话、重放重复任务，并在留出门控后巩固已验证技能。其定义、用法与结果见 **[`docs/sleep/README.md`](docs/sleep/README.md)**。 +- **[2026-06-03]** 🎉 **[gbrain](https://github.com/garrytan/gbrain), [gbrain-evals](https://github.com/garrytan/gbrain-evals/blob/main/docs/benchmarks/2026-06-03-skillopt.md), 与 [darwin-skill](https://github.com/alchaincyf/darwin-skill) 均已集成 SkillOpt。** +- **[2026-06-02]** 🎉 **SkillOpt [v0.1.0](https://github.com/microsoft/SkillOpt/releases/tag/v0.1.0) 现已在 [PyPI](https://pypi.org/project/skillopt/)!** 发布。使用 `pip install skillopt` 安装。首发版本包含完整训练循环（rollout → reflect → aggregate → select → update → evaluate）、多后端支持（OpenAI / Azure / Claude / Qwen / MiniMax）、六个内置基准测试，以及 WebUI 仪表盘。 --- ## Overview -Modern agent skills are usually hand-crafted, generated one-shot by a strong -LLM, or evolved through loosely controlled self-revision — none of which -behaves like a deep-learning optimizer for the skill itself, and none of -which reliably improves over its starting point under feedback. +现代 agent 技能通常靠手工编写、由强 LLM 一次性生成，或通过松散控制的自我修订来演化——这些方式都不像针对技能本身的深度学习优化器，也都不能在反馈下可靠地超越起点。 -**SkillOpt treats the skill document as the trainable state of a frozen -agent**, and trains it with the discipline that makes weight-space -optimization reproducible. A separate optimizer model turns scored rollouts -into bounded add / delete / replace edits on a single skill document; a -candidate edit is accepted only when it strictly improves a held-out -validation score. A textual learning-rate budget, a rejected-edit buffer, -and an epoch-wise slow / meta update make skill training stable while -adding **zero inference-time model calls** at deployment. +**SkillOpt 将技能文档视为冻结 agent 的可训练状态**，并以使权重空间优化可复现的纪律来训练它。独立的优化器模型将带评分的 rollout 转化为对单一技能文档的有界 add / delete / replace 编辑；候选编辑仅在其严格提升留出验证分数时才被接受。文本学习率预算、被拒编辑缓冲区，以及按 epoch 的慢速 / 元更新，使技能训练保持稳定，同时在部署时**零额外推理时模型调用**。 -The deployed artifact is a compact `best_skill.md` (typically 300–2,000 -tokens) that runs against the unchanged target model. Across **six -benchmarks, seven target models, and three execution harnesses** (direct -chat, Codex CLI, Claude Code CLI), SkillOpt is best or tied-best on **all -52 evaluated (model, benchmark, harness) cells** and on GPT-5.5 lifts the -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 benchmarks without further optimization. +部署产物是一个紧凑的 `best_skill.md`（通常 300–2,000 tokens），在不变的目标模型上运行。在**六个基准测试、七个目标模型和三种执行框架**（direct chat、Codex CLI、Claude Code CLI）上，SkillOpt 在**全部 52 个已评估（模型、基准测试、框架）单元格**上均为最佳或并列最佳；在 GPT-5.5 上，平均无技能准确率提升 **+23.5 点（direct chat）、+24.8 点（Codex agentic loop 内）、+19.1 点（Claude Code 内）**。优化后的技能产物可跨模型规模、在 Codex 与 Claude Code 框架之间，以及迁移至相近基准测试，而无需进一步优化。 -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/). +完整方法、消融实验与各单元格结果见 [paper](https://arxiv.org/abs/2605.23904);；循环的可视化导览见 [project page](https://microsoft.github.io/SkillOpt/);；更深入的 API / 后端 / 基准测试文档见 [`docs/`](docs/)。 ## 🎬 Demo Video https://github.com/user-attachments/assets/eb12d3bc-371c-467f-904d-91b61f339ed7

- ▶ Watch the full demo on YouTube + ▶ 在 YouTube 观看完整演示

--- @@ -63,24 +51,21 @@ https://github.com/user-attachments/assets/eb12d3bc-371c-467f-904d-91b61f339ed7 ### Adding a new backend -A backend = a chat / exec target (e.g. `openai_chat`, `claude_chat`, -`qwen_chat`, `minimax_chat`, `codex_exec`, `claude_code_exec`). See -[`docs/guide/new-backend.md`](docs/guide/new-backend.md) for the full -contract; in short you add a `skillopt/model/_backend.py` module, -register it in `skillopt/model/common.py` + `backend_config.py`, and wire -it through the router in `skillopt/model/__init__.py`. `qwen_backend.py` -and `minimax_backend.py` are good templates. +后端 = 聊天 / 执行目标（例如 `openai_chat`、`claude_chat`、 +`qwen_chat`、`minimax_chat`、`codex_exec`、`claude_code_exec`）。完整约定见 +[`docs/guide/new-backend.md`](docs/guide/new-backend.md)；简而言之，你需要添加 `skillopt/model/_backend.py` 模块， +在 `skillopt/model/common.py` + `backend_config.py` 中注册，并在 `skillopt/model/__init__.py` 的路由器中接入。`qwen_backend.py` +与 `minimax_backend.py` 是不错的模板。 ### Adding a new benchmark -A benchmark = a `skillopt/envs//` package with a `dataloader.py`, a -`rollout.py`, and an `initial.md` seed skill. See -[`docs/guide/new-benchmark.md`](docs/guide/new-benchmark.md) for the full -contract; the simplest reference is `skillopt/envs/searchqa/`. +基准测试 = 带有 `dataloader.py`、 +`rollout.py` 和 `initial.md` 种子技能的 `skillopt/envs//` 包。完整约定见 +[`docs/guide/new-benchmark.md`](docs/guide/new-benchmark.md)；最简单的参考是 `skillopt/envs/searchqa/`。 ### WebUI -Launch the monitoring dashboard (optional): +启动监控仪表盘（可选）： ```bash pip install -e ".[webui]"