SkillOpt: Self-Evolving Agent Skills with Zero Inference Overhead

Train agent skills like you train neural networks — with epochs, (mini-)batchsize, learning rates, and validation gates — but without touching model weights.

📖 For installation, data preparation, training/eval commands, configuration, and framework internals, start with the versioned SkillOpt documentation. A concise rendered overview is available in the Documentation & Reproduction Guide, and longer-form engineering analysis appears on the Technical Blog. We also maintain a Changelog for released and unreleased changes.

• [2026-11] 🎤SkillOpt is accepted to NeurIPS 2026 as a Spotlight! See you in Sydney!
• [2026-11] 🏆SkillOpt won 1st Place in the Executive Challenge at the Microsoft Global Hackathon 2026 (badge , issued by The Microsoft Garage).
• [2026-07-24] 📰SkillOpt in the news. Read the officialMicrosoft Research feature , along with recent coverage fromVentureBeat ,Synced (机器之心) ,Flowtivity , andThe Decoder .
• [2026-07-02] 🚀SkillOpt v0.2.0 is out on PyPI! Headline feature:SkillOpt-Sleep , a nightly offline self-evolution engine (harvest → mine → replay → consolidate behind a held-out validation gate), now shipped as theskillopt-sleep CLI. It also includes experimental multi-objective, replay, and dream-rollout controls; the main CLI keeps conservative defaults and does not expose every experiment-harness control as a flag. The release source adds integration shells forClaude Code, Codex, Copilot, and Devin , plus anOpenClaw reference adaptation ; these plugin/MCP files live in the repository rather than the PyPI wheel. It also adds SearchQA split materialization, Windows robustness, and hardened JSON parsing. See therelease notes for full release details 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** for what it is, how to use it, and results.
• [2026-06-03] 🎉gbrain, gbrain-evals, and darwin-skill have all integrated SkillOpt.
• [2026-06-02] 🎉SkillOpt v0.1.0 is now available on PyPI! Install withpip 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.

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.

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; in the default paper-style path, 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.

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.

For the full method, ablations, and per-cell results see the paper; for a visual walkthrough of the loop see the project page; for deeper API / backend / benchmark docs see docs/.

64c8f76086bed7bd7a5ce664a7a14f40_raw.mp4 #

▶ Watch the full demo on YouTube

A backend = a chat / exec target (e.g. openai_chat, claude_chat, qwen_chat, minimax_chat, copilot_chat, openai_compatible, codex_exec, claude_code_exec, cursor_exec, copilot_exec). If a provider implements the OpenAI Chat Completions protocol, try the built-in openai_compatible backend before adding code. See docs/guide/new-backend.md for the full contract. Chat backends add a skillopt/model/<name>_backend.py module; target-only exec backends use the shared harness in codex_harness.py. Both register through common.py, backend_config.py, and skillopt/model/__init__.py.

A benchmark = a skillopt/envs/<name>/ package with an adapter, a data , a scored rollout helper, a YAML config, and optionally an initial seed skill. See docs/guide/new-benchmark.md for the full contract; the simplest reference is skillopt/envs/searchqa/.

Launch the monitoring dashboard (optional):

pip install -e ".[webui]"
python -m skillopt_webui.app

The default host is loopback-only. Exposing the dashboard (--host 0.0.0.0 or --share) requires --auth-user/--auth-pass (or SKILLOPT_WEBUI_USER/ SKILLOPT_WEBUI_PASS).

@article{yang2026skillopt,
  title={Skillopt: Executive strategy for self-evolving agent skills},
  author={Yang, Yifan and Gong, Ziyang and Huang, Weiquan and Yang, Qihao and Zhou, Ziwei and Huang, Zisu and Li, Yan and Gao, Xuemei and Dai, Qi and Liu, Bei and others},
  journal={arXiv preprint arXiv:2605.23904},
  year={2026}
}