SkillOpt
Executive Strategy for Self-Evolving Agent Skills. SkillOpt treats a compact natural-language skill document as the trainable state of a frozen language agent, then learns that document through rollouts, reflection, bounded edits, and held-out validation gates.
SkillOpt in motion.
A short visual overview of how SkillOpt treats natural-language skills as trainable artifacts: roll out, reflect, edit, validate, and export.
Promotional video for the SkillOpt project page. The static paper teaser is shown below for high-resolution inspection.
The core loop at a glance.
The teaser summarizes the SkillOpt training loop: rollout evidence, optimizer-side reflection, bounded skill edits, validation gating, and the exported reusable skill.
Figure from the SkillOpt paper. On small screens, the figure area scrolls horizontally to preserve the original details.
Train the procedure, not the weights.
SkillOpt makes the skill document itself the optimization target. The target model, backend, and harness stay fixed; the procedure that guides evidence gathering, tool use, verification, and output formatting evolves.
A skill is external state for an agent.
Instead of fine-tuning a model or hand-maintaining prompts, SkillOpt runs the frozen agent on scored batches, asks an optimizer model to propose structured edits, and accepts a candidate only when validation performance improves.
The target model executes tasks with the current skill and records scored trajectories.
The optimizer analyzes success and failure minibatches to find reusable procedures.
Candidate add, delete, and replace operations are merged and ranked under a budget.
The candidate skill is kept only if it improves held-out selection performance.
A training loop for natural-language skills.
The loop deliberately mirrors a learning algorithm: rollout evidence acts like a forward pass, reflection acts like a language-level backward pass, and the textual learning rate bounds how far the skill can move.
Evidence
Rollout batches capture messages, tool calls, verifier feedback, task metadata, and final scores.
Minibatches
Failures and successes are reflected separately so edits correct recurring errors while preserving working behavior.
Bounded Edits
An edit budget functions as a textual learning rate, preventing useful rules from being overwritten by broad rewrites.
Memory
Rejected edits, slow update, and optimizer-side meta skill provide longer-horizon feedback without bloating deployment.
SkillOpt improves GPT and Qwen target models.
The table reports main-result gains across target models and execution harnesses, comparing no-skill execution with the final SkillOpt skill on held-out test splits.
SkillOpt clears the strongest baseline on every benchmark.
The controls are doing real work.
The paper isolates the optimizer components that keep skill learning stable: enough evidence, bounded textual updates, rejected-edit feedback, slow update, and optimizer-side memory.
What the ablations say
A typical run turns failures into concrete operating rules.
This ALFWorld run uses GPT-5.4-mini as the frozen target model and GPT-5.5 as the optimizer model. The plot tracks train rollout and held-out selection scores; hover or focus a point to inspect the skill edit proposed at that stage.
The exported skill behaves like a reusable artifact.
SkillOpt exports a compact best_skill.md . The paper tests whether that artifact transfers across model sizes, execution harnesses, and nearby benchmarks without further target-side optimization.
GPT-5.4 LiveMath skill transferred to GPT-5.4-nano on LiveMathBench.
Codex-trained SpreadsheetBench skill transferred into Claude Code.
GPT-5.4-nano used as its own optimizer improved SpreadsheetBench over baseline.
The target model consumes only the final skill, not optimizer memory.
Citation.
If you find SkillOpt useful, please cite the arXiv preprint below.
@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} }