| title | SkillGrad: Optimizing Agent Skills Like Gradient Descent |
|---|---|
| authors | Hanyu Wang, Yifan Lan, Bochuan Cao, Lu Lin, Jinghui Chen |
| date | 2026-05-26 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2605.27760 |
| upvotes | 18 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf code |
| abstract | Agent skills provide a lightweight way to adapt LLM agents to specialized domains by storing reusable procedural knowledge in structured files. However, whether downloaded from third parties or self-generated, these skills are often unreliable, incomplete, or outdated. Existing skill-evolution methods often address these deficiencies through heuristic reflections without an explicit optimization formulation. In this paper, we propose SkillGrad, a gradient-descent-inspired framework for optimizing agent skills. SkillGrad treats the skill package as a structured parameter to optimize in a gradient descent fashion: task executions provide trajectory-level loss evidence, automatic diagnoses then provide text-based gradients that indicate the correction directions. To stabilize optimization across iterations, a momentum agent accumulates recurring diagnostic patterns into a persistent memory overlay. Finally, an LLM-based patcher executes the parameter update by applying layer-aware edits to the skill package. Evaluated on SpreadsheetBench Verified and WikiTableQuestions, SkillGrad consistently outperforms training-based skill evolution baselines across two backbone LLMs, improving over the strongest training-based baseline by 6.7 percentage points on average. Ablations further show that momentum and contrastive diagnosis both contribute to the final skill quality. |
cite
@misc{wang2026skillgrad,
title={SkillGrad: Optimizing Agent Skills Like Gradient Descent},
author={Hanyu Wang and Yifan Lan and Bochuan Cao and Lu Lin and Jinghui Chen},
year={2026},
eprint={2605.27760},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2605.27760}
}