个性化 Skills 能否帮助 Coding Agent？基于开发者交互轨迹的实证研究
Do Personalized Skills Help Coding Agents? An Empirical Study of Developer Interaction Traces
AI 导读
一项实证研究提出结合规则引导与 LLM 精炼的框架，从开发者与 coding agent 的交互记录中提炼开发者专属 skills，并构建基于 LLM 开发者模拟器的交互式回放框架进行评估。
正文 · 原文
Abstract:As human developers increasingly collaborate with large language model (LLM)-powered coding agents, adapting to individual developer preferences, potentially via agent skills, may offer way to reduce repeated guidance and improve collaboration efficiency. However, existing approaches primarily focus on building skills for each task rather for each human developer. In this work, we propose a framework that combines rule-based bootstrapping with LLM-based refinement to distill developer-specific skills from their interactions with coding agents. We further develop an interactive replay framework with an LLM-based developer simulator for evaluation. We conduct experiments on a collection of replayable real-world developer-agent interaction sessions. We find that overall, task-specific skills are the most effective; However, personalized skills become more effective when developer preferences are manifested with enough frequency, especially when developers work on tasks that are highly related. These findings provide empirical insights suggest that i) broadly transferable procedural knowledge can be more robust than developer-specific preference signals and ii) effective personalization requires mining from rich user preference signals.
| Comments: | 18 pages, 10 figures |
| Subjects: | Software Engineering (cs.SE); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2608.10319 [cs.SE] |
| (or arXiv:2608.10319v3 [cs.SE] for this version) | |
| https://doi.org/10.48550/arXiv.2608.10319 arXiv-issued DOI via DataCite |
Submission history
From: Shuyan Huang [view email]
[v1]
Mon, 10 Aug 2026 23:41:02 UTC (4,188 KB)
[v2]
Sat, 15 Aug 2026 06:04:23 UTC (745 KB)
[v3]
Wed, 28 Oct 2026 23:58:19 UTC (798 KB)
来源：arXiv cs.AI · arxiv.org