个性化技能能帮到编程智能体吗？一项开发者交互轨迹实证研究

View PDF HTML (experimental)

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.

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)