arXiv cs.AI· Melika Sepidband, Jiho Shin, Song Wang, Hadi Hemmati·· 11 小时前AI 评分42
智能体该如何"看"代码？重新审视面向智能体软件工程的代码表示
How Should Agents See Code? Rethinking Code Representations for Agentic Software Engineering
AI 导读
一项研究把基于仓库地图的代码表示作为智能体软件工程的设计变量，用 Claude Code 搭配 Haiku 4.5 在四个仓库级任务上对比原始工具基线。
正文 · 原文
Abstract:LLM agents are increasingly used for repository-level software engineering tasks. However, most agents still access repositories through raw files, lexical search, and shell commands, treating code primarily as text. This paper investigates map-based code-representation workflows as a design variable in agentic software engineering, examining how different repository views change agents' retrieval behavior, task success, token use, and latency.
In this paper, we study five code-representation workflows: abstract syntax trees, call graphs, module dependencies, documentation-enriched search, and a hybrid workflow that combines them. Each workflow exposes a repository map that the agent can query during a task. We evaluate Claude Code with Haiku 4.5 against a raw-tool baseline on four repository-level tasks: fault localization with LinuxFLBench, repository-level code generation and repair with SWE-bench Pro, test generation with SWT-bench, and security patching with SecBench.
The results show that representation workflows are most useful as token-saving tools when localization is the bottleneck, while their success gains narrow when the decisive step is patch or test authoring. On LinuxFLBench, all five workflows improve recall@10 over the baseline (0.757-0.829 vs. 0.717) and reduce token usage by 25-39%. On SWE-bench Pro, resolution remains close to the baseline (44.3-50.6% vs. 49.0%) while token usage drops by 17-26%. On SecBench, Callgraph has the highest patch-resolution rate in this sample (34.3% vs. 28.9%) and uses fewer tokens, but all workflows increase latency. On SWT-bench, Hybrid and Docs have the highest reproducing-test rates in this sample (47.8% and 47.2% vs. 44.7%), but all workflows use more tokens and take longer. Overall, map-based workflows change both what the agent inspects and how much it spends, but their benefits are task-dependent rather than universal.
| Subjects: | Software Engineering (cs.SE); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.07286 [cs.SE] |
| (or arXiv:2611.07286v1 [cs.SE] for this version) | |
| https://doi.org/10.48550/arXiv.2611.07286 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Melika Sepidband [view email]
[v1]
Thu, 5 Nov 2026 01:08:43 UTC (759 KB)
来源：arXiv cs.AI · arxiv.org