arXiv cs.AI· Haibo Jin, Xinjie Li, Peng Kuang, Haohan Wang·· 10 天前AI 评分32
HERMES：用模块化可执行 Dev-Primitives 做软件工程 Harness Engineering
Harness Engineering for Software Engineering via Modular Executable Dev-Primitives
AI 导读
针对 LLM 智能体在长周期软件工程任务中上下文爆炸与语义漂移的问题，研究者提出 Dev-Primitives——把仓库构件与其常驻 LLM 配对，使其具备自然语言推理、组件间通信和局部自我修改能力，并据此构建 HERMES 框架，通过依赖感知的动态激活与缺陷诊断机制在仓库规模上实例化这些原语。
正文 · 原文
Abstract:Large language models (LLMs) equipped with terminal access have demonstrated strong capabilities in automating software engineering tasks. However, existing agents remain brittle on long-horizon workflows, where they must repeatedly reconstruct program state scattered across source files, configurations, tests, dependencies, and runtime behavior, leading to increasingly long interaction histories, context explosion, and semantic drift. Large repositories further complicate the identification of task-relevant components. To address these challenges, we introduce \textbf{Dev-Primitives} (\emph{Development Primitives}), a modular and executable abstraction that transforms repository components from passive software artifacts into active participants in software engineering. Each Dev-Primitive pairs a repository artifact with a resident LLM, which gives the artifact an agent-native interface grounded in its own implementation and dependencies, enabling natural-language reasoning, inter-component communication, and localized self-modification. Building on Dev-Primitives, we propose \textbf{HERMES}, a Harness Engineering framework for software engineeRing via Modular Executable Dev-PrimitiveS, which instantiates these primitives at repository scale through a dependency-aware dynamic activation mechanism and a bug diagnosis mechanism that maps execution evidence back to the components that must be revised. Extensive experiments on four software engineering benchmarks demonstrate that HERMES outperforms matched baseline harnesses by 12.4\% on average. Moreover, when paired with strong activation and diagnosis models, HERMES, even with Qwen3-8B Dev-Primitives, remains within 4.5\% of the homogeneous GPT-5.6 Sol configuration across all four benchmarks, while reducing inference cost by 26.2\% on Terminal-Bench 4.0, highlighting the importance of harness design in software engineering agents.
| Comments: | 30 pages |
| Subjects: | Software Engineering (cs.SE); Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Multiagent Systems (cs.MA) |
| Cite as: | arXiv:2610.07832 [cs.SE] |
| (or arXiv:2610.07832v1 [cs.SE] for this version) | |
| https://doi.org/10.48550/arXiv.2610.07832 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Haibo Jin [view email]
[v1]
Tue, 6 Oct 2026 06:32:11 UTC (526 KB)
来源：arXiv cs.AI · arxiv.org