1
AI-to-AI Code Reviews of GitHub Pull Requests
AI 自动审查 GitHub 拉取请求，实证研究揭示效果与挑战
Article URL: https://arxiv.org/abs/2608.21311 Comments URL: https://news.ycombinator.com/item?id=49426227 Points: 1 # Comments: 0
2
Software Engineering for AI-driven Building Operation
AI落地建筑运营的软件工程指南，涵盖系统设计到部署的完整链路。
arXiv:2608.16237v1 Announce Type: cross Abstract: Building operations are energy-inefficient. Artificial Intelligence (AI)-driven control systems prom…
3
AI Workflow Orchestration: How AI Agents Can Work Like Your Engineering Team
AI智能体如何像工程团队一样协同工作？从导师Agent出发，重构你的AI开发工作流
Imagine you are a beginner developer. You have been asked to build a new feature: “Add authentication to the application.” You open your AI coding age…
4
Towards Assurance Closure in AI-Native Large-Scale Agile Software Development
AI原生大规模敏捷开发如何实现保障闭环？这篇arXiv论文给出系统化探索，软件工程从业者值得一读。
arXiv:2608.07317v1 Announce Type: cross Abstract: The AI-Native Manifesto envisions large-scale agile software development in which humans increasingl…
5
SkillMOO: Multi-Objective Optimization of Agent Skills for Software Engineering
面向软件工程智能体的技能多目标优化新方法，值得一读
arXiv:2604.09297v3 Announce Type: replace-cross Abstract: Agent skills are increasingly used to configure coding agents for software engineering (SE) …
6
Feedback Loops and Code Perturbations in LLM-based Software Engineering: A Case Study on a C-to-Rust Translation System
用C转Rust案例揭示LLM工程里的反馈回路与代码扰动，技术深度拉满。
arXiv:2512.02567v2 Announce Type: replace-cross Abstract: The advent of strong generative AI has a considerable impact on various software engineering…
7
Ask HN: How to turn Claude Code into an effective software engineer
吐槽Claude Code过于保守，探讨如何调教它从“避雷”型助手变成真正懂重构的工程师，HN高赞讨论。
Claude code is living in the past. Like an atomically powered steam engine. The LLM is trained on the past. The capabilities have leapt forward, but i…
8
Meta launches Muse Code, an AI agent for large code bases
Meta 发布 Muse Code 测试版，专攻大型代码库的完整工程任务，规划、写码、验证一把抓。
Meta expanded its AI coding offerings with a new agent that, it promises, can handle complex tasks with complex software.
9
The Impact of LLM-Assistants on Software Developer Productivity: A Systematic Review and Mapping Study
系统综述LLM助手对开发者生产力的实证影响，揭示关键证据与挑战，值得开发者和管理者参考。
arXiv:2507.03156v3 Announce Type: replace-cross Abstract: Large language model assistants (LLM-assistants) present new opportunities to transform soft…
10
一年连融三轮数亿元！字节+清华姚班，重构企业软件工程
字节+清华姚班背景，这家AI公司一年三轮融资，解决企业级软件工程“提效难”的痛点，不是吹“10倍”，而是Agent Infra与Harness框架带来的真实60%整体提效。
要做硬核的事情，而非摘低垂的果实
11
Learning from 53.6K Real-World Developer Edits of AI-Generated Code
研究5.36万次真实开发者编辑，揭示AI代码生成模型的实际改进方向
arXiv:2607.25130v1 Announce Type: cross Abstract: Imperfections in AI-generated code require that software developers modify the generated code manual…
12
Clean Code: The Fellowship of the Function
告别“万能函数”，学习如何用职责拆分和整洁命名让代码可读性飙升。
The Quest Begins (The "Why") I still remember the first time I opened a legacy repository and saw a function called handleStuff() . Inside, there were…
13
Cross-Model LLM Code Review: Should you use Claude to review Codex or vice versa?
Claude和Codex交叉审查代码，哪种配对更高效？KDD'26研究揭示答案。
arXiv:2607.21656v1 Announce Type: cross Abstract: Developers increasingly use two coding agents together: one writes a draft, and the other reviews it…
14
Evaluating LLM-Based 0-to-1 Software Generation in End-to-End CLI Tool Scenarios
这篇论文评估了大模型在端到端CLI工具场景中从零生成完整软件的潜力，为AI编程质量提供了新视角。
arXiv:2604.06742v2 Announce Type: replace-cross Abstract: The evolution of Large Language Models (LLMs) has catalyzed a paradigm shift towards intent-…
15
Learn by Building
与其被动接受AI生成的代码，不如主动动手构建——这才是人类保持优势的关键。
As long as we don't have AGI or superintelligence, we still need good software engineers. And even if we do reach AGI and coding is "solved," are we r…
16
Early Adoption of Agentic Coding Tools by GitHub Projects
从学术视角揭示GitHub项目如何采纳AI代理工具生成PR，探索人机协作新范式。
arXiv:2607.14037v1 Announce Type: cross Abstract: Agentic coding tools are increasingly capable of generating and submitting pull requests (PRs) to so…
17
Partial Contracts Suffice: Sound, LLM-Inferred Regression Verification
用LLM推断部分合约，实现无需全程序重新验证的回归验证，大幅降低验证成本。
arXiv:2607.10291v1 Announce Type: cross Abstract: Software evolves continuously, yet ensuring that a patch preserves intended behavior without re-veri…
18
Kill the Loop: Why `while true` Is Not Reliability
别再无脑用while true！它并非可靠保障，更优雅的退出策略才是稳定系统的关键。
Disclosure up front: I build agentproto , which runs checks inside an agent's loop rather than only at the end. Everything about why that matters you …
19
Aleena: Alignment Agent for Research Software Engineering Collaborations
专为研究软件工程协作设计的AI对齐代理Aleena，让AI队友更懂人类科学家的需求与节奏！
arXiv:2607.08043v1 Announce Type: cross Abstract: Research software collaborations span meetings, informal chats, pull requests, and GitHub issues. A …
20
DeepSWE: Measuring Frontier Coding Agents on Original, Long-Horizon Engineering Tasks
新基准DeepSWE用113个原创、长周期软件工程任务评估编码代理，避免SWE-bench的数据泄露问题。
arXiv:2607.07946v1 Announce Type: cross Abstract: DeepSWE is a benchmark of 113 original, long-horizon software engineering tasks for evaluating codin…