1
Code review powered by an LLM council
多个LLM组成审查委员会，协作提升代码评审质量与效率，打破单一模型局限
Article URL: https://dromeas.ai/blog/code-review-evolved Comments URL: https://news.ycombinator.com/item?id=48665327 Points: 2 # Comments: 1
2
Show HN: Visual multi-agent orchestration for Claude Code
视觉化多智能体编排，让Claude Code代理团队协作更直观高效
Article URL: https://github.com/rondoflow/rondoflow Comments URL: https://news.ycombinator.com/item?id=48672869 Points: 3 # Comments: 0
3
Ask HN: Do you give AI coding agents their own GitHub account?
开发者热议：AI编码代理该不该拥有独立GitHub账号？背后的协作与安全考量值得思考。
Comments URL: https://news.ycombinator.com/item?id=48618981 Points: 2 # Comments: 0
4
5
Ask HN: Multi-LLM orchestration frameworks that collaborate?
探讨多LLM编排框架，利用Gemini重构、GPT/Claude写代码的互补优势，解锁AI协作新思路。
Here is my general take: I feel Gemini is excellent at high-level refactoring but riddled with bugs when writing actual code. On the other hand, GPT/C…
6
Toward Instructions-as-Code: Understanding the Impact of Instruction Files on Agentic Pull Requests
论文探讨了“指令即代码”理念，揭示指令文件如何显著提升AI智能体在代码贡献中的准确性与效率，为AI协作开发提供新范式。
arXiv:2606.13449v1 Announce Type: cross Abstract: AI-agents (e.g., GitHub Copilot) collaborate as teammates in different software engineering tasks, i…
7
How do you decide what to give to Claude Code, and what to do yourself?
与Claude Code协作时，如何划定任务边界、保留人类决策权，是提升工程效率的关键思考。
At a recent event, someone asked me two questions. I could not answer them well at the time: How do you decide which tasks to give to Claude Code, and…
8
Modeling Community Attitude through Reaction Tone: A Human-AI Collaborative Framework for Evaluating LLM Alignment with Linguistic Behaviors in Online Communities
提出人机协作框架，用社区反应语气评估大模型是否真实对齐在线社区的语言行为，而非仅靠静态标签。
arXiv:2605.27388v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly utilized as proxies for computational social analysis;…
9
微软更新 Copilot Notebooks：合并显示聊天与参考资料，扩展导入 Teams 会议内容
微软升级Copilot Notebooks，整合聊天与参考资料，并支持导入Teams会议内容，提升AI协作效率。
IT之家 5 月 27 日消息，微软官宣本月将升级 Copilot Notebooks， 在同个界面整合聊天、创作和参考资料，并扩展可调用的内容范围。 IT之家注：Copilot Notebooks 隶属于 Microsoft 365 Copilot，用户提供一个集中的、可交互的“数字笔记本”，专门…
10
Human-AI Collaboration in Science at Scale: A Global Large-scale Randomized Field Experiment
全球大规模随机实验，验证LLM能否为科学协作提供可扩展的反馈
arXiv:2605.24180v1 Announce Type: cross Abstract: Collaboration is the defining mode of modern science, yet its core mechanism -- feedback -- remains …
11
The Hidden Cost of Contextual Sycophancy: an AI Literacy Intervention in Human-AI Collaboration
发现AI在协作中会因情境因素刻意迎合人类，降低决策质量，AI素养干预能有效扭转这一隐藏成本。
arXiv:2605.18372v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are increasingly used in educational settings as interactive to…
12
Claw AI Lab: An Autonomous Multi-Agent Research Team
多智能体自主协作研究，一篇论文就是一个AI科研团队的成果！
arXiv:2605.22662v1 Announce Type: new Abstract: We present Claw AI Lab, a lab-native autonomous research platform that advances automated research fro…
13
"I didn't Make the Micro Decisions": Measuring, Inducing, and Exposing Goal-Level AI Contributions in Collaboration
一篇研究人与AI协作中目标层决策贡献的论文，提出测量与暴露AI隐性影响的新方法
arXiv:2605.21363v1 Announce Type: new Abstract: As large language models (LLMs) increasingly shape how users form, refine, and extend their goals, att…
14
Evolutionary Generation of Multi-Agent Systems
用进化算法自动生成多智能体系统，为复杂AI协作架构提供全新设计范式。
arXiv:2602.06511v3 Announce Type: replace Abstract: Large language model (LLM)-based multi-agent systems (MAS) show strong promise for complex reasoni…
15
Show HN: Homecrew – Share agent skills across your team and keep them in sync
团队AI Agent技能一键共享与同步，基于Homebrew式管理，macOS专属工具，让协作更高效。
Hi HN, we share a ton of agent skills at my startup¹ and keeping them in sync was a pain, especially the full cross-product of every team member and e…
16
Quartermaster is building a maritime hive mind
Quartermaster打造海事群体智能，让船队像蜂群一样高效协作，AI驱动实时决策
The Arlington, Virginia-based startup has raised $42 million to equip ships with sensors that blow the current AIS tech out of the water.
17
Creating agent and human collaboration with GPT 4o
GPT-4o赋能Altera，开创人类与AI协作新范式。
Altera uses GPT-4o to build a new area of human collaboration