1
国家无线电办公室部署卫星网络国内协调第三方评估：2026 至 2027 年度试行，频率兼容争议可通过独立机构裁决
IT之家 9 月 4 日消息，工信部今日发文，宣布国家无线电办公室近日印发《关于开展卫星网络国内协调第三方机构评估工作（2026—2027 年）的通知》（IT之家以下简称《通知》），于 2026 至 2027 年度试行开展卫星网络国内协调第三方机构评估工作。此举旨在深化空间无线电管理领域改革，提升卫…
2
The Collaboration Tax: How Much LLM Multi-Agent Systems Pay to Coordinate
多智能体协作并非免费午餐，这篇论文量化了LLM系统协调的隐形成本，值得关注。
arXiv:2608.22152v1 Announce Type: new Abstract: Multi-agent systems built from large language models are deployed widely, yet how much performance is …
3
The New Calendly
一键管理会议全流程，自动协调时区与日程，会前会后事务尽在掌握，让约会议变得高效轻松。
Handle all of the work before, during, and after meetings Discussion | Link
4
苹果应用商店出现山寨版政务 App，闽政通官方回应称相关部门正在协调处理
苹果商店惊现山寨“闽政通”，官方回应正协调处理，教你擦亮眼辨真假政务App！
IT之家 8 月 12 日消息，据新黄河今日报道，福建政务服务 App 统一平台（简称“闽政通 App”）在苹果应用商店被“假冒”一事在网上引发关注。 ▲ 左为正版“闽政通”，右为山寨版“闽证通” 该假冒的 App 名为“ 闽证通 ”，其在下载页标注自己是“民政便民服务应用”。 对此，闽政通 App…
5
Show HN: Heddle- ATC for Your Subagents
多AI代理协作编辑代码时，Heddle能像空中交通管制一样防止冲突覆盖，确保高效协同。
A layer above git. git reports collisions after the tokens are spent; Heddle reports them before. Now I spawn as many subagents as I want to work on d…
6
Coordination layer for AI coding agents, built on Git
当多个AI编码代理同时改代码时，它会用Git自动协调冲突，避免AI互相覆盖彼此的工作。
Article URL: https://github.com/zyads/loom-vcs Comments URL: https://news.ycombinator.com/item?id=49044517 Points: 2 # Comments: 0
7
Explainable Belief Harmonization under Dynamic Epistemic Partitions
提出动态认知划分下的可解释信念协调方法，融合共识迭代与逻辑推理，解决多智能体信念组合难题
arXiv:2607.21210v1 Announce Type: cross Abstract: Existing approaches to multi-agent belief combination have established mature foundations for combin…
8
The Lumper Problem
揭示2026年全球认知基础设施中的算法单一文化现象，一场悄然发生的协调奇迹如何塑造AI生成的内容世界。
On the morning of 9 April 2026, a small miracle of coordination is unfolding in the cognitive infrastructure of the planet. A graduate student in Hyde…
9
Cosmonapse – an event-driven protocol for AI agent systems
事件驱动的Agent-to-Agent协议，将智能体视为纯函数、通过消息协调，无需中央编排器，支持Python和TypeScript SDK。
Article URL: https://github.com/Cosmonapse/cosmonapse-core Comments URL: https://news.ycombinator.com/item?id=48987399 Points: 2 # Comments: 0
10
RCWT: Measuring Task-Budget Displacement from Coordination Content in LLM Calls
从协调内容入手，提出RCWT方法量化LLM调用中的任务-预算偏移，为AI系统资源分配提供新视角。
arXiv:2607.12216v1 Announce Type: new Abstract: Multi-agent and memory-augmented LLM systems often place coordination content, shared state, prior dis…
11
OpenAI’s Head of Safety Is Leaving the Company
OpenAI安全负责人离职，内部安全挑战随模型训练加速而加剧，引发行业关注
Johannes Heidecke’s departure comes as OpenAI tries to further integrate its research and safety teams.
12
AgentKindergarten – daycare for your AI coding agents
为AI编码代理提供“日托”服务的开源项目，名字有趣，值得关注。
Article URL: https://github.com/rokrak1/agentkindergarten Comments URL: https://news.ycombinator.com/item?id=48870547 Points: 2 # Comments: 0
13
Learning social norms enhances compatibility in dynamic human-AI coordination
让AI学会人类社会的潜规则，动态合作不再鸡同鸭讲
arXiv:2607.07021v1 Announce Type: new Abstract: Humans continuously coordinate with others in dynamic interactions, often through implicit, hard-to-qu…
14
A-TMA: Decoupling State-Aware Memory Failures in Long-Term Agent Memory
长期记忆系统中“幽灵记忆”如何导致状态失效？解读LLM代理事实变化的协调故障
arXiv:2607.01935v1 Announce Type: new Abstract: Long term memory lets LLM agents act as persistent assistants, but user facts change. A useful memory …
15
A mesh of old phones as bodies, LLM agents as minds — coordinating through a log they argue in
旧手机当躯体、LLM当大脑，靠一份争论日志协调成网格，另类AI实验让人大开眼界。
The shared log in my house has entries I didn't write. The agents write them to each other. Recent ones: "you keep saying 'don't be wrong' but this dr…
16
Governed Shared Memory for Multi-Agent LLM Systems
多智能体LLM如何高效协调？本文提出受治理的共享内存机制，为解决Agent间信息共享与一致性难题提供新方案。
arXiv:2606.24535v1 Announce Type: new Abstract: Multi-agent LLM environments require robust mechanisms for shared knowledge management. This paper for…
17
How Much Coordination Gain Is Real? A Paired Noise-Floor Protocol for Multi-Agent LLM Benchmarks
新协议揭穿多智能体LLM协调增益的虚假繁荣，用配对噪声底线方法精准衡量真实协同效应。
arXiv:2606.20695v1 Announce Type: cross Abstract: Multi-agent LLM coordination papers report small benchmark deltas as evidence that one architecture …
18
ViCoStream: Streaming VideoLLMs Can Run Beyond 100 FPS with Stage-Wise Coordinated Inference
流式视频大模型推理飙至100+FPS，ViCoStream用阶段协调机制破解实时处理瓶颈，视频理解应用提速必读。
arXiv:2606.19849v1 Announce Type: new Abstract: Streaming VideoLLMs must continuously process incoming video while maintaining low query latency, maki…
19
Tracecraft: Multi-agent AI coordination in a bucket you own
多智能体AI协调框架，支持自托管，让你完全掌控数据与协作过程。
Comments URL: https://news.ycombinator.com/item?id=48586547 Points: 1 # Comments: 0
20
Tacit Coordination of Large Language Models
大型语言模型如何在无沟通的多智能体环境中达成隐性协调？这篇论文探索了焦点效应的关键作用。
arXiv:2601.22184v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are increasingly deployed in multi-agent settings that require …