开源项目Myco，帮你统一调度Claude、DeepSeek等多个LLM，实现智能体群组协作。
Article URL: https://github.com/primoia/myco Comments URL: https://news.ycombinator.com/item?id=48234596 Points: 1 # Comments: 0
多智能体LLM状态协调新方案，自动读集重建无需改动SDK
arXiv:2605.17076v1 Announce Type: new Abstract: Concurrent LLM agents sharing mutable natural-language state produce Structural Race Conditions (SRCs)…
用Markdown文件驱动多模型AI代理协作，实现任务路由与自我优化，让团队越用越强
Article URL: https://github.com/yehudalevy-collab/polis-protocol Comments URL: https://news.ycombinator.com/item?id=48171752 Points: 2 # Comments: 0
针对多智能体LLM协调中序列微调导致上下文分布偏移的缺陷，提出信任区域微调方法，有效提升团队协同表现。
arXiv:2605.15207v1 Announce Type: new Abstract: Multi-agent LLM systems have shown promise for complex reasoning, yet recent evaluations reveal they o…
OpenAI 发布出站协调披露政策，主动报告第三方漏洞，推动规模化负责任的安全协作。
OpenAI introduces its Outbound Coordinated Disclosure Policy to guide how it responsibly reports vulnerabilities in third-party software—emphasizing i…
AI原生组织与AI辅助截然不同。它让AI代理成为一等公民，拥有稳定身份和持久上下文，代理之间直接协调而非人类中转。人类只负责方向、判断和关系工作。aweb.ai的真实实践，为小团队指明操作路线。
Article URL: https://aweb.ai/blog/ai-first-company-howto Comments URL: https://news.ycombinator.com/item?id=48158737 Points: 3 # Comments: 11