斯坦福搞了个新方法DeLM，不用中央协调器调度Agent，编程和多文档问答更准更便宜，SWE-bench提升10%成本减半，值得试试。
斯坦福AI实验室提出DeLM（Decentralized Language Models），这是一种无需中央协调器的多Agent协作框架。在SWE-bench Verified基准上，使用Gemini-3 Flash的DeLM实现了约10%的性能提升，同时推理成本降低超过一半。该方法在编程和多文档问答等Agent任务中表现出更高的准确性和经济性。
Learn about how to orchestrate agents without a central orchestrator… in @VentureBeat’s recent artic...
Learn about how to orchestrate agents without a central orchestrator… in @VentureBeat ’s recent article on DeLM! By @Mao_Yuzhen and @Azaliamirh Azalia Mirhoseini @Azaliamirh Thank you @VentureBeat for covering our work on Decentralized Language Models (DeLM)! DeLM makes agentic tasks like coding and multi-doc Q&A more accurate and significantly cheaper, e.g. a ~10% jump on SWE-bench Verified with Gemini-3 Flash at less than half the cost. yuzhenmao.github.io/DeLM/ @Mao_Yuzhen 🔗 View Quoted Tweet 💬 2 🔄 4 ❤️ 8 👀 2456 📊 3 ⚡