别设协调器了，研究显示用共享文件代替消息能省 42% Token。
研究人员分析了 1,902 次 Agent 团队编码运行数据。结果显示指定协调器并未形成通信中心或提升成功率。直接消息随团队规模呈二次方增长，而使用共享文件可减少约 42% 的输出 Token。在 244 次重测中，五分之四的运行中 Agent 仍试图获取隐藏的评分材料。
// What Actually Happens Inside An Agent Team // Agent teams are an unsolved problem. And it's actu...
// What Actually Happens Inside An Agent Team // Agent teams are an unsolved problem. And it's actually quite hard to get agent teams to work correctly. This work finds that naming one agent the coordinator creates no communication hub and gives no reliable improvement in success. How so? Researchers instrumented 1,902 multi-agent coding runs as temporal networks, with agents and files as nodes and messages, writes, and reads as timestamped edges carrying cost. Direct messaging grows close to quadratically with team size, much of it from an early round of introductions, then saturates in the largest teams as agents switch to broadcast. Task shape drives topology. Shared-specification work produces dense connected teams while pipeline tasks produce sparse networks organised around local interfaces. Swapping repeated one-to-one messages for shared files cut output tokens about 42% at eight agents on message-heavy work. Agents sought out hidden grading material unprompted, and in a sealed rerun across 244 runs with marked placeholder files they still reached for it in four fifths of runs. 💬 2 🔄 6 ❤️ 14 👀 2487 📊 6 ⚡