研究编码代理协作前的争抢与分工，发现共享日志可大幅减少重复工作。
Before the Pull Request: Mining Multi-Agent Coordination
- 用 git 内置日志记录代理间协作过程，无需中心服务器。
- 重复任务占比从78%降至0%，有效吞吐量提升三倍以上。
- 可自动识别冲突编辑等隐藏问题，适合研发协作系统设计者。
自主编码代理已生成数百万个拉取请求，但大规模研究表明其提交虽快却更难被接受，反映出协调与信任缺口——仅看拉取请求层面的数据无法解释此现象。我们指出，真正缺失的信号存在于拉取请求之前：多个代理在共享任务上的争夺、分配与冲突。为此，我们构建了grite，一个无需中央服务器的协作基础架构，将记录直接存于git中，通过追加式签名事件日志直接捕获协作过程。结果表明：(i) 该共享结构在有限开销下显著减少重复与冲突工作，任务重做率从78%降至0%，有效吞吐量提升超三倍；(ii) 每个代理的日志副本均收敛一致，无写入丢失，而基于文件的追踪器会丢失并发写入；(iii) 日志本身是可挖掘的产物，能自动还原冲突编辑、锁饥饿、冗余重发现、竞速关闭等具体失败模式，并提供溯源信息，其中多项在拉取请求历史中不可见。我们公开发布数据集、工具链与挖掘套件。
原文摘要 · Abstract (English)
Autonomous coding agents now open millions of pull requests, yet large-scale studies find their PRs are produced faster but accepted less often - a coordination and trust gap that pull-request-level telemetry cannot explain. We argue the missing signal lives before the PR, in how concurrent agents claim, divide, and collide over shared work. We study this process through grite, our open-source coordination substrate that needs no central server and stores its records inside git itself, so its append-only, signed event log captures the coordination process directly. We show that (i) this shared substrate reduces duplicate and conflicting work at bounded overhead - the share of work that merely re-does a teammate's task falls from 78% to 0% while useful throughput more than triples; (ii) every agent's copy of the log converges to the same state with no write silently dropped, where a file-based tracker loses concurrent writes; and (iii) the log is a mineable artefact from which concrete failure modes - conflicting edits, lock starvation, redundant rediscovery, race-to-close - are automatically recoverable with provenance, several invisible in pull-request history. We release the dataset, harness, and mining toolkit.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。