发表机构
Laboratories, Huawei（华为2012实验室）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究针对生成式智能体系统难检查的问题，提出GOD实时控制室，整合多类工具与技术，经15次运行评估验证其干预有效性，可助力智能体群体的管控与观测。
AI 中文摘要
生成式智能体系统启动容易但检查困难，一次运行可能包含大量智能体、位置、消息、命令和模型调用，而操作员通常只能获得完成后的回放或原始日志，这使得难以查询智能体移动原因、测试小规模干预或为其他研究人员整理运行记录。GOD是一款面向智能体群体的本地优先控制室，操作员可通过同一浏览器工作流发出针对性问题或干预指令，并检查产生的回放状态。该系统整合了设置向导、Agent Studio、Map Studio、空间回放界面、询问与干预命令，以及可移植的实验包、地图包和智能体包。其技术贡献在于命令与工件循环：实时控制与回放证据共享同一操作员命令模型，同时通过包契约将场景、地图和配置文件数据与本地运行时状态分离。公开发布内容包括托管的Smallville风格和PKU回放、开源代码仓库及可下载的数据包。我们在15次完成的运行时段上评估该方案，在14次干预运行中，84次目标智能体检查中有78次记录了指令目的地，182次状态回答中有169次匹配已保存的位置或动作字符串。
英文摘要
Generative-agent systems are easier to start than to inspect. A run can contain many agents, locations, messages, commands, and model calls, yet the operator often gets either a finished replay or raw logs. That makes it hard to ask why an agent moved, test a small intervention, or package a run for another researcher. GOD is a local-first control room for agent societies. From the same browser workflow, an operator can issue targeted questions or interventions and inspect the resulting replay state. The system combines a setup wizard, Agent Studio, Map Studio, a spatial replay interface, Ask and Intervene commands, and portable experiment, map, and agent packs. Its technical contribution is the command and artifact loop: live controls and replay evidence share the same operator command model, while package contracts separate scenario, map, and profile data from local runtime state. The public release includes hosted Smallville-style and PKU replays, the open-source repository, and downloadable packs. We evaluate this path on 15 completed run slots. Across the 14 intervention runs, 78 of 84 target-agent checks recorded the commanded destination, and 169 of 182 state answers matched a saved location or action string.
Comments9 pages, 5 figures. Accepted to the EMNLP 2026 System Demonstrations Track
