GOD: Govern, Observe, and Direct - A Real-Time Control Room for Agent Societies
Artificial IntelligenceMultiagent Systems
Summary
The authors created GOD, a tool that helps people control and understand groups of virtual agents in simulations. Instead of just watching a finished replay or raw data, users can ask questions and make changes during or after a simulation. GOD combines features like maps, agent editors, and easy ways to test and share experiments. Their system ensures that commands and results are connected, making it easier to explore why agents behave a certain way. They tested GOD on several runs and found it reliably tracked agent actions and states.
generative-agent systemssimulation replayagent interventionlocal-first controlspatial interfaceagent profilingscenario packagingcommand modelexperiment reproducibility
Authors
Yige Luo, Ran Guan
Abstract
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.