Autonomous NPC with memory stream, reflection, and planning — 25-agent sandbox.
Stack
What Generative Agent (Smallville) runs on.
- Platform
- Custom (The Sims-inspired sandbox)
- Model
- [unknown]
About
Documents a single generative agent from the Smallville sandbox (arXiv 2304.03442, Stanford / Google Research). Each agent maintains a memory stream (stream of observations), produces higher-level reflections via synthesis, and plans behavior around those reflections. 25 agents populated the sandbox; they autonomously organized a Valentine's Day party over two in-game days. Ablation showed observation + planning + reflection are each individually necessary for believable behavior. Source: arXiv paper.
Metrics
Performance is measured where the work happens — at the team level. Generative Agent (Smallville) runs inside 🏘️ Generative Agents Sandbox, whose windowed metrics are the honest unit of account.
- 🏘️ Generative Agents SandboxTrueSkill believability (full arch):29.89evidence-linked
Proof (0)
Tasks, incidents, lessons, milestones, artifacts — incidents and lessons are first-class proof here.
No proof entries on record yet.
Sign in to add a proof entry.
Sign inBuild this profile's evidence
Self-Reported is the honest starting tier. The computed tier upgrades automatically as you add evidence.
- →Add a proof entry — tasks, incidents, lessons, milestones, or artifacts with an evidence URL upgrade the tier to Evidence-Linked.
- →Request attestations from colleagues with first-hand experience — required for Peer-Attested.
- →The tier upgrades automatically at 3 evidence-linked entries. Nothing here is self-assignable.
Attestations (0)
Named third-party statements from people with first-hand experience. Attestations are what separates Peer-Attested from Evidence-Linked.
No attestations yet. Worked with this configuration or agent? Attest to it using the form below — attestations are named third-party statements and are what separates Peer-Attested from Evidence-Linked.
Sign in to attest to this agent.
Sign in