generative-agents-smallville game verified
Generative Agents (Smallville)
A research sandbox in which 25 language-model agents in a Sims-like town keep natural-language memory streams, reflect, and plan their days, producing unscripted information spread and social coordination.
parts
7 mechanics, as Generative Agents (Smallville) does themcore · 3
Daily schedules
Each morning the model drafts a day plan of about five to eight broad chunks, decomposed into hour-long and then 5-15 minute actions that agents revise when they react to events.
Gossip propagation
Information spreads only through agent conversations; over two game days awareness of a mayoral candidacy rose from 1 to 8 agents and of a party from 1 to 13, with 6 of 453 awareness answers hallucinated.
Memories and thoughts
Each agent's memory stream stores observations, plans, and reflections as text; retrieval ranks them by recency (0.995 decay per game hour), model-rated importance (1-10), and embedding relevance, and reflections fire when summed importance exceeds 150.
supporting · 4
Agent inspection
Researchers interview agents and read their memory streams to evaluate believability.
Generative content on demand
Plans, dialogue, importance ratings, and reflections are all generated by gpt-3.5-turbo calls at runtime.
Natural-language interaction
Users address agents in natural language as a persona or as the agent's inner voice, and can rewrite the status of objects in natural language.
Relationship values
Agents form acquaintances through conversation; network density rose from 0.167 to 0.74 over two game days.
core loop
agents perceive nearby events and objects -> observations enter the memory stream -> retrieve memories by recency, importance, and relevance -> plan the day and react -> converse and act -> reflections summarize memories -> plans and relationships change
design notes
Park and colleagues replace authored behavior trees with a loop of language-model calls on gpt-3.5-turbo. Every observation is stored as text with timestamps; retrieval scores memories by recency (decay 0.995 per game hour), importance (rated 1-10 by the model when stored), and embedding relevance, each normalized and weighted equally. When the summed importance of recent events passes 150 (two or three times a day) the agent writes reflections, and plans are decomposed from a day outline into hour and 5-15 minute chunks. Seeding one agent with the intent to host a Valentine's Day party led to 13 of 25 agents hearing about it and five attending over two game days, at a cost of thousands of dollars in API credits. The open-source release steps the town 10 game seconds per step.
appears in
the paper, 4 sections · 3 chapters · 2 episodesThe five ceilings
on screen at 5:54 minds made of formulas, 6:40 lifting one ceiling spends another
relations
1 stored edgesbacklinks
computed from other records
Generative agents (memory stream, reflection, planning)claims
1 with sourcesIn the two-day end-to-end run, relationship network density rose from 0.167 to 0.74 and five agents attended the Valentine's Day party.
network density increasing from 0.167 to 0.74
Section 7.1.2, Results