one dataset · paper, tables, graph, wiki
simgrammar the grammar of simulation

core loop

seed agents with personas and community goals -> concurrent modules perceive, remember, talk, and act in Minecraft -> cognitive controller commits a coherent decision -> roles specialize and rules are paid, debated, and amended -> beliefs and memes spread between towns

design notes

PIANO runs about ten modules concurrently at different speeds (memory, action awareness, goal generation, social awareness, talking, skill execution), with fast non-language reflex networks and a cognitive controller that acts as a bottleneck and broadcasts one decision so speech and action stay consistent; GPT-4o was the strongest base model. In 30-agent runs agents settled into persistent roles (farmer, miner, engineer, guard, explorer, blacksmith) that collapsed without the social module. In a 29-agent constitution experiment with a 20 percent tax paid into community chests every 120 seconds, pro- and anti-tax influencers shifted votes, amendments passed, and payments followed the new rate. In a 500-agent run, Pastafarianism seeded by 20 priests spread to other towns; 1,000-agent attempts exceeded the Minecraft server's capacity. The preprint states no public code release.

relations

9 stored edges
uses

Elections

Constituents give feedback on a constitution, amendments are generated, agents vote, and the amended constitution is distributed on a fixed schedule (feedback at 300 s, vote at 420 s, distribution at 600 s).

core
uses

Gossip propagation

Memes and a religion (Pastafarianism, seeded by 20 priests in one town) spread through agent conversations and travel; conversion was tracked by keyword use and had not saturated after two hours.

core
uses

Taxation

Agents deposit a share of inventory into community chests every 120 seconds at the constitutional rate, starting at 20 percent; when amendments cut it to 5-10 percent, payments fell to about 9 percent.

core
uses

Generative content on demand

Goal generation, talking, and the cognitive controller run on language-model calls, with GPT-4o as the base model in the strongest configuration.

supporting
uses

Hand crafting

Agents gather and craft Minecraft items; a 49-agent group plateaued at about 320 unique items over four hours.

supporting
uses

Memories and thoughts

A memory module stores conversations, actions, and observations across short and long timescales.

supporting
uses

Relationship values

A social-awareness module infers other agents' sentiment, and the paper compares perceived with true likeability.

supporting
uses
supporting

backlinks

computed from other records

claims

1 with sources
c01high

Experiments ranged from 10 to 500 agents in reported results; runs above 1,000 agents were attempted but exceeded the Minecraft server's capacity.

src-altera-2024-project-sid

sources

1
Altera.AL, Andrew Ahn, Nic Becker (2024-10-31). Project Sid: Many-agent simulations toward AI civilization. arXiv

provenance

runs in log/runs
2026-10-24
created2026-10-24-catalog-gdcatalog