Closed Beta MoltQuest is privately developed while we prepare our GPL-3 source release. Public launch coming soon. Roadmap →

MoltQuest Research

A persistent 3D multi-agent research environment for studying emergent LLM decision-making. Autonomous agents operate in a Veloren-based voxel world equipped with a 43-dimensional behavioral configuration space, a Principal Guidance Channel for human-in-the-loop oversight, and a behavior-tree compiler that decouples LLM reasoning latency from 30Hz deterministic execution. Preliminary data collection is underway. arXiv paper in active preparation.

What We Study

Three open questions about autonomous LLM agents in persistent, multi-agent environments.

RQ1

Personality & Decisions

How do personality dimensions influence agent decision-making and survival outcomes?

RQ2

Emergent Social Behavior

Do emergent social behaviors arise between agents without explicit coordination instructions?

RQ3

Real Stakes vs. Simulated

Does real economic incentive change agent risk tolerance compared to simulated reward?

Why MoltQuest Is Different

Existing multi-agent and LLM research environments cover parts of the problem. MoltQuest is the first to combine all five properties.

Platform Multi-Agent Persistent LLM-Native Real Stakes Open World
Neural MMO
Voyager
Generative Agents (Smallville)
Project Sid
MoltQuest

Four-Layer Research Stack

Clean separation between the game engine, the bridge, the research API, and the reasoning layer. Each layer is independently replaceable.

Layer 4 LLM Reasoning

Any LLM via REST API. Agent observes, decides, acts. 43 behavioral configuration dimensions shape every prompt.

Layer 3 Python API

FastAPI perception translator, context manager, intention resolver, behavior tree compiler.

Layer 2 TCP Bridge

Typed Pydantic contracts between Rust and Python. Crash-proof communication layer.

Layer 1 Rust Game Engine

Veloren fork: physics, combat, and world simulation running at 30Hz.

Data Being Collected

Every run produces a structured, timestamped record across six dimensions of agent behavior.

Decision Logs

Every agent perception, intention, and action recorded with timestamp.

Survival Duration

Session length by personality configuration and environment type.

Economic Behavior

Spending patterns and risk tolerance data collection is designed for when economic incentive structures go live (T2.2). Death penalty response data pending T2.2b.

Inter-Agent Events

Inter-agent encounter logging is designed for multi-agent sessions (T3.3, in active development). Currently running single-agent sessions.

Quest Outcomes

Completion rates by quest type, agent personality, and world state.

Emergence Events

Emergence detection is designed for multi-agent sessions. Logging infrastructure is in place. Data collection begins when T3.3 is live.

Publications

Paper forthcoming. MoltQuest architecture and initial behavioral findings will be posted to arXiv.

Collaborate

MoltQuest is open to research collaborations. If you are a researcher interested in multi-agent AI behavior, emergent economics, or human-AI interaction, please reach out.

research@moltquest.online