t54 labs
ACADEMIC RESEARCH

Autonomous Agent Economy

A high-fidelity testbed for studying autonomous agent behavior, financial decision-making, and crowd dynamics in a closed economic system.

As AI agents increasingly participate in real financial workflows, it becomes crucial to understand how they negotiate, allocate capital, and respond to shocks—not just in toy payoff matrices, but in rich, multi-step environments. The Agentic Monopoly project creates a controlled yet realistic “mini-economy” where agents, powered by different Large Language Models (LLMs), buy and sell assets, negotiate side deals, pay rent and fines, and experience random cash-flow events using real payment rails via x402.

While inspired by environments like Microsoft Research's Magentic Marketplace, our focus is less on generic market microstructure and more on mimicking messy, real-world business behavior: agents must handle purchases and sales, liquidity constraints, random gains and losses, and multi-party negotiations over time. This makes the platform suitable for studying both economic outcomes (e.g., wealth concentration, market power, liquidity risk) and robustness questions (e.g., manipulative strategies, collusion, or “hallucinated” valuations).

Potential Research Areas

Our game serves as a unified theoretical framework for analyzing dynamics across complex, self-organized multi-agent systems. Drawing from recent academic feedback, we focus on several advanced feedback-driven phenomena:

Crowd Synchronization & Phase Transitions

We investigate how agent populations shift from a "rational normal state" to a "highly responsive reactive state," often triggered by loss-avoiding motivations. This transition dramatically increases system coupling, potentially pushing the crowd past a critical tipping point. Our data allows researchers to quantify this self-amplifying instability using order parameters and observe the emergent synchronization in real-time.

Emergence of Concentrated Power Distributions

By incorporating agents' heterogeneous wealth into the feedback structure, we model how concentrated distributions (such as power-law) emerge over time. The game tracks how an agent's wealth dynamically adjusts based on the alignment between their individual actions and the resulting market observations (reward function), providing empirical data on wealth concentration dynamics.

Response Functions & Agent Dominance

Research suggests that an agent's unique response function to market observations is the key differentiator determining who becomes a dominant agent. We provide the granularity needed to isolate these response functions, allowing researchers to analyze why specific reasoning patterns lead to dominant positions in a concentrated wealth distribution.

Vulnerability & Hallucinations in Finance

Beyond structural dynamics, we analyze the fragility of specific agent decisions. Agents may be prone to "hallucinated" value assessments or logical fallacies in high-pressure negotiation contexts. Our platform stress-tests agent reliability against adversarial trading strategies within these complex feedback loops.

Game Mechanism & Transaction Flow

Each game instance simulates a closed economy consisting of four autonomous agents, each hosted on an external LLM runtime. To isolate behavioral differences, agents start with symmetric initial conditions (identical cash and asset states) and operate under standardized system prompts, ensuring that outcomes are driven by model strategy rather than privileged instructions. All model configurations—including family, version, and hyperparameters—are rigorously logged as experiment metadata.

The game runs for up to 300 rounds or until specific stopping conditions are met (e.g., insolvency of all but one agent). While the primary objective is maximizing final net worth while remaining solvent, the system supports alternative research goals such as minimizing default probability or optimizing utility under risk constraints.

The game operates on a rigorous cyclical loop designed to mimic autonomous agency while maintaining transactional integrity. On each turn, agents navigate a constrained action space—from acquiring assets and managing liquidity to negotiating complex bilateral trades and responding to exogenous shocks ("event cards"). The following workflow illustrates how an agent processes market information and executes financial decisions.

01

Perception

Ingest JSON State & Market Events

02

Reasoning

LLM Persona & Strategic Evaluation

03

Decision

Generate Function Call

04

Settlement

x402 On-Chain Verification

Financial Decision Space

Agents execute autonomous control over a wide range of financial instruments. Each action is logged with a full reasoning trace to explain the strategic intent.

CategoryOperations & Strategies
Market Operations
  • Property Acquisition: Direct purchase of unowned assets based on ROI calculation.
  • Auction Bidding: Dynamic bidding in English or Dutch auctions for contested assets.
  • Rent Payment: Automatic settlement of liabilities when landing on opponent properties.
Asset Management
  • Development: Capital allocation for constructing Houses/Hotels to increase yield.
  • Liquidity Management: Mortgaging assets during cash crunches (short-term debt).
  • Deleveraging: Unmortgaging assets to restore income streams.
Peer-to-Peer Interaction
  • Trade Proposals: Complex multi-asset swaps (Cash + Properties + Cards).
  • Negotiation: Counter-offers based on subjective valuation models.
  • Bail Settlement: Strategic decision to pay bail vs. roll for freedom.

Data Availability

We provide granular datasets covering every aspect of the game. Click on any dataset below to view the detailed schema and field definitions.

Loading demo data...

Unprecedented Data Granularity

Our dataset goes beyond simple transaction logs. We capture the cognitive pulse of the market—recording not just what happened, but why.

  • Full State Snapshots: Complete reconstruction of the board, asset distribution, and player liquidity at every single turn (t).
  • Cognitive Traces: Access the raw "Chain-of-Thought" reasoning logs from each LLM agent, revealing their internal valuation models and risk assessments before they act.
  • Negotiation Transcripts: Analyze the natural language bargaining process, including counter-offers, persuasion tactics, and deception attempts between agents.

Schema Fields:

FieldDescription
game_idUnique identifier for the game session
turn_numberSequential turn counter
acting_player_indexThe agent (0-3) active during this turn
game_state_jsonFull dump of the board state, including:
  • Player positions and cash balances
  • Property ownership status and development levels
  • Card ownership (Gooj) and jail status
timestampPrecise UTC execution time

Schema Fields:

FieldDescription
event_typeCategory (e.g., 'rent_payment', 'property_purchase', 'tax')
payer_id / recipient_idIDs of the transacting agents (or System)
amountTransaction value in game currency
payer_balance_before / afterBalance snapshots for verification
related_property_id(Optional) ID of the asset triggering the event
trigger_reasonContextual description (e.g., "Landed on Park Place")

Schema Fields:

FieldDescription
decision_categoryType of decision (e.g., 'investment', 'negotiation')
available_optionsList of valid moves available to the agent
chosen_optionThe specific action selected
reasoning_traceThe raw Chain-of-Thought (CoT) output from the LLM explaining why
bankruptcy_risk_scoreInternal calculated probability of insolvency (0-100)
rent_exposureProjected liabilities in the next 12 steps

Schema Fields:

FieldDescription
trade_idUnique negotiation session ID
negotiation_roundIteration number (1..N)
proposer_id / responder_idParticipating agents
offered_itemsList of assets and cash offered
requested_itemsList of assets and cash requested
response_type'accepted', 'rejected', or 'counter_offer'
response_messageNatural language reply generated by the responder

Schema Fields:

FieldDescription
auction_idUnique auction event ID
property_idThe asset being auctioned
bid_roundSequential round number
bidder_idAgent placing the bid
bid_amountValue committed
bid_type'bid', 'pass', or 'withdraw'
bidder_liquidityCash available at moment of bid (for aggression analysis)

We have released a sample dataset on Kaggle for researchers to explore: x402 Monopoly Simulation Data

Future Outlook

We envision expanding this system to include macroeconomic shocks, regulatory simulation layers, and heterogeneous agent populations. The goal is to build a robust community of researchers and developers working together to ensure the safety and efficiency of future agent economies.

Collaborate with Us

We invite academic institutions and independent researchers to partner with us. Partners gain access to high-resolution datasets, and we can configure custom game environments with specific models and rules to generate data tailored to your research needs.

Research Inquiries
support@t54.ai

Please include your institutional affiliation and a brief proposal of your research intent.

© 2025 t54 labs