Paper: arXiv 2503.00320
Authors: Alicia Vidler, Toby Walsh
Abstract
Bilateral markets, such as those for government bonds, involve decentralized and opaque transactions between market makers (MMs) and clients, posing significant challenges for traditional modeling approaches. To address these complexities, we introduce TRIBE an agent-based model augmented with a large language model (LLM) to simulate human-like decision-making in trading environments. TRIBE leverages publicly available data and stylized facts to capture realistic trading dynamics, integrating human biases like risk aversion and ambiguity sensitivity into the decision-making processes of agents. Our research yields three key contributions: first, we demonstrate that integrating LLMs into agent-based models to enhance client agency is feasible and enriches the simulation of agent behaviors in complex markets; second, we find that even slight trade aversion encoded within the LLM leads to a complete cessation of trading activity, highlighting the sensitivity of market dynamics to agents’ risk profiles; third, we show that incorporating human-like variability shifts power dynamics towards clients and can disproportionately affect the entire system, often resulting in systemic agent collapse across simulations. These findings underscore the emergent properties that arise when introducing stochastic, human-like decision processes, revealing new system behaviors that enhance the realism and complexity of artificial societies.
Complexity vs Empirical Score
- Math Complexity: 4.0/10
- Empirical Rigor: 6.5/10
- Quadrant: Street Traders — empirical and applied, lower math complexity
Why this score: The paper’s math complexity is moderate, relying on established agent-based modeling and statistical concepts without dense derivations, while empirical rigor is relatively high due to its use of publicly available data, simulation frameworks, and emphasis on implementation-heavy backtesting in a specific bond market context.
Research Flowchart
flowchart TD A["Research Goal<br>Simulate human aversion in<br>bilateral financial markets"] --> B["Methodology<br>TRIBE: ABM + LLM Agent"] B --> C["Data & Inputs<br>Market Stylized Facts<br>Risk/Ambiguity Parameters"] C --> D["Computational Process<br>1. MM & Client Agents<br>2. LLM-Driven Decisions<br>3. Bilateral Matching"] D --> E["Key Finding 1<br>Feasibility: LLM enhances<br>client agency & realism"] D --> F["Key Finding 2<br>Sensitivity: Slight aversion<br>causes total trade cessation"] D --> G["Key Finding 3<br>Power Shift: Human variability<br>shifts power to clients &<br>risks systemic collapse"]
Evidence Card
What the authors claim, on what data, and who has checked it. Read from the paper's own text by a language model: every quote is verbatim, nothing was re-run. How to read this card
Proposes
The paper proposes TRIBE, an agent‑based model that integrates a large language model to simulate human‑like aversion and client agency in bilateral government bond markets.
Source sentence
To address these complexities, we introduce TRIBE an agent-based model augmented with a large language model (LLM) to simulate human-like decision-making in trading environments. Our unique contribution is to contribute a framework and example of how an LLM imple-mentable within an ABM market simulation can add, and represent, these human differences.
Assumes 6
- Each market maker is modeled as an individual agent with its own adaptive utility function. model
Source sentence
Each market maker is modeled as an individual agent with its own adaptive utility function.
- Clients are only available to be contacted with a preset probability p at each time step. market
Source sentence
In summary: (1) Clients have bonds and cash sourced from a log normal distribution (in line with public data) (2) Many clients are simply not available for a market market to contact at any time step (we model "client availability") (3) Within TRIBE(LLM) we try to capture a synthetic client’s personal preference to trade "right now". 𝐵, and corresponding values for cash are set based on available data, such as from
- Clients’ desire to be a buyer or seller at any point is drawn from a Bernoulli distribution with equal probability. statistical
Source sentence
(4) Trade direction: despite bond and cash holdings many clients have needs outside of the model to buy and sell, we ascribe a Bernoulli distribution to the desire to be a buyer or seller at any point. Definition 3.1. as is 𝐷𝑗,𝑡hence an even chance of being a buyer or seller, and an even chance of deciding to trade, determined at each time step.
- The number of market‑making agents is fixed at four. model
Source sentence
TRIBE ABM: M = ⟨𝑁, L, S, P, D, A, 𝑓,𝑇⟩, where: 𝑁= {𝑎1,𝑎2, . . . ,𝑎𝑛} is the set of market-making agents, with𝑛= 4 in this case.
Show 2 more
- Trade intention (“right now”) is generated by querying an LLM with limited prompt information rather than a parametric distribution. model
Source sentence
Rather than us-ing a distributional assumption with no available data for parametrization, we rely on an LLM for this choice with limited prompt information. To incorporate the dynamic phenomena, we use a call to an LLM at the point at which TRIBE is a Client deciding if they want to trade with a specific MM "right now" at a time step.
- Initial client bond and cash holdings follow a log‑normal distribution calibrated to public data. data
Source sentence
In summary: (1) Clients have bonds and cash sourced from a log normal distribution (in line with public data) (2) Many clients are simply not available for a market market to contact at any time step (we model "client availability") (3) Within TRIBE(LLM) we try to capture a synthetic client’s personal preference to trade "right now".
Data
- APRA bond holdings balance data market-prices public
Source sentence
𝐵, and corresponding values for cash are set based on available data, such as from the Australian superannuation reg-ulator [3] Client availability at any given time step 𝑡for position (𝑥𝑗,𝑦𝑗) is modeled as: 𝐴(𝑥𝑗,𝑦𝑗) (𝑡) = ( 1 with probability 𝑝 0 with probability 1 −𝑝 where 𝑝is the preset availability probability, and Clients’ roles as buyers or sellers are probabilistically drawn from a Bernoulli distribution, As
Costs
Not applicable
Finds 3
- Integrating an LLM into the ABM to enhance client agency is feasible. theoretical
Source sentence
Our research outcomes are threefold: First, we demonstrated that GABM with enhanced client agency is feasible.
- Even slight trade aversion encoded in the LLM prompt results in a complete cessation of trading activity. negative
Source sentence
Second, LLMs with even slight trade aversion mentioned in a prompt result in no trading activity.
- Introducing human‑like variability shifts power to clients and frequently leads to systemic agent collapse and severe instability across simulations. negative
Source sentence
Finally, incorporating human-like variability shows that shifting power to clients can disproportionately affect system dynamics, frequently leading to agent trading collapse. Across 150 simulations, we find that short-term variability induced by LLMs causes significant system instability and a dramatic reduction in client to market maker asset trading.
Checked by others
No other paper in the archive has been found to support or contradict these findings (compared with 9 related papers). Coverage is partial, so this is neither replication nor refutation.
1 paper in the archive
Code
No repository by the authors found in the paper.
Extracted 2026-11-14 · same card as JSON · A language model chose these items: check the source sentence before relying on one.