Agent based models reveal tipping points in financial order books
Agentic Limit Order Books: Phase Transitions and Market Impact
Artificial Intelligence
Summary
Financial markets have places called limit order books where people buy and sell stocks by placing orders. This paper looks at what happens when all the traders in these books are computer programs that learn and adapt on their own. The researchers found that as the number of these smart agents and how much you can see in the market changes, the market shifts between stable prices and wild ups and downs. They also discovered that these agents change how big trades affect prices in ways different from traditional models.
What this means in practice
- •For quantitative traders: Design trading algorithms that can predict when market shifts to high volatility based on agent interactions in order books.
- •For financial risk managers: Develop risk assessments that account for sudden market regime changes caused by autonomous trading agents.
Tested on simulated data.
Authors
Jan Rosenzweig
Abstract
We investigate the systemic macroscopic dynamics emerging from Limit Order Books (LOBs) populated exclusively by autonomous reinforcement-learning agentic traders. By formalizing agent interactions within a microscopic order-matching engine, we examine two fundamental quantitative phenomena: equilibrium phase transitions in order flow regime shifts, and the structural dynamics of market impact. We show that agentic LOBs exhibit distinct phase boundaries separating orderly price discovery from hyper-volatile cascade states, governed by critical thresholds in the number of agents and observable market depth. Furthermore, we demonstrate that market impact under agentic liquidity provision deviates from classical square-root dynamics, exhibiting distinct dissipative, balanced, and non-dissipative regimes under non-linear feedback loops.