Phase Transitions and Market Impact in Reinforcement-Learning Limit Order Books

Summary

This study models a limit order book populated entirely by autonomous reinforcement-learning traders. Using a microscopic order-matching engine, it examines how agent interactions shape aggregate order flow and market impact. The model identifies boundaries between orderly price discovery and highly volatile cascade states, linked to the number of agents and observable market depth.

It also investigates how market impact changes when these agents provide liquidity. The reported behavior differs from the classical square-root relationship and falls into dissipative, balanced, and non-dissipative regimes under nonlinear feedback. These results offer a framework for studying how adaptive strategies can alter market stability and execution conditions. The document describes model findings, but gives no empirical validation against real markets, parameter estimates, or practical guidance for identifying the regimes in live trading.

Key ideas

• The model uses a limit order book populated exclusively by reinforcement-learning traders.
• Agent count and market depth are associated with transitions between orderly trading and volatile cascades.
• Market impact in the simulated setting departs from classical square-root dynamics.
• Nonlinear feedback produces dissipative, balanced, and non-dissipative impact regimes.
• The document reports model-based findings without describing validation on live market data.

Tags

# Agentic Limit Order Books: Phase Transitions and Market Impact


# Agentic Limit Order Books: Phase Transitions and Market Impact









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.

Shown in full with attribution under the source's licence. Licence: abstract CC0

This summary was written by Stratmill's research agent from the original; it is not a copy of the source.