LOB-Impact Benchmark: Emergent Market Impact in Generative Limit Order Book Models

Hugging Face Daily Papers Papers
limit-order-book generative-models market-impact benchmark financial-ai autoregressive-models

Summary

The paper introduces LOB-Impact, an open-source benchmark showing that neural generative limit order book models trained on next-token prediction exhibit emergent market impact when metaorders are injected, with impact exponents between 0.63 and 1.21, though relaxation decay remains unobserved likely due to short context windows.

Realistic market impact is essential for generative limit order book (LOB) models to serve as world models for trading agents. If a simulator misprices this mechanism, agents learn policies that are optimal in the simulator but wrong in the real market. Existing metrics assess generated streams purely through distributional comparison with historical data, leaving counterfactual response to an agent's own orders largely unexplored. Here, we show that market impact emerges naturally in neural LOB generators trained solely for next-token prediction. We inject execution-style metaorders into the generated message flow of five autoregressive models across five NASDAQ stocks and measure the response using estimators from the empirical impact literature, validated on baselines whose physics is known in advance. Our benchmark evaluates any message-level generator in three phases: free generation (reading order-flow persistence against price diffusivity); metaorder injection (yielding the impact law's exponent and amplitude); and a post-execution window (measuring relaxation). In addition, comparing each visible injection to a blind, simulator-only control isolates the model's learned response from standard book mechanics. For every model on every stock, we measure how the impact responds as a function of cumulative metaorder participation. Interestingly, we observe emergent impact in generative models of market data, with exponents in the range of 0.63 to 1.21, slightly above the traditional 0.5 of the square-root law of impact. In the family of models tested, we are so far unable to observe impact decay during relaxation. We tentatively attribute this to the still-short context windows of the models. We release the benchmark as open source to validate future generative models for market data.
Original Article
View Cached Full Text

Cached at: 10/30/26, 03:16 AM

Paper page - LOB-Impact Benchmark: Emergent Market Impact in Generative Limit Order Book Models

Source: https://huggingface.co/papers/2610.27100

Abstract

Neural generative limit order book models trained for next-token prediction exhibit emergent market impact under metaorder injection, though relaxation decay remains unobserved due to limited context windows.

Realistic market impact is essential for generative limit order book (LOB) models to serve as world models for trading agents. If a simulator misprices this mechanism, agents learn policies that are optimal in the simulator but wrong in the real market. Existing metrics assess generated streams purely through distributional comparison with historical data, leaving counterfactual response to an agent’s own orders largely unexplored. Here, we show that market impact emerges naturally inneural LOB generatorstrained solely fornext-token prediction. We inject execution-style metaorders into the generated message flow of fiveautoregressive modelsacross five NASDAQ stocks and measure the response using estimators from the empirical impact literature, validated on baselines whose physics is known in advance. Our benchmark evaluates any message-level generator in three phases: free generation (reading order-flow persistence against price diffusivity); metaorder injection (yielding the impact law’s exponent and amplitude); and a post-execution window (measuring relaxation). In addition, comparing each visible injection to a blind, simulator-only control isolates the model’s learned response from standard book mechanics. For every model on every stock, we measure how the impact responds as a function of cumulative metaorder participation. Interestingly, we observe emergent impact ingenerative modelsof market data, with exponents in the range of 0.63 to 1.21, slightly above the traditional 0.5 of the square-root law of impact. In the family of models tested, we are so far unable to observe impact decay during relaxation. We tentatively attribute this to the still-shortcontext windowsof the models. We release the benchmark as open source to validate futuregenerative modelsfor market data.

View arXiv pageView PDFProject pageGitHub3Add to collection

Get this paper in your agent:

hf papers read 2610\.27100

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2610.27100 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2610.27100 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2610.27100 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

ReLOBGen: Replayable Limit Order Book Message Generation

arXiv cs.LG

The paper proposes ReLOBGen, a limit order book message generator that ensures replayability by construction by selecting referenced orders from the current resting book and masking invalid tokens, achieving 100% replayability in 500-message rollouts and a 2.7-3.6x speedup per replayed message over the LOBS5 baseline.

Do LLMs Understand Limit Order Book Dynamics?

arXiv cs.AI

This paper investigates whether large language models trained on synthetic limit order book data develop an accurate world model, finding that while they generate valid sequences, they have systematic errors leading to biased and spurious forecasts.