A paper titled "LOB-Impact Benchmark" argues that generative limit order book (LOB) models must reproduce realistic market impact to function as world models for trading agents, warning that simulators which misprice this mechanism teach agents policies that are optimal in the simulator but wrong in the real market. The work introduces a benchmark for emergent market impact in generative LOB models, contending that existing metrics assess generated streams purely on realism without capturing this mechanism.
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 pure
EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.