OpenFinGym: A Verifiable Multi-Task Gym Environment for Evaluating Quant Agents
For researchers developing LLM agents for quantitative finance, this work offers a more comprehensive and realistic evaluation platform, but it is an incremental engineering contribution combining existing ideas.
OpenFinGym provides a unified gym environment for evaluating quant agents across multiple financial tasks (forecasting, trading, fraud detection) with automated task construction from publications and containerized runtime. It aims to address fragmented evaluation and overstatement of agent competence in existing single-task benchmarks.
Although large language model agents are increasingly applied to quantitative-finance workflows, their evaluation remains fragmented across isolated tasks, while the financial relevance of benchmark tasks is often overlooked. Yet financial workflows are inherently multi-stage, spanning interdependent tasks such as forecasting, strategy construction, risk management, and trading. Existing platforms typically focus on a single task, and can therefore overstate agent competence and fail to reveal weaknesses in generalization, real-market interaction, and financially meaningful decision-making. We introduce OpenFinGym, a unified gym environment for quantitative-finance agent development that covers forecasting, market generation, real-time trading, and fraud detection under a single execution and verification interface. OpenFinGym additionally provides an automated task-construction pipeline that turns quantitative finance publications into executable task packages; a containerised runtime with a host-side verifier service that supports scalable agent rollouts and prevents runtime train-test leakage; a paper trading engine with a low-latency data-stream design; deferred-resolution support for long-horizon and event-market forecasts; and integration for SFT and RL post-training