用内部竞争机制提升大模型交易系统稳定性，让决策更可靠。
ContestTrade: A Multi-Agent Trading System Based on Internal Contest Mechanism
- 分数据与研究两队，通过竞赛机制筛选最优策略
- 2024年后A股回测中收益和风险调整后表现优于基线
- 适合关注大模型在金融场景落地的开发者与研究者
在金融交易中，基于大语言模型（LLM）的智能体虽具潜力，但其决策易受噪声与非平稳市场信息影响。本文提出ContestTrade，一种基于机构投资流程设计的多智能体交易系统，包含两个专业团队：(1) 数据团队将海量市场数据浓缩为适配有限上下文窗口的多样化文本因子；(2) 研究团队通过工具增强的深度研究生成并行多路径交易决策。核心是每队内部的“量化-预测-分配”竞赛机制：仅在市场结果可观察后对智能体输出打分，依据历史得分预测未来效用，并将资源分配给预测效用为正的智能体。在2024年后A股回测中，ContestTrade展现出更高回测收益与风险调整后绩效，优于对比基线。文章进一步阐述时间协议、实现细节及局限性，明确结果适用范围。
原文摘要 · Abstract (English)
In financial trading, large language model (LLM)-based agents demonstrate significant potential, but their decisions can be sensitive to noisy and non-stationary market information. We propose ContestTrade, a multi-agent trading system with an internal competitive mechanism inspired by institutional investment workflows. The system consists of two specialized teams: (1) a Data Team that processes and condenses massive market data into diversified textual factors optimized for constrained LLM context windows, and (2) a Research Team that produces parallelized multipath trading decisions via tool-augmented deep research. The core design is a "Quantify-Predict-Allocate" contest mechanism within each team: agent outputs are scored only after market outcomes become observable, future utility is predicted from historical scores, and resources are allocated to agents with positive predicted utility. In a post-2024 A-share backtest, ContestTrade achieves higher backtested return and risk-adjusted performance than the evaluated baselines. We further describe the temporal protocol, implementation choices, and limitations to clarify the scope of these results.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。