PolySwarm：一种多智能体大语言模型框架，用于预测市场交易和延迟套利
PolySwarm: A Multi-Agent Large Language Model Framework for Prediction Market Trading and Latency Arbitrage
AI总结：
本文提出PolySwarm框架，通过多智能体大语言模型实时预测市场交易和去中心化平台上的延迟套利，结合贝叶斯方法和信息论分析，展示其在概率校准上的优越性能。
摘要：
本文介绍了PolySwarm，一种新的多智能体大语言模型（LLM）框架，用于在去中心化平台上进行实时预测市场交易和延迟套利。PolySwarm部署了50个多样化的LLM角色，同时评估二元结果市场，通过置信度加权的贝叶斯组合，将群体共识与市场隐含概率相结合，并应用四分之一凯利仓位大小进行风险控制执行。系统集成了基于Kullback-Leibler（KL）散度和Jensen-Shannon（JS）散度的信息论市场分析引擎，以检测跨市场不效率和否定对误定价。延迟套利模块利用滞后的Polymarket价格，通过对数正态定价模型推导CEX隐含概率，并在人类反应时间内执行交易。我们提供了完整的架构描述、实现细节和评估方法，使用Brier分数、校准分析和对数损失指标，与人类超预测者性能进行基准测试。我们进一步讨论了开放挑战，包括智能体池中的幻觉、大规模计算成本、监管暴露和反馈回路风险，并概述了未来研究的五个优先方向。实验结果表明，群体聚合在Polymarket预测任务中的概率校准上始终优于单模型基线。
英文摘要：
This paper presents PolySwarm, a novel multi-agent large language model (LLM) framework designed for real-time prediction market trading and latency arbitrage on decentralized platforms such as Polymarket. PolySwarm deploys a swarm of 50 diverse LLM personas that concurrently evaluate binary outcome markets, aggregating individual probability estimates through confidence-weighted Bayesian combination of swarm consensus with market-implied probabilities, and applying quarter-Kelly position sizing for risk-controlled execution. The system incorporates an information-theoretic market analysis engine using Kullback-Leibler (KL) divergence and Jensen-Shannon (JS) divergence to detect cross-market inefficiencies and negation pair mispricings. A latency arbitrage module exploits stale Polymarket prices by deriving CEX-implied probabilities from a log-normal pricing model and executing trades within the human reaction-time window. We provide a full architectural description, implementation details, and evaluation methodology using Brier scores, calibration analysis, and log-loss metrics benchmarked against human superforecaster performance. We further discuss open challenges including hallucination in agent pools, computational cost at scale, regulatory exposure, and feedback-loop risk, and outline five priority directions for future research. Experimental results demonstrate that swarm aggregation consistently outperforms single-model baselines in probability calibration on Polymarket prediction tasks.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
