用多智能体融合预测市场与全球新闻，挖掘高价值投资信号。
PolyGnosis 2.0: Enhancing LLM Reasoning via Agentic Harness Engineering for Polymarket and OSINT Insight Extraction
- 构建多智能体系统，融合预测市场与全球新闻流
- 发现结构化分割是关键，过度反思会导致逻辑偏差
- 适合量化交易与情报分析领域研究者参考
本文提出PolyGnosis 2.0，一种开创性的多智能体架构，通过整合Polymarket异常信号与全球开源情报（OSINT）流，特别是全球事件、语言与情绪数据库（GDELT），提取预测性智能。我们定义并聚焦于‘视角错配’——即Polymarket情绪与全球媒体流向之间的叙事分歧——作为高α交易信号。超越泛化的智能体优势，我们严格量化了‘驾驭工程’技术在高噪声金融领域的有效性，包括反思循环、工具调用、分而治之（D&C）划分和思维链（CoT）。实证评估显示，尽管结构化划分对多维对齐至关重要，但无约束的终端反思会引发逻辑漂移。此外，所有智能体配置均存在普遍的‘共识偏误’，需确定性验证。最终，我们识别出一个帕累托最优配置，在保持专业级分析精度的同时，最小化延迟与令牌开销，为预测市场中的自主智能提供可靠蓝图。
原文摘要 · Abstract (English)
This paper introduces PolyGnosis 2.0, a pioneering multi-agent architecture designed to extract predictive intelligence by synthesizing Polymarket anomaly signals with global Open Source Intelligence (OSINT) streams, specifically Global Database of Events, Language, and Tone (GDELT). We define and target "Perspective Mismatches", the narrative divergence between Polymarket sentiment and global media flows, as high-alpha trading signals. Moving beyond generic agentic superiority, we rigorously quantify the efficacy of "Harness Engineering" techniques, including reflection loops, tool-calling, divide-and-conquer partitioning (D&C), and chain-of-thought (CoT), within high-noise financial domains. Our empirical evaluation against human-expert benchmarks reveals that while structural partitioning is mandatory for multi-dimensional alignment, unconstrained terminal reflection actively induces logical drift. Furthermore, we identify a pervasive "consensus bias" across all agent configurations during narrative reasoning, necessitating deterministic validation. Ultimately, we isolate a Pareto-optimal configuration that achieves professional-grade analytical precision while minimizing latency and token overhead, providing a robust blueprint for autonomous intelligence in prediction markets.
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。