PolyGnosis 2.0: 通过智能体工程增强LLM推理，用于Polymarket和OSINT洞察提取
PolyGnosis 2.0: Enhancing LLM Reasoning via Agentic Harness Engineering for Polymarket and OSINT Insight Extraction
AI总结：
本文提出PolyGnosis 2.0多智能体架构，通过融合Polymarket异常信号与全球开源情报（GDELT）来提取预测情报，并量化“视角错配”作为高阿尔法交易信号，同时评估“工具工程”技术（如反射循环、工具调用、分治和思维链）在高噪声金融领域的有效性。
摘要：
本文介绍了PolyGnosis 2.0，这是一种开创性的多智能体架构，旨在通过综合Polymarket异常信号与全球开源情报（OSINT）流（特别是全球事件、语言和语调数据库（GDELT））来提取预测情报。我们定义并瞄准“视角错配”，即Polymarket情绪与全球媒体流之间的叙事分歧，作为高阿尔法交易信号。超越通用的智能体优越性，我们严格量化了“工具工程”技术（包括反射循环、工具调用、分治分区（D&C）和思维链（CoT））在高噪声金融领域的有效性。我们针对人类专家基准的实证评估表明，虽然结构分区对于多维对齐是必需的，但无约束的终端反射会主动导致逻辑漂移。此外，我们在所有智能体配置的叙事推理过程中发现了一种普遍的“共识偏差”，需要确定性验证。最终，我们分离出一个帕累托最优配置，该配置在最小化延迟和令牌开销的同时实现了专业级的分析精度，为预测市场中的自主智能提供了稳健的蓝图。
英文摘要：
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.
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。
