PolyGnosis 2.0: Enhancing LLM Reasoning via Agentic Harness Engineering for Polymarket and OSINT Insight Extraction
This work provides a blueprint for autonomous intelligence in prediction markets, but the improvements are incremental and domain-specific.
PolyGnosis 2.0 introduces a multi-agent architecture that combines Polymarket anomaly signals with GDELT OSINT to extract predictive intelligence, achieving professional-grade analytical precision by identifying a Pareto-optimal configuration that minimizes latency and token overhead.
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.