Agentic AI 用于预测市场聚类与关系发现：分层 agentic reduction（HAR）管线研究
Agentic AI for Clustering and Relationship Discovery in Prediction Markets
AI 导读
一项 arXiv 研究提出分层 agentic reduction（HAR）管线，用 LLM 推理将预测市场合约按题目与结算规则分入主题聚类，并给出带理由的有符号跨市场关系图。
正文 · 原文
Abstract:Prediction market platforms list thousands of contracts whose logical and economic connections are implicit in their resolution rules. We introduce a hierarchical agentic reduction (HAR) pipeline for constructing inspectable cross-event relation graphs and a behavioral benchmark for evaluating their alignment with market prices. This partitions a catalog of prediction markets, specified by question and resolution text, into topic clusters, applies typed LLM reasoning to small batches, and proposes signed relations with rationales between specific markets. We evaluate semantic relation graphs spanning eight monthly Kalshi catalogs (February to September 2026). Using data from 30.3 million trades, we compute a benchmark that compares linked pairs' signed price-change correlations with those of matched, unlinked controls from the same topic cluster on identical timestamps. Under full-sample and leave-first-week-out evaluation, relations identified by our pipeline exhibit higher signed Pearson price-change correlations, with statistical significance, than matched within-topic controls. This increase also appears under Spearman correlation and becomes larger among relations labeled as medium or high strength. This benchmark provides a criterion for comparing relation-discovery methods against observations beyond their input text, and our results indicate the ability of agentic AI and LLM reasoning to identify meaningful relations between individual markets in connected Web marketplaces.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2512.02436 [cs.AI] |
| (or arXiv:2512.02436v4 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2512.02436 arXiv-issued DOI via DataCite |
Submission history
From: Brian Zhu [view email]
[v1]
Tue, 2 Dec 2025 05:45:48 UTC (327 KB)
[v2]
Sat, 8 Aug 2026 16:26:56 UTC (128 KB)
[v3]
Tue, 29 Sep 2026 14:55:04 UTC (128 KB)
[v4]
Tue, 27 Oct 2026 19:14:49 UTC (96 KB)
来源：arXiv cs.AI · arxiv.org