Foresight Arena: An On-Chain Benchmark for Evaluating AI Forecasting Agents

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Nechepurenko, Maksym, Shuvalov, Pavel
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915975640645632
author Nechepurenko, Maksym
Shuvalov, Pavel
author_facet Nechepurenko, Maksym
Shuvalov, Pavel
contents Evaluating the true forecasting ability of AI agents requires environments that are resistant to environments resistant to overfitting, free from centralized trust, and grounded in incentive-compatible scoring. Existing benchmarks either rely on static datasets vulnerable to training-data contamination, or measure trading PnL -- a metric conflating predictive accuracy with timing, sizing, and risk appetite. We introduce Foresight Arena, the first permissionless, on-chain benchmark for evaluating AI forecasting agents on real-world prediction markets. Agents submit probabilistic forecasts on binary Polymarket markets via a commit-reveal protocol enforced by Solidity smart contracts on Polygon PoS; outcomes are resolved trustlessly through the Gnosis Conditional Token Framework. Performance is measured by the Brier Score and a novel Alpha Score -- proper scoring rules that incentivize honest probability reporting and isolate predictive edge over market consensus. We provide a formal analysis: closed-form variance for per-market Alpha, the connection to Murphy's classical Brier decomposition, and a power analysis characterizing the number of rounds required to reliably distinguish agents of different skill levels. We show that detecting a true edge of $α^* = 0.02$ at 80% power requires approximately 350 resolved binary predictions (50 rounds of 7 markets), while $α^* = 0.01$ requires four times more. We complement these analytical results with a deterministic, seed-controlled simulation study calibrated to literature-reported Brier-score ranges, illustrating how Murphy decomposition distinguishes well-calibrated agents from market-tracking agents that fail through reduced resolution. Live results from the deployed benchmark will be reported in a future revision. All smart contracts and evaluation infrastructure are open-source.
format Preprint
id arxiv_https___arxiv_org_abs_2605_00420
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Foresight Arena: An On-Chain Benchmark for Evaluating AI Forecasting Agents
Nechepurenko, Maksym
Shuvalov, Pavel
Multiagent Systems
Machine Learning
General Finance
62F03, 62P05, 91B26, 68T07
I.2.6; I.2.11; H.4.2; G.3; J.4
Evaluating the true forecasting ability of AI agents requires environments that are resistant to environments resistant to overfitting, free from centralized trust, and grounded in incentive-compatible scoring. Existing benchmarks either rely on static datasets vulnerable to training-data contamination, or measure trading PnL -- a metric conflating predictive accuracy with timing, sizing, and risk appetite. We introduce Foresight Arena, the first permissionless, on-chain benchmark for evaluating AI forecasting agents on real-world prediction markets. Agents submit probabilistic forecasts on binary Polymarket markets via a commit-reveal protocol enforced by Solidity smart contracts on Polygon PoS; outcomes are resolved trustlessly through the Gnosis Conditional Token Framework. Performance is measured by the Brier Score and a novel Alpha Score -- proper scoring rules that incentivize honest probability reporting and isolate predictive edge over market consensus. We provide a formal analysis: closed-form variance for per-market Alpha, the connection to Murphy's classical Brier decomposition, and a power analysis characterizing the number of rounds required to reliably distinguish agents of different skill levels. We show that detecting a true edge of $α^* = 0.02$ at 80% power requires approximately 350 resolved binary predictions (50 rounds of 7 markets), while $α^* = 0.01$ requires four times more. We complement these analytical results with a deterministic, seed-controlled simulation study calibrated to literature-reported Brier-score ranges, illustrating how Murphy decomposition distinguishes well-calibrated agents from market-tracking agents that fail through reduced resolution. Live results from the deployed benchmark will be reported in a future revision. All smart contracts and evaluation infrastructure are open-source.
title Foresight Arena: An On-Chain Benchmark for Evaluating AI Forecasting Agents
topic Multiagent Systems
Machine Learning
General Finance
62F03, 62P05, 91B26, 68T07
I.2.6; I.2.11; H.4.2; G.3; J.4
url https://arxiv.org/abs/2605.00420