Search arXiv⌕ Search
Home/Archive/arXiv

arXiv · 2605.00420

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

Maksym Nechepurenko·Pavel Shuvalov
View original source ↗Read source document ↗Export metadata ↓

Abstract

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.

Explore related subjects

cs.MAcs.LGq-fin.GN

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Maksym Nechepurenko, Pavel Shuvalov. 2026-05-04. Foresight Arena: An On-Chain Benchmark for Evaluating AI Forecasting Agents. https://arxiv.org/abs/2605.00420

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

Highway Congestion Reduction through Reinforcement Learning Based Eulerian Headway Control

Connected automated vehicles (CAVs) equipped with adaptive cruise control (ACC) create new opportunities for highway congestion mitigation. Traditional practice relies on Eulerian variable speed limits (VSL) which regulate traffic through roadside signs, but suffer from infrequent updates and limited driver compliance. Recent research explored Lagrangian strategies that directly control individual vehicles, offering high reactivity and compliance, yet in realistic multi-lane settings they depend on drivers' latent lane-change intentions, making robust vehicle-level decisions difficult. Hence, we propose an Eulerian control system optimized through reinforcement learning, that (i) leverages ACC for reactivity and compliance, and (ii) obviates dependence on latent driver intentions by regulating aggregate density near bottlenecks, crucially via headway commands rather than speed commands. We evaluate two variants of our system, time-headway and distance-headway control, in large-scale simulations across a range of traffic conditions. Both variants outperform baselines, improving traffic flow by up to 10.6% over human traffic and 6.7% over traditional VSL. To strengthen evaluation, we propose a novel boundary-aware speed metric addressing a recognized flaw in simulation studies with dynamic vehicle entry and exit. The empirical results, together with our emphasis on deployable system design, suggest a path towards practical, safe, and scalable highway congestion mitigation.

cs.MA↗
arXiv2026

The Bystander Effect in Multi-Agent Reasoning: Quantifying Cognitive Loafing in Collaborative Interactions

Multi-agent systems (MAS) assume that collaborating inherently improves Large Language Model (LLM) reasoning. We challenge this by demonstrating that simulated social pressure triggers an algorithmic ``Bystander Effect,'' inducing severe cognitive loafing. By evaluating 22,500 deterministic trajectories across 3 dataset contexts (GAIA, SWE-bench, Multi-Challenge) with 3 state-of-the-art (SOTA) models, we semantically audit internal reasoning traces against external outputs. We formalize the \textit{Interaction Depth Limit} ($D_L$), the exact plurality threshold where an agent's logical sovereignty collapses into social compliance. Crucially, we uncover the \textit{Sovereignty Gap}: models frequently compute the correct derivation internally but suffer ``Alignment Hallucinations'' -- actively subjugating empirical evidence to sycophantically appease a simulated swarm. We prove that multi-agent social load is strictly non-commutative; the "brand" identity of the ``Lead Anchor'' auditor disproportionately dictates the swarm's integrity. These findings expose architectural vulnerabilities, proving that unstructured multi-agent topologies can degrade independent reasoning.

cs.MA↗
arXiv2026

CONCAT: Consensus- and Confidence-Driven Ad Hoc Teaming for Efficient LLM-Based Multi-Agent Systems

Although large language model (LLM) based multi-agent systems (MAS) show their capability to solve complex tasks and achieve higher performance over single agent systems, they lead to huge computational overheads because of heavy communication between agents. Previous research has made efforts to train a sparse multi-agent graph or fine-tune a planner to orchestrate the workflow better. However, such extra training processes introduce computational costs and limit MAS to specific domains, therefore compromising their generalizability. In this paper, we propose CONCAT, a training-free multi-agent collaboration framework based on CONsensus and Confidence-driven Ad hoc Teaming to efficiently organize agent interactions. Specifically, agents are clustered based on their initial answers, and leaders of each cluster are selected based on the agents' confidence. Then, a heuristic function based on the Theory of Mind is designed to predict the collaboration benefits between every two leaders according to their answers and confidence. Finally, an ad hoc multi-agent network is organized after evicting a percentage of communications based on the predicted benefits. Experiments across three LLMs and three benchmarks show that CONCAT achieves up to 2.02x higher efficiency (accuracy/latency ratio) than LLM-Debate and outperforms training-aware methods such as AgentDropout, while reducing average latency by 50.1% on Qwen2.5-14B-Instruct, without any task-specific training.

cs.MA↗