Fortytwo: Swarm Inference with Peer-Ranked Consensus

TL;DR

Fortytwo introduces a decentralized swarm inference protocol that uses peer-ranked consensus and reputation systems to improve AI inference accuracy, resilience, and scalability without centralized control.

Contribution

The paper presents Fortytwo, a novel decentralized inference protocol leveraging swarm intelligence, peer-ranked consensus, and reputation mechanisms to outperform traditional voting methods and resist attacks.

Findings

Achieves 85.90% accuracy on GPQA Diamond, outperforming majority voting.

Demonstrates robustness against adversarial prompts with minimal accuracy degradation.

Provides a scalable, secure, and open framework for decentralized AI inference.

Abstract

As centralized AI hits compute ceilings and diminishing returns from ever-larger training runs, meeting demand requires an inference layer that scales horizontally in both capacity and capability. We present Fortytwo, a novel protocol that leverages swarm intelligence principles and distributed pairwise ranking consensus to achieve superior performance in AI inference. Our approach reimagines collaboration among AI nodes using swarm inference: a peer-ranked, reputation-weighted consensus across heterogeneous models that surfaces the highest-quality responses. Using pairwise ranking with a custom Bradley-Terry-style aggregation model, we demonstrate that swarm inference substantially outperforms majority voting, achieving 85.90% on GPQA Diamond versus 68.69% for majority voting with the same model set - an improvement of +17.21 percentage points (approximately +25.1% relative). The protocol incorporates on-chain reputation so node influence adapts to demonstrated accuracy over time, yielding a meritocratic consensus that filters low-quality or malicious participants. To resist Sybil attacks, Fortytwo employs proof-of-capability in its consensus: nodes must successfully complete calibration/test requests and stake reputation to enter ranking rounds, making multi-identity attacks economically unattractive while preserving openness. Across six challenging benchmarks, including GPQA Diamond, LiveCodeBench, and AIME, our evaluation indicates higher accuracy and strong resilience to adversarial and noisy free-form prompting (e.g., prompt-injection degradation of only 0.12% versus 6.20% for a monolithic single-model baseline), while retaining practical deployability. Together, these results establish a foundation for decentralized AI systems - democratizing access to high-quality inference through collective intelligence without sacrificing reliability or security.