Fortytwo: Swarm Inference with Peer-Ranked Consensus
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.
Code (0)
등록된 구현이 없습니다.
Results from the Paper
| Rank | Task | Dataset | Model | Metrics |
|---|---|---|---|---|
| GPQA | Fortytwo | Accuracy: 85.90 |
Similar Papers 제목 키워드 기반
DANCeRS: A Distributed Algorithm for Negotiating Consensus in Robot Swarms with Gaussian Belief Propagation
Robot swarms require cohesive collective behaviour to address diverse challenges, including shape formation and decision-making. Existing approaches often treat consensus in discrete and continuous decision spaces as dis…
Collision AvoidanceSwarm Oracle: Trustless Blockchain Agreements through Robot Swarms
Blockchain consensus, rooted in the principle ``don't trust, verify'', limits access to real-world data, which may be ambiguous or inaccessible to some participants. Oracles address this limitation by supplying data to b…
MusicSwarm: Biologically Inspired Intelligence for Music Composition
We show that coherent, long-form musical composition can emerge from a decentralized swarm of identical, frozen foundation models that coordinate via stigmergic, peer-to-peer signals, without any weight updates. We compa…
Proof of Swarm Based Ensemble Learning for Federated Learning Applications
Ensemble learning combines results from multiple machine learning models in order to provide a better and optimised predictive model with reduced bias, variance and improved predictions. However, in federated learning it…
ECG ClassificationEnsemble LearningFederated LearningDecentralized Multi-Agent Swarms for Autonomous Grid Security in Industrial IoT: A Consensus-based Approach
As Industrial Internet of Things (IIoT) environments expand to include tens of thousands of connected devices. The centralization of security monitoring architectures creates serious latency issues that savvy attackers c…