# Fortytwo: Swarm Inference with Peer-Ranked Consensus

arXiv: https://arxiv.org/abs/2510.24801 · HTML: https://mlsanity.com/paper/2510.24801/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 44 references that are in the map.
- First posted on arXiv 27 Oct 2025.

## Builds on (most cited first, 23 of 23)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [GPQA: A Graduate-Level Google-Proof Q&A Benchmark](https://mlsanity.com/paper/2311.12022/) (2023)
- [LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code](https://mlsanity.com/paper/2403.07974/) (2024)
- [Language Models (Mostly) Know What They Know](https://mlsanity.com/paper/2207.05221/) (2022)
- [Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference](https://mlsanity.com/paper/2403.04132/) (2024)
- [Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve](https://mlsanity.com/paper/2403.02310/) (2024)
- [Humanity's Last Exam](https://mlsanity.com/paper/2501.14249/) (2025)
- [Improving Federated Learning Personalization via Model Agnostic Meta Learning](https://mlsanity.com/paper/1909.12488/) (2019)
- [Scaling provable adversarial defenses](https://mlsanity.com/paper/1805.12514/) (2018)
- [Rethinking Bradley-Terry Models in Preference-Based Reward Modeling: Foundations, Theory, and Alternatives](https://mlsanity.com/paper/2411.04991/) (2024)
- [Scaling up Trustless DNN Inference with Zero-Knowledge Proofs](https://mlsanity.com/paper/2210.08674/) (2022)
- [opML: Optimistic Machine Learning on Blockchain](https://mlsanity.com/paper/2401.17555/) (2024)
- [zkDL: Efficient Zero-Knowledge Proofs of Deep Learning Training](https://mlsanity.com/paper/2307.16273/) (2023)
- [Deep Neural Networks for Encrypted Inference with TFHE](https://mlsanity.com/paper/2302.10906/) (2023)
- [Enabling Weak LLMs to Judge Response Reliability via Meta Ranking](https://mlsanity.com/paper/2402.12146/) (2024)
- [Proof of Quality: A Costless Paradigm for Trustless Generative AI Model Inference on Blockchains](https://mlsanity.com/paper/2405.17934/) (2024)
- [Scalable and Probabilistic Leaderless BFT Consensus through Metastability](https://mlsanity.com/paper/1906.08936/) (2019)
- [AI-Based Crypto Tokens: The Illusion of Decentralized AI?](https://mlsanity.com/paper/2505.07828/) (2025)
- [Self-Supervised Inference of Agents in Trustless Environments](https://mlsanity.com/paper/2409.08386/) (2024)
- [Proof of Useful Intelligence (PoUI): Blockchain Consensus Beyond Energy Waste](https://mlsanity.com/paper/2504.17539/) (2025)

## Abstract (arXiv)

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.