# MAGNET: Autonomous Expert Model Generation via Decentralized Autoresearch and BitNet Training

arXiv: https://arxiv.org/abs/2603.25813 · HTML: https://mlsanity.com/paper/2603.25813/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 25 references that are in the map.
- First posted on arXiv 26 Mar 2026.

## Builds on (most cited first, 12 of 12)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [ORPO: Monolithic Preference Optimization without Reference Model](https://mlsanity.com/paper/2403.07691/) (2024)
- [The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits](https://mlsanity.com/paper/2402.17764/) (2024)
- [BitNet: Scaling 1-bit Transformers for Large Language Models](https://mlsanity.com/paper/2310.11453/) (2023)
- [DiLoCo: Distributed Low-Communication Training of Language Models](https://mlsanity.com/paper/2311.08105/) (2023)
- [Bitnet.cpp: Efficient Edge Inference for Ternary LLMs](https://mlsanity.com/paper/2502.11880/) (2025)
- [Spectra: Surprising Effectiveness of Pretraining Ternary Language Models at Scale](https://mlsanity.com/paper/2407.12327/) (2024)
- [A Vision for Auto Research with LLM Agents](https://mlsanity.com/paper/2504.18765/) (2025)
- [BitTensor: A Peer-to-Peer Intelligence Market](https://mlsanity.com/paper/2003.03917/) (2020)
- [Incentivizing Permissionless Distributed Learning of LLMs](https://mlsanity.com/paper/2505.21684/) (2025)
- [What happens when nanochat meets DiLoCo?](https://mlsanity.com/paper/2511.13761/) (2025)

## Abstract (arXiv)

We present MAGNET (Model Autonomously Growing Network), a decentralized system for autonomous generation, training, and serving of domain-expert language models across commodity hardware. MAGNET integrates four components: (1) autoresearch, an autonomous ML research pipeline that automates dataset generation, hyperparameter exploration, evaluation, and error-driven iteration; (2) BitNet b1.58 ternary training, enabling CPU-native inference via bitnet.cpp without GPU hardware; (3) DiLoCo-based distributed merging for communication-efficient aggregation of domain specialists; and (4) on-chain contribution tracking on the HOOTi EVM chain. We validate autoresearch through three case studies: video safety classification (balanced accuracy 0.9287 to 0.9851), cryptocurrency directional prediction (41% to 54.9% hit rate), and BitNet hyperparameter optimization (10-phase sweep, -16.7% validation loss).