---
license: apache-2.0
pipeline_tag: other
---

# Equilibrium Reasoners: Learning Attractors Enables Scalable Reasoning

This repository contains the models presented in the paper [Equilibrium Reasoners: Learning Attractors Enables Scalable Reasoning](https://huggingface.co/papers/2605.21488).

- **Code:** [GitHub Repository](https://github.com/locuslab/eqr)
- **Project Page:** [X/Twitter Thread](https://x.com/huskydogewoof/status/2057641657580064941?s=20)

Equilibrium Reasoners (EqR) enable test-time scaling without external verifiers or task-specific priors by learning task-conditioned attractors. This approach allows neural networks to adaptively allocate test-time compute based on task difficulty by scaling internal dynamics along two axes: depth (iterations) and breadth (stochastic trajectories).

## Citation

```bibtex
@article{huang2026equilibrium,
  title={Equilibrium Reasoners: Learning Attractors Enables Scalable Reasoning},
  author={Huang, Benhao and Geng, Zhengyang and Kolter, Zico},
  journal={arXiv preprint arXiv:2605.21488},
  year={2026}
}
```