About this paper
Energy-Based Reasoners guide looped latent reasoning by learning an energy function whose gradient refines states and signals when to stop, with exploration-based training improving performance and efficiency.
Looping is a powerful inductive bias for reasoning. By repeatedly iterating a recurrent block, looped models can scale their effective depth and enable multi-step reasoning in latent space. However, existing looped models are not inherently guided by an explicit measure of progress, making it difficult to determine when to stop looping and how to improve upon the current state. To enable this, we introduce Energy-Based Reasoners (EBRs), which learn an energy function over latent reasoning states and formulate looped updates as gradient descent on this energy. The energy scores latent states, while its gradient guides refinement and provides a signal for stopping. To train EBRs effectively,…
inductive biasrecurrent blocklooped modelseffective depthmulti-step reasoninglatent spaceenergy functionlatent reasoning statesgradient descentEnergy-Based Reasoners
- Upvotes
- 3
- Authors
- 5
- Published
- Nov 6, 2026
Summary and abstract excerpt via Hugging Face Papers ↗ · arXiv.
Trending history
Energy-Based Reasoners: Your Recurrent Reasoner Should Be an Energy-Based Model was first seen on Hugging Face · Daily papers on Nov 17, 2026. Since then it has appeared in 14 checks on 3 different days. Its best position was #17 of 30, reached on Nov 18, 01:28 UTC. It dropped off the list after Nov 19, 01:28 UTC.