Energy-Based Reasoners: Your Recurrent Reasoner Should Be an Energy-Based Model

William Chen1, Alexi Gladstone2, Zeyu Li1, Heng Ji2, Yilun Du3

1Duke University2UIUC3Harvard University

TL;DR – We introduce Energy-Based Reasoners (EBRs), reasoning models that learn an energy function over latent reasoning states and formulate looped updates as gradient descent on this energy. Its value scores candidate predictions without requiring an external verifier, while its gradient guides refinement and provides a natural signal for stopping. With only 1.8M parameters, EBRs achieve 99.9% accuracy on Sudoku-Extreme while using 345× less inference compute than the next-best model. On N-Queens and Graph Coloring, EBRs achieve state-of-the-art coverage while maintaining near-100% single-sample accuracy.