Energy-guided Recursive Model Sets New Benchmarks on Structured Reasoning Tasks

Jul 14, 2026

A new preprint introduces the Energy-guided Recursive Model (ERM), which applies Hopfield energy functions to select among candidate solutions during recursive reasoning. ERM achieves state-of-the-art accuracy on structured tasks, including 98.97% on Sudoku, 88.04% on PPBench, and 99.30% on Maze, outperforming previous models. The method provides a principled inference mechanism without relying on additional q-heads or heuristic voting.

Why it matters: This work demonstrates a novel, principled approach to inference in recursive reasoning models, potentially advancing performance on complex structured problems.

Full story at: arXiv Machine Learning ↗