Recursive Reasoning Models

Latest papers

13 papers3 papers in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

Energy-Based Reasoners: Your Recurrent Reasoner Should Be an Energy-Based Model
Nov 6, 2026William Xingxu Chen, Alexi Gladstone, Zeyu Michael Li +2Recursive Reasoning Models Efficient Language Model Reasoning
Duke University · UIUC · Harvard University
Nested Shared-Operator Recursion on ARC-AGI-1: An Empirical Study of HRM, TRM and URM
Oct 19, 2026Sara Neri, Eugenio Gaeta, Andrea Ceschini +2Recursive Reasoning Models Abstract Reasoning
University of Padova Padova, Italy · Universidad Politécnica de Madrid Madrid, Spain · Escuela Técnica Superior de Ingenieros de Telecomunicación Universidad Politécnica de Madrid Av. Complutense, 30 28040 Madrid, Spain +2
Resample the Answer: Where to Spend Test-Time Compute in Recursive Reasoning
Oct 12, 2026Maxime IllouzRecursive Reasoning Models Inference-Time Search
Concordia University Mila – Québec AI Institute Montréal, Canada
Pretraining and Test-Time Training Budgets Matter for ARC: A Controlled Study of VARC and TRM
Oct 9, 2026Adrien Deliege, Marc Van DroogenbroeckRecursive Reasoning Models Abstract Reasoning
Montefiore Institute of Electrical Engineering and Computer Science, University of Liège, Liège, Belgium
What Limits Recursive Reasoning Models: Optimization, Architecture and Test-Time Scaling
Sep 30, 2026Yuliana Shakhvalieva, Dmitrii Kharchev, Viacheslav Bezrukov +4Recursive Reasoning Models Neural Algorithmic Reasoning
RND NLP, DAIMLD, Russian Federation
Energy-guided Recursive Model
Jul 11, 2026Yifei Zhao, Ying TangLanguage Modeling Recursive Language Models
Institute of Fundamental and Frontier Sciences, University of Electronic Science and Technology of China, Chengdu 611731, China · School of Physics, University of Electronic Science and Technology of China, Chengdu 611731, China
What Survives When You Compress a Recursive Reasoner for the Edge?
Jun 25, 2026Pearse Jim, Steven Kolawole, Opegbemi Matthias Busoye +2Model Compression Efficient Neural Network Inference
ML Collective · Carnegie Mellon University
Boosting Inference with Guided Reasoning: Stochastic Exploration for Recursive Models
May 24, 2026Andrew Corbett, Archit Sood, Anna Tzatzopoulou +2Inference-Time Search Recursive Reasoning Models
digiLab, UK · University of Bristol, UK
Interaction Locality in Hierarchical Recursive Reasoning
May 20, 2026Yosuke Miyanishi, Tetsuro MorimuraRecursive Reasoning Models Spatial Reasoning
CyberAgent Inc.
Probabilistic Tiny Recursive Model
May 19, 2026Amin Sghaier, Ali Parviz, Alexia Jolicoeur-MartineauRecursive Reasoning Models Test-Time Scaling
Mila – Quebec AI Institute ILLS & ETS Montreal · Independent
Generative Recursive Reasoning
May 19, 2026Junyeob Baek, Mingyu Jo, Minsu Kim +3Latent Variable Models Recursive Reasoning Models
KAIST · Mila – Québec AI Institute · New York University +1
Form Follows Function: Recursive Stem Model
Mar 3, 2026Navid HakimiRecursive Reasoning Models Neural Algorithmic Reasoning
Recursive Models for Long-Horizon Reasoning
Mar 2, 2026Chenxiao Yang, Nathan Srebro, Zhiyuan LiRecursive Language Models Language Modeling
Toyota Technological Institute at Chicago

Nov 6, 2026J/K move · Enter open · S save

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

William Xingxu Chen, Alexi Gladstone, Zeyu Michael Li, Heng Ji+1

Duke University · UIUC · Harvard University

Recursive Reasoning Models Efficient Language Model Reasoning Energy-Based Models Algorithmic Reasoning Continuous Latent Reasoning

Open paper AskPDF arXiv

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, we further introduce exploration-based training to discover additional modes and to better shape the energy landscape over a broader set of states. Across four algorithmic reasoning benchmarks, EBRs match or outperform prior recurrent reasoning models, achieving 99.9% accuracy on Sudoku-Extreme while using 345

\times

less inference compute than the next-best model and maintaining comparable training compute. On all multi-solution benchmarks, EBRs achieve state-of-the-art coverage of distinct valid solutions while maintaining near-100% single-sample accuracy. These results suggest that energy-based models are a promising approach for strong reasoning performance.