Energy-Based Reasoners: Your Recurrent Reasoner Should Be an Energy-Based Model
cs.LG
Submitted: 2026-11-06
Updated: 2026-11-06
Code: https://github.com/wwillchen/ebr
Terminology
Sources
- On the Measure of Intelligence
- Reasoning with Latent Thoughts: On the Power of Looped Transformers
- Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters
- Training Large Language Models to Reason in a Continuous Latent Space
- Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach
- Universal Transformers
- Hierarchical Reasoning Model
- Less is More: Recursive Reasoning with Tiny Networks
- Universal Reasoning Model
- Training Verifiers to Solve Math Word Problems
- Probabilistic Tiny Recursive Model
- Fixed-Point Reasoners: Stable and Adaptive Deep Looped Transformers
- Equilibrium Reasoners: Learning Attractors Enables Scalable Reasoning
- Generative Recursive Reasoning
- Learning Iterative Reasoning through Energy Diffusion
- Energy-Based Transformers are Scalable Learners and Thinkers
- Flow Reasoning Models: Turning Flows Into Efficient Recurrent Reasoners
- Thinking with Looped Flows
- Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation
- Are Your Reasoning Models Reasoning or Guessing? A Mechanistic Analysis of Hierarchical Reasoning Models
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis