Classical Energies Learn to Reason 1,000x Faster than Looped Models
cs.AI, cs.LG
Submitted: 2026-11-12
Updated: 2026-11-19
Code: https://github.com/Prefrontal-AI/CRAM
Project page: https://www.astrolog.org/labyrnth/algrithm
Terminology
Sources
- Generative Recursive Reasoning
- Energy-Based Reasoners: Your Recurrent Reasoner Should Be an Energy-Based Model
- On the Measure of Intelligence
- Reasoning with Neural Cellular Automata
- Solve the Loop: Attractor Models for Language and Reasoning
- Universal Reasoning Model
- Energy-Based Transformers are Scalable Learners and Thinkers
- Adaptive Computation Time for Recurrent Neural Networks
- Flow Reasoning Models: Turning Flows Into Efficient Recurrent Reasoners
- Equilibrium Reasoners: Learning Attractors Enables Scalable Reasoning
- Less is More: Recursive Reasoning with Tiny Networks
- Modern Methods in Associative Memory
- Fixed-Point Reasoners: Stable and Adaptive Deep Looped Transformers
- Are Your Reasoning Models Reasoning or Guessing? A Mechanistic Analysis of Hierarchical Reasoning Models
- Tiny Recursive Message Passing
- Probabilistic Tiny Recursive Model
- Thinking with Looped Flows
- Hierarchical Reasoning Model
- Self-conditioned Flow Map Language Models via Fixed-point Flows
- Energy-guided Recursive Model
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents