What Limits Recursive Reasoning Models: Optimization, Architecture and Test-Time Scaling
cs.LG, cs.AI
Submitted: 2026-09-30
Updated: 2026-09-30
Terminology
Sources
- Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computation
- On the Measure of Intelligence
- ARC-AGI-2: A New Challenge for Frontier AI Reasoning Systems
- Looped Transformers for Length Generalization
- Universal Reasoning Model
- Hierarchical Reasoning Models: Perspectives and Misconceptions
- Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach
- Less is More: Recursive Reasoning with Tiny Networks
- The ConceptARC Benchmark: Evaluating Understanding and Generalization in the ARC Domain
- Fixed-Point Reasoners: Stable and Adaptive Deep Looped Transformers
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks