What Makes Recurrence Effective in Looped Language Models?
cs.LG, cs.CL
Submitted: 2026-09-29
Updated: 2026-09-29
Terminology
Sources
- A Mechanistic Analysis of Looped Reasoning Language Models
- Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
- LT2: Linear-Time Looped Transformers
- Solve the Loop: Attractor Models for Language and Reasoning
- The Llama 3 Herd of Models
- Ouroboros: Dynamic Weight Generation for Recursive Transformers via Input-Conditioned LoRA Modulation
- Encode, Think, Decode: Scaling test-time reasoning with recursive latent thoughts
- Sparse Layers are Critical to Scaling Looped Language Models
- DeepLoop: Depth Scaling for Looped Transformers
- Muon is Scalable for LLM Training
- Per-Token Fixed-Point Convergence in Depth-Recurrent Transformers
- Teaching Pretrained Language Models to Think Deeper with Retrofitted Recurrence
- Fixed-Point Reasoners: Stable and Adaptive Deep Looped Transformers
- Adaptive Depth in Looped Transformers: Diagnosing Learned Halting Gates and Trajectory Readouts
- Parcae: Scaling Laws For Stable Looped Language Models
- How Much Is One Recurrence Worth? Iso-Depth Scaling Laws for Looped Language Models
- Retrofitting Recurrent Depth into a Pretrained Language Model: Installation, Extrapolation, Transfer, and Retention at Two Parameter Budgets
- Universal YOCO for Efficient Depth Scaling
- On the Residual Scaling of Looped Transformers: Stability and Transferability
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: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks