Recurrent Self-Improvement: Dynamic Cross-Loop On-Policy Distillation for Looped Language Models
cs.LG, cs.CL
Submitted: 2026-10-07
Updated: 2026-10-07
Comments: 28 pages, 8 figures. Submitted to ICLR 2027
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Program Synthesis with Large Language Models
- The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- LoopRPT: Reinforcement Pre-Training for Looped Language Models
- Qwen3 Technical Report
- Scaling Latent Reasoning via Looped Language Models
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