paper-with-me

홈 › Papers

Accelerating Training Speed of Tiny Recursive Models with Curriculum Guided Adaptive Recursion

2025-11-11 · Kaleem Ullah Qasim, Jiashu Zhang arxiv

Background: Recursive reasoning models achieve strong performance through iterative refinement, allowing small networks to match large language models. However, training is computationally expensive, often requiring 36 GPU-hours for Sudoku extreme. Existing models use fixed recursion depth and uniform supervision weighting, leading to inefficient training. Objectives: We propose CGAR (Curriculum-Guided Adaptive Recursion), applying curriculum learning to architectural depth. CGAR introduces Progressive Depth Curriculum (PDC) to dynamically adjust recursion depth and Hierarchical Supervision Weighting (HSW) to apply exponentially decaying importance to supervision steps. Methods: PDC implements a three-stage schedule transitioning from shallow (2, 1) to full depth (6, 3) configurations, providing 41.4% FLOPs reduction. HSW applies exponential decay to supervision steps, achieving 40% gradient variance reduction and accelerated convergence. Results: On Sudoku-Extreme, CGAR achieves 1.71x training speedup (10.93 to 6.38 hours) with only a 0.63% accuracy drop (86.65% to 86.02%). PDC alone achieves 2.26x speedup with 85.47% accuracy, showing a Pareto improvement in efficiency and quality. HSW provides 1.61x speedup. CGAR-trained models show superior inference efficiency with 100% halting accuracy and 11% fewer reasoning steps. Conclusions: CGAR enables efficient training of recursive models on modest hardware. By treating depth as a scheduled parameter, it achieves substantial savings and prevents overfitting, making these models practical for neurosymbolic AI and program synthesis. https://github.com/Kaleemullahqasim/CGAR and huggingface.co/Kaleemullah/trm-cgar-sudoku.

📄 PDF Abstract BibTeX arXiv:2511.08653

Code (0)

등록된 구현이 없습니다.

Tasks

Program Synthesis

Similar Papers 제목 키워드 기반

SPEED-RL: Faster Training of Reasoning Models via Online Curriculum Learning

2025-06-10 · Ruiqi Zhang, Daman Arora, Song Mei, Andrea Zanette

Training large language models with reinforcement learning (RL) against verifiable rewards significantly enhances their reasoning abilities, yet remains computationally expensive due to inefficient uniform prompt samplin…

Reinforcement Learning (RL)

Proximal Curriculum with Task Correlations for Deep Reinforcement Learning

2024-05-03 · Georgios Tzannetos, Parameswaran Kamalaruban, Adish Singla

Curriculum design for reinforcement learning (RL) can speed up an agent's learning process and help it learn to perform well on complex tasks. However, existing techniques typically require domain-specific hyperparameter…

Deep Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Test-time Adaptation of Tiny Recursive Models

2025-11-04 · Ronan Killian McGovern arxiv

Prior to the close of the 2025 ARC Prize competition, the leading open source approach - known as TRM, or Tiny Recursive Models - involved training a 7M parameter recursive neural network on augmented variants of ARC tas…

Test-time Adaptation

Tiny-TSM: Efficiently Training a Lightweight SOTA Time Series Foundation Model

2025-11-24 · Felix Birkel arxiv

We present Tiny-TSM, a time series foundation model characterized by small scale, economical training, and state-of-the-art performance. It comprises 23M total parameters, trained on a single A100 GPU in less than a week…

Neural Architecture SearchSynthetic Data GenerationData Augmentation

Accelerating Reinforcement Learning for Reaching using Continuous Curriculum Learning

2020-02-07 · Sha Luo, Hamidreza Kasaei, Lambert Schomaker

Reinforcement learning has shown great promise in the training of robot behavior due to the sequential decision making characteristics. However, the required enormous amount of interactive and informative training data p…

Decision Makingreinforcement-learningReinforcement LearningReinforcement Learning (RL)+1