paper-with-me

홈 › Papers

Complexity Agnostic Recursive Decomposition of Thoughts

2025-12-10 · Kaleem Ullah Qasim, Jiashu Zhang, Hafiz Saif Ur Rehman arxiv

Large language models often fail on multi-step reasoning due to fixed reasoning strategies that ignore problem specific difficulty. We introduce CARD (Complexity Agnostic Recursive Decomposition), a framework that predicts problem complexity before generation and adapts decomposition accordingly. Our system comprises MRCE (Multi-dimensional Reasoning Complexity Estimator), a 0.6B Qwen model predicting 30 fine-grained features from question text and a two-stage recursive solver: (1) hierarchical decomposition into K steps based on task profile and (2) per-step thought budget allocation (1, 5-9, or 10 thoughts) via recursive MRCE profiling. Evaluated on three reasoning models (Qwen3-0.6B, DeepSeek-R1-Distill-Qwen-1.5B, Qwen3-1.7B), CARD achieves 81.4% to 89.2% accuracy on GSM8K while reducing token cost by 1.88x to 2.40x compared to fixed decomposition baselines. On MATH-500, CARD reaches 75.1 to 86.8% accuracy using 1.71x to 5.74x fewer tokens. Our results demonstrate that preemptive complexity estimation enables both higher accuracy and significant efficiency gains.

📄 PDF Abstract BibTeX arXiv:2601.04210

Code (0)

등록된 구현이 없습니다.

Results from the Paper

RankTaskDatasetModelMetrics
#28 GSM8K GSM8K CARD Accuracy: 89.2

Similar Papers 제목 키워드 기반

Recursive Decomposition of Logical Thoughts: Framework for Superior Reasoning and Knowledge Propagation in Large Language Models

2025-01-03 · Kaleem Ullah Qasim, Jiashu Zhang, Tariq Alsahfi, Ateeq Ur Rehman Butt

Enhancing the reasoning capabilities of Large Language Models remains a critical challenge in artificial intelligence. We introduce RDoLT, Recursive Decomposition of Logical Thought prompting, a novel framework that sign…

GSM8KMathPrompt Engineering

Shapley Sets: Feature Attribution via Recursive Function Decomposition

2023-07-04 · Torty Sivill, Peter Flach

Despite their ubiquitous use, Shapley value feature attributions can be misleading due to feature interaction in both model and data. We propose an alternative attribution approach, Shapley Sets, which awards value to se…

Fairness

OptiTree: Hierarchical Thoughts Generation with Tree Search for LLM Optimization Modeling

2025-10-25 · Haoyang Liu, Jie Wang, Yuyang Cai, Xiongwei Han 외 arxiv

Optimization modeling is one of the most crucial but technical parts of operations research (OR). To automate the modeling process, existing works have leveraged large language models (LLMs), prompting them to break down…

PENCIL: Long Thoughts with Short Memory

2025-03-18 · Chenxiao Yang, Nathan Srebro, David Mcallester, Zhiyuan Li

While recent works (e.g. o1, DeepSeek R1) have demonstrated great promise of using long Chain-of-Thought (CoT) to improve reasoning capabilities of language models, scaling it up during test-time is challenging due to in…

PartNet: A Recursive Part Decomposition Network for Fine-grained and Hierarchical Shape Segmentation

2019-03-02 · CVPR 2019 6 · Fenggen Yu, Kun Liu, Yan Zhang, Chenyang Zhu 외

Deep learning approaches to 3D shape segmentation are typically formulated as a multi-class labeling problem. Existing models are trained for a fixed set of labels, which greatly limits their flexibility and adaptivity. …

3D Instance Segmentation3D Part SegmentationSegmentationSemantic Segmentation