Many inference scaling methods work by breaking a problem into smaller steps (or groups of tokens), then sampling and choosing the best next step. However, these steps and their sizes are usually predetermined based on human intuition or domain knowledge. This paper introduces dynamic decomposition, a method that automatically and adaptively splits solution and reasoning traces into steps during inference. This approach improves computational efficiency by focusing more resources on difficult steps, breaking them down further and prioritizing their sampling. Experiments on coding and math benchmarks (APPS, MATH, and LiveCodeBench) show that dynamic decomposition performs better than static methods, which rely on fixed steps like token-level, sentence-level, or single-step decompositions. These results suggest that dynamic decomposition can enhance many inference scaling techniques.
View on arXiv@article{light2025_2502.16706,
title={ DISC: Dynamic Decomposition Improves LLM Inference Scaling },
author={ Jonathan Light and Wei Cheng and Wu Yue and Masafumi Oyamada and Mengdi Wang and Santiago Paternain and Haifeng Chen },
journal={arXiv preprint arXiv:2502.16706},
year={ 2025 }
}