DISC: DISC: Dynamic Decomposition Improves LLM Inference Scaling
Inference scaling methods for large language models often work by breaking problems into steps or groups of tokens, then sampling and selecting the best next steps. However, these steps and their sizes are usually fixed or manually designed based on domain knowledge. We introduce dynamic decomposition, a method that adaptively and automatically breaks down solution and reasoning traces into manageable steps during inference. By allocating compute more effectively - especially by subdividing difficult steps and prioritizing their sampling - dynamic decomposition significantly boosts inference efficiency. Experiments on benchmarks like APPS, MATH, and LiveCodeBench show that dynamic decomposition outperforms fixed strategies such as token-level, sentence-level, and single-step decompositions, reducing the pass@10 error rate by 5.0%, 6.7%, and 10.5% respectively. These results show the promise of dynamic decomposition for improving a broad range of inference scaling techniques.
Code (0)
등록된 구현이 없습니다.
Tasks
Computational EfficiencyMathSentenceSimilar Papers 제목 키워드 기반
Stochastic Nonparametric Event-Tensor Decomposition
Tensor decompositions are fundamental tools for multiway data analysis. Existing approaches, however, ignore the valuable temporal information along with data, or simply discretize them into time steps so that important …
Tensor DecompositionDynamics-Aligned Shared Hypernetworks for Contextual RL under Discontinuous Shifts
Zero-shot generalization in contextual reinforcement learning remains a core challenge, particularly when the context is latent and must be inferred from data. A canonical failure mode arises when latent context disconti…
Zero-shot GeneralizationReinforcement LearningUnsupervised Video Decomposition using Spatio-temporal Iterative Inference
Unsupervised multi-object scene decomposition is a fast-emerging problem in representation learning. Despite significant progress in static scenes, such models are unable to leverage important dynamic cues present in vid…
ObjectRepresentation LearningDCD: Decomposition-based Causal Discovery from Autocorrelated and Non-Stationary Temporal Data
Multivariate time series in domains such as finance, climate science, and healthcare often exhibit long-term trends, seasonal patterns, and short-term fluctuations, complicating causal inference under non-stationarity an…
Causal InferenceOn Dynamic Programming Decompositions of Static Risk Measures in Markov Decision Processes
Optimizing static risk-averse objectives in Markov decision processes is difficult because they do not admit standard dynamic programming equations common in Reinforcement Learning (RL) algorithms. Dynamic programming de…
Reinforcement Learning (RL)