LGAICLNov 1, 2025

Reasoning Planning for Language Models

arXiv:2511.00521v22 citationsh-index: 6Has Code
Originality Highly original
AI Analysis

This work addresses a key bottleneck in language model generation for tasks like mathematical reasoning, offering a more efficient and accurate method selection approach.

The paper tackles the challenge of selecting appropriate reasoning methods for language models by introducing EPIC, an Ensemble Planning with Contrastive learning framework, which improves accuracy and reduces computational overhead on mathematical reasoning tasks.

Selecting an appropriate reasoning method for a given query remains a key challenge in language model generation. Existing approaches typically generate multiple candidate responses and use an aggregation strategy to select the output answer, often assuming that more candidate answers yield higher accuracy. We revisit this assumption through a rigorous theoretical analysis, deriving accuracy bounds for standard aggregation methods under fixed generation distributions and candidate sizes. Building on these insights, we introduce EPIC, an Ensemble Planning with Contrastive learning framework to learn a shared representation space that captures both model reasoning abilities and query-method compatibility. EPIC incorporates our probability bounds as a regularizer in a utility-driven optimization that balances accuracy and computational cost. Experiments on diverse mathematical reasoning tasks show that EPIC consistently selects optimal reasoning methods, improving accuracy while reducing computational overhead. Our code can be found at https://github.com/nguyenngocbaocmt02/EPIC.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes