# CRISP: Complex Reasoning with Interpretable Step-based Plans

Authors: Matan Vetzler, Koren Lazar, Guy Uziel, Eran Hirsch, Ateret Anaby-Tavor, Leshem Choshen
Venue: arXiv preprint arXiv:2507.08037 (2025)

## Abstract
Recent advancements in large language models (LLMs) underscore the need for stronger reasoning capabilities to solve complex problems effectively. While Chain-of-Thought (CoT) reasoning has been a step forward, it remains insufficient for many domains. A promising alternative is explicit high-level plan generation, but existing approaches largely assume that LLMs can produce effective plans through few-shot prompting alone, without additional training. In this work, we challenge this assumption and introduce CRISP (Complex Reasoning with Interpretable Step-based Plans), a multi-domain dataset of high-level plans for mathematical reasoning and code generation. The plans in CRISP are automatically generated and rigorously validated--both intrinsically, using an LLM as a judge, and extrinsically, by evaluating their impact on downstream task performance. We demonstrate that fine-tuning a small model on CRISP enables it to generate higher-quality plans than much larger models using few-shot prompting, while significantly outperforming Chain-of-Thought reasoning. Furthermore, our out-of-domain evaluation reveals that fine-tuning on one domain improves plan generation in the other, highlighting the generalizability of learned planning capabilities.

## Links
- arXiv: https://arxiv.org/abs/2507.08037
- PDF: https://arxiv.org/pdf/2507.08037
- HTML: https://arxiv.org/html/2507.08037
- Hugging Face: https://huggingface.co/papers/2507.08037
- alphaXiv: https://www.alphaxiv.org/abs/2507.08037
- DOI: https://doi.org/10.48550/arXiv.2507.08037
- Semantic Scholar: https://www.semanticscholar.org/paper/280252187

## How to cite
@article{vetzler2025crisp,
title={CRISP: Complex Reasoning with Interpretable Step-based Plans},
  author={Vetzler, Matan and Lazar, Koren and Uziel, Guy and Hirsch, Eran and Anaby-Tavor, Ateret and Choshen, Leshem},
  journal={arXiv preprint arXiv:2507.08037},
  year={2025}
}