Jupiter: Enhancing LLM Data Analysis Capabilities via Notebook and Inference-Time Value-Guided Search

• URL: http://arxiv.org/abs/2509.09245v1
• Date: Thu, 11 Sep 2025 08:27:54 GMT
• Title: Jupiter: Enhancing LLM Data Analysis Capabilities via Notebook and Inference-Time Value-Guided Search
• Authors: Shuocheng Li, Yihao Liu, Silin Du, Wenxuan Zeng, Zhe Xu, Mengyu Zhou, Yeye He, Haoyu Dong, Shi Han, Dongmei Zhang,
• Abstract summary: We propose a scalable pipeline that extracts high-quality, tool-based data analysis tasks and their executable multi-step solutions from real-world Jupyter notebooks.<n>Using this pipeline, we introduce NbQA, a large-scale dataset of standardized task-solution pairs.<n>We also present Jupiter, a framework that formulates data analysis as a search problem and applies Monte Carlo Tree Search.
• Score: 37.53003959273494
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models (LLMs) have shown great promise in automating data science workflows, but existing models still struggle with multi-step reasoning and tool use, which limits their effectiveness on complex data analysis tasks. To address this, we propose a scalable pipeline that extracts high-quality, tool-based data analysis tasks and their executable multi-step solutions from real-world Jupyter notebooks and associated data files. Using this pipeline, we introduce NbQA, a large-scale dataset of standardized task-solution pairs that reflect authentic tool-use patterns in practical data science scenarios. To further enhance multi-step reasoning, we present Jupiter, a framework that formulates data analysis as a search problem and applies Monte Carlo Tree Search (MCTS) to generate diverse solution trajectories for value model learning. During inference, Jupiter combines the value model and node visit counts to efficiently collect executable multi-step plans with minimal search steps. Experimental results show that Qwen2.5-7B and 14B-Instruct models on NbQA solve 77.82% and 86.38% of tasks on InfiAgent-DABench, respectively-matching or surpassing GPT-4o and advanced agent frameworks. Further evaluations demonstrate improved generalization and stronger tool-use reasoning across diverse multi-step reasoning tasks.

Related papers

• ML-Tool-Bench: Tool-Augmented Planning for ML Tasks [23.54937738755734]
  We introduce a benchmark for evaluating tool-augmented machine learning agents.<n>Our benchmark goes beyond traditional tool-use evaluation by incorporating an in-memory named object management.<n>Our approach improves over ReAct by 16.52 percentile positions, taking the median across all Kaggle challenges.
  arXiv  Detail & Related papers  (2025-11-29T23:59:40Z)
• ChartM$^3$: A Multi-Stage Code-Driven Pipeline for Constructing Multi-Dimensional and Multi-Step Visual Reasoning Data in Chart Comprehension [15.798942458550515]
  This study proposes an automated multi-stage code-driven pipeline for generating visual reasoning datasets.<n>We construct ChartM$3$, a multi-dimensional and multi-step dataset containing 38K charts and 142K Q&A pairs for training, along with 2,871 high-quality evaluation samples.
  arXiv  Detail & Related papers  (2025-11-04T09:45:34Z)
• Generalizing Test-time Compute-optimal Scaling as an Optimizable Graph [42.247964605609745]
  Test-Time Scaling (TTS) improves large language models (LLMs) by allocating additional computation during inference.<n>We formalize it as a multi-LLM collaboration graph, where nodes encode roles and model assignments, edges capture information flow.<n>We propose Agent-REINFORCE, an LLM-agent-augmented framework that mirrors the REINFORCE pipeline by mapping sampling-gradient-update to sampling-feedback-update.
  arXiv  Detail & Related papers  (2025-10-29T22:14:25Z)
• InfiAlign: A Scalable and Sample-Efficient Framework for Aligning LLMs to Enhance Reasoning Capabilities [27.09178257629886]
  InfiAlign is a scalable and sample-efficient post-training framework for large language models (LLMs)<n>At the core of InfiAlign is a robust data selection pipeline that automatically curates high-quality alignment data from open-source reasoning.<n>Our results highlight the effectiveness of combining principled data selection with full-stage post-training.
  arXiv  Detail & Related papers  (2025-08-07T15:34:06Z)
• ToolVQA: A Dataset for Multi-step Reasoning VQA with External Tools [9.788417605537965]
  We introduce ToolVQA, a large-scale multimodal dataset comprising 23K instances, designed to bridge the gap in real-world tool-use proficiency.<n>ToolVQA features real-world visual contexts and challenging implicit multi-step reasoning tasks, better aligning with real user interactions.<n>To construct this dataset, we propose ToolEngine, a novel data generation pipeline that employs Depth-First Search (DFS) with a dynamic in-context example matching mechanism.
  arXiv  Detail & Related papers  (2025-08-05T10:06:16Z)
• DABstep: Data Agent Benchmark for Multi-step Reasoning [2.6709582216950767]
  DABstep is a novel benchmark for evaluating AI agents on realistic multi-step data analysis tasks.<n>It comprises over 450 real-world challenges derived from a financial analytics platform.<n>Dabstep is released with a public leaderboard and toolkit to accelerate research in autonomous data analysis.
  arXiv  Detail & Related papers  (2025-06-30T10:49:21Z)
• IDA-Bench: Evaluating LLMs on Interactive Guided Data Analysis [60.32962597618861]
  IDA-Bench is a novel benchmark evaluating large language models in multi-round interactive scenarios.<n>Agent performance is judged by comparing its final numerical output to the human-derived baseline.<n>Even state-of-the-art coding agents (like Claude-3.7-thinking) succeed on 50% of the tasks, highlighting limitations not evident in single-turn tests.
  arXiv  Detail & Related papers  (2025-05-23T09:37:52Z)
• Empowering Large Language Models in Wireless Communication: A Novel Dataset and Fine-Tuning Framework [81.29965270493238]
  We develop a specialized dataset aimed at enhancing the evaluation and fine-tuning of large language models (LLMs) for wireless communication applications.<n>The dataset includes a diverse set of multi-hop questions, including true/false and multiple-choice types, spanning varying difficulty levels from easy to hard.<n>We introduce a Pointwise V-Information (PVI) based fine-tuning method, providing a detailed theoretical analysis and justification for its use in quantifying the information content of training data.
  arXiv  Detail & Related papers  (2025-01-16T16:19:53Z)
• BabelBench: An Omni Benchmark for Code-Driven Analysis of Multimodal and Multistructured Data [61.936320820180875]
  Large language models (LLMs) have become increasingly pivotal across various domains. BabelBench is an innovative benchmark framework that evaluates the proficiency of LLMs in managing multimodal multistructured data with code execution. Our experimental findings on BabelBench indicate that even cutting-edge models like ChatGPT 4 exhibit substantial room for improvement.
  arXiv  Detail & Related papers  (2024-10-01T15:11:24Z)
• CRAFT Your Dataset: Task-Specific Synthetic Dataset Generation Through Corpus Retrieval and Augmentation [51.2289822267563]
  We propose a method for generating synthetic datasets, given a small number of user-written few-shots that demonstrate the task to be performed.<n>We demonstrate that CRAFT can efficiently generate large-scale task-specific training datasets for four diverse tasks: biology, medicine, and commonsense question-answering (QA)<n>Our experiments show that CRAFT-based models outperform or match general LLMs on QA tasks, while exceeding models trained on human-curated summarization data by 46 preference points.
  arXiv  Detail & Related papers  (2024-09-03T17:54:40Z)
• DiscoveryBench: Towards Data-Driven Discovery with Large Language Models [50.36636396660163]
  We present DiscoveryBench, the first comprehensive benchmark that formalizes the multi-step process of data-driven discovery. Our benchmark contains 264 tasks collected across 6 diverse domains, such as sociology and engineering. Our benchmark, thus, illustrates the challenges in autonomous data-driven discovery and serves as a valuable resource for the community to make progress.
  arXiv  Detail & Related papers  (2024-07-01T18:58:22Z)
• CMDBench: A Benchmark for Coarse-to-fine Multimodal Data Discovery in Compound AI Systems [10.71630696651595]
  Compound AI systems (CASs) that employ LLMs as agents to accomplish knowledge-intensive tasks have garnered significant interest within database and AI communities. silos of multimodal data sources make it difficult to identify appropriate data sources for accomplishing the task at hand. We propose CMDBench, a benchmark modeling the complexity of enterprise data platforms.
  arXiv  Detail & Related papers  (2024-06-02T01:10:41Z)
• Diffusion Model is an Effective Planner and Data Synthesizer for Multi-Task Reinforcement Learning [101.66860222415512]
  Multi-Task Diffusion Model (textscMTDiff) is a diffusion-based method that incorporates Transformer backbones and prompt learning for generative planning and data synthesis. For generative planning, we find textscMTDiff outperforms state-of-the-art algorithms across 50 tasks on Meta-World and 8 maps on Maze2D.
  arXiv  Detail & Related papers  (2023-05-29T05:20:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.