ACL Findings2026
Tree-Notebook: A Context-Aware Agent with Tree Search and Entropy-Aware Data Shadow for Interactive Data Science
Abstract
While LLM-based agents have emerged as a focal point for automating data science tasks, they continue to grapple with inefficient context management, "silent failures" (where code executes correctly but fails the task objectives), and error propagation inherent in sequential generation.In this paper, we propose Tree-Notebook, an agentic framework designed to mimic the iterative cognitive process of human data scientists.At its core, Tree-Notebook conceptualizes Jupyter Notebook cells as nodes within a tree structure, facilitating organized and efficient context retrieval.We formalize the task-solving process as a Partially Observable Markov Decision Process (POMDP) over a dynamic tree, utilizing an entropy-based information gain function for path evaluation to enhance adaptability in real-world environments.Furthermore, we introduce the "Data Shadow" system, which resolves silent failures by performing real-time tracking of data distributions, provenance, and semantic constraints.Experimental results demonstrate that Tree-Notebook achieves state-of-the-art (SOTA) performance on both InfiAgent-DABench and DS-Bench.To further evaluate robustness, we introduce an augmented version of InfiAgent-DABench to simulate complex environments, where Tree-Notebook consistently maintains its SOTA standing.Code is available at
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
- Tree of Thoughts: Deliberate Problem Solving with Large Language Models cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
- Reflexion: language agents with verbal reinforcement learning cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
- Graph of Thoughts: Solving Elaborate Problems with Large Language Models cites Tree of Thoughts: Deliberate Problem Solving with Large Language Models
- Graph of Thoughts: Solving Elaborate Problems with Large Language Models cites Reflexion: language agents with verbal reinforcement learning
- Graph of Thoughts: Solving Elaborate Problems with Large Language Models cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
Builds on26
- Chain-of-Thought Prompting Elicits Reasoning in Large Language ModelsJason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma et al.NeurIPS 2022 · 22,562 citations
- Reflexion: language agents with verbal reinforcement learningNoah Shinn, Federico Cassano, Ashwin Gopinath, Karthik Narasimhan et al.NeurIPS 2023 · 5,828 citations
- Tree of Thoughts: Deliberate Problem Solving with Large Language ModelsShunyu Yao, Dian Yu, Jeffrey Zhao, Izhak Shafran et al.NeurIPS 2023 · 5,068 citations
- Graph of Thoughts: Solving Elaborate Problems with Large Language ModelsMaciej Besta, Nils Blach, Ales Kubicek, Robert Gerstenberger et al.AAAI 2024 · 1,292 citations
- Planning with Diffusion for Flexible Behavior SynthesisMichael Janner, Yilun Du, Joshua B. Tenenbaum, Sergey LevineICML 2022 · 1,115 citations
Related papers
- DatawiseAgent: A Notebook-Centric LLM Agent Framework for Adaptive and Robust Data Science AutomationZiming You, Yumiao Zhang, Dexuan Xu, Yiwei Lou et al.EMNLP 2025 · 2 citations
- Data Interpreter: An LLM Agent for Data ScienceSirui Hong, Yizhang Lin, Bang Liu, Bangbang Liu et al.ACL Findings 2025 · 45 citations
- Jupiter: Enhancing LLM Data Analysis Capabilities via Notebook and Inference-Time Value-Guided SearchShuocheng Li, Yihao Liu, Silin Du, Wenxuan Zeng et al.AAAI 2026 · 1 citation
- Mistake Notebook Learning: Batch-Clustered Failures for Training-Free Agent AdaptationXuanbo Su, Yingfang Zhang, Hao Luo, Xiaoteng Liu et al.ACL Findings 2026
- EvoDS: Self-Evolving Autonomous Data Science Agent with Skill Learning and Context ManagementZherui Yang, Fan Liu, Yansong Ning, Hao LiuKDD 2026 · 3 citations
