---
title: "Tree-Notebook — paper by Qiu et al. (2026) — summary and ideas"
description: "The authors also release a noise-augmented InfiAgent-DABench. 89.49% accuracy. 55 references."
authors: ["Junkun Qiu", "Min Huang", "Qinghai Miao"]
year: 2026
venue: "Findings of the Association for Computational Linguistics: ACL 2026"
source: "https://aclanthology.org/2026.findings-acl.783/"
doi: "10.18653/v1/2026.findings-acl.783"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/qiu-2026-tree-notebook-context-aware-agent/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/qiu-2026-tree-notebook-context-aware-agent/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/46/) / Tree-Notebook: A Context-Aware Agent with Tree Search and Entropy-Aware Data Shadow for Interactive Data Science

# Tree-Notebook: A Context-Aware Agent with Tree Search and Entropy-Aware Data Shadow for Interactive Data Science

**Authors:** Junkun Qiu, [Min Huang](https://md.research.elamur.ai/free/en/authors/min-huang/) and Qinghai Miao · **Year:** 2026 · **Venue:** [Findings of the Association for Computational Linguistics: ACL 2026](https://md.research.elamur.ai/free/en/venues/findings/) ([Findings of the Association for Computational Linguistics 2026](https://md.research.elamur.ai/free/en/venues/findings/2026/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.findings-acl.783/) · [PDF](https://aclanthology.org/2026.findings-acl.783.pdf) · [DOI 10.18653/v1/2026.findings-acl.783](https://doi.org/10.18653/v1/2026.findings-acl.783) · [OpenAlex](https://openalex.org/W7166854095)

**Citations:** 0 citations (OpenAlex, 2026-10-14)

## Summary
LLM agents for data science often behave like linear script writers. They fill the context window with redundant output and cannot cleanly abandon a bad analysis path. They also miss "silent failures", where code runs without errors but corrupts the data, for example a dropna() call that deletes most rows. Tree-Notebook addresses this by organising Jupyter cells as nodes of a search tree. Problem solving is framed as a POMDP whose path evaluation combines task utility with an entropy-based information-gain signal. High semantic entropy triggers branching into alternative hypotheses. A "Data Shadow" probe runs after each cell and records DataFrame metadata (shape, schema, types, statistics, provenance). This gives the model a compact view of the kernel state that it otherwise cannot see. Checkpoint-based rollbacks let the agent backtrack, and isomorphic merging collapses equivalent states into a DAG. The authors also release a noise-augmented InfiAgent-DABench. The system reports state-of-the-art results on InfiAgent-DABench and DS-Bench and remains strongest under noise. This suggests that tree-structured, data-aware agents are more robust than linear ones.

## Key points
- With GPT-4o on InfiAgent-DABench, Tree-Notebook reaches 89.49% accuracy, compared with 85.99% for TaskWeaver and Datawise Agent and 81.32% for ReAct. On the noise-augmented version (irrelevant files, data noise) it scores 80.54%.
- Ablations on the base and noisy splits show that every component contributes. Removing dynamic branching gives 85.99/73.15, removing spatio-temporal backtracking gives 87.55/77.82, and removing Data Shadow gives 86.38/76.65.
- The method costs about 14,977 tokens per task, slightly below TaskWeaver's 15,069 and above Datawise Agent's 8,557.
- On DS-Bench, Data Shadow removes the need for exploratory calls such as df.info(). Without the semantic evaluator, Tree-Notebook averages 5.73 LLM invocations per task, compared with 10.19 for Datawise Agent.
- The authors list several limitations:
  - higher inference overhead than linear agents;
  - dependence on the evaluator LLM's entropy estimates;
  - Data Shadow is designed for tabular data only.
- Code is available at github.com/QJK-BUAA/Tree-Notebook.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

## Institutions

- [University of Chinese Academy of Sciences](https://md.research.elamur.ai/free/en/universities/university-of-chinese-academy-of-sciences/) — University, Beijing, China · 147 works · 8,480 citations

📚 Shelves (5): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 16,194 works · [🗄️ Information Systems](https://md.research.elamur.ai/free/en/shelves/computer-science/information-systems/) · 1,437 works · [🎯 Decision Sciences](https://md.research.elamur.ai/free/en/shelves/decision-sciences/) · 209 works · [🎯 Information Systems and Management](https://md.research.elamur.ai/free/en/shelves/decision-sciences/information-systems-and-management/) · 41 works

## Cite

Cite as: Junkun Qiu, Min Huang and Qinghai Miao. 2026. Tree-Notebook: A Context-Aware Agent with Tree Search and Entropy-Aware Data Shadow for Interactive Data Science. Findings of the Association for Computational Linguistics: ACL 2026.

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{qiu2026tree,
  title = {{Tree-Notebook: A Context-Aware Agent with Tree Search and Entropy-Aware Data Shadow for Interactive Data Science}},
  author = {Junkun Qiu, Min Huang and Qinghai Miao},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.783},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.783}
}
```

- [← previous Tree-Based Interview Topic Guidance for Collecting Target Information under Adaptive Topic continuation/switching](https://md.research.elamur.ai/free/en/papers/nagasawa-2026-tree-based-interview-topic-guidance/)
- [next → Tree-of-Evidence: Efficient “System 2” Search for Faithful Multimodal Grounding](https://md.research.elamur.ai/free/en/papers/nnamdi-2026-tree-evidence-efficient-system-2/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/46/)

## References

55 references, 9 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Mourad Aouini and Jinan Loubani. 2025. Towards more contextual agents: An extractor-generator optimization framework. arXiv preprint arXiv:2502.12926. — [arXiv:2502.12926](https://arxiv.org/abs/2502.12926) [find](https://scholar.google.com/scholar?q=Mourad+Aouini+and+Jinan+Loubani%2E+2025%2E+Towards+more+contextual+agents%3A+An+extractor%2Dgenerator+optimization+framework%2E+arXiv+preprint+arXiv%3A2502%2E12926%2E+%E2%80%94+%5BarXiv%3A2502%2E12926%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2502%2E1)
2. Jincheng Bai, Zhenyu Zhang, Jennifer Zhang, and Jason Zhu. 2025. Insight agents: An llm-based multi-agent system for data insights. In Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval, pages 4335–4339. [find](https://scholar.google.com/scholar?q=Jincheng+Bai%2C+Zhenyu+Zhang%2C+Jennifer+Zhang%2C+and+Jason+Zhu%2E+2025%2E+Insight+agents%3A+An+llm%2Dbased+multi%2Dagent+system+for+data+insights%2E+In+Proceedings+of+the+48th+International+ACM+SIGIR+Conference+on+Res)
3. Maciej Besta, Nils Blach, Ales Kubicek, Robert Gerstenberger, Michal Podstawski, Lukas Gianinazzi, Joanna Gajda, Tomasz Lehmann, Hubert Niewiadomski, Piotr Nyczyk, et al. 2024. Graph of thoughts: Solving elaborate problems with large language models. In Proceedings of the AAAI conference on artifici… [find](https://scholar.google.com/scholar?q=Maciej+Besta%2C+Nils+Blach%2C+Ales+Kubicek%2C+Robert+Gerstenberger%2C+Michal+Podstawski%2C+Lukas+Gianinazzi%2C+Joanna+Gajda%2C+Tomasz+Lehmann%2C+Hubert+Niewiadomski%2C+Piotr+Nyczyk%2C+et+al%2E+2024%2E+Graph+of+thoughts%3A+Solv)
4. Abhi Chivukula, Jay Somasundaram, and Vijay Somasundaram. 2025. Agint: Agentic graph compilation for software engineering agents. arXiv preprint arXiv:2511.19635. — [arXiv:2511.19635](https://arxiv.org/abs/2511.19635) [find](https://scholar.google.com/scholar?q=Abhi+Chivukula%2C+Jay+Somasundaram%2C+and+Vijay+Somasundaram%2E+2025%2E+Agint%3A+Agentic+graph+compilation+for+software+engineering+agents%2E+arXiv+preprint+arXiv%3A2511%2E19635%2E+%E2%80%94+%5BarXiv%3A2511%2E19635%5D%28https%3A%2F%2Farxiv%2Eor)
5. Victor Dibia. 2023. Lida: A tool for automatic generation of grammar-agnostic visualizations and infographics using large language models. arXiv preprint arXiv:2303.02927. [find](https://scholar.google.com/scholar?q=Victor+Dibia%2E+2023%2E+Lida%3A+A+tool+for+automatic+generation+of+grammar%2Dagnostic+visualizations+and+infographics+using+large+language+models%2E+arXiv+preprint+arXiv%3A2303%2E02927%2E)
6. David Donoho. 2017. 50 years of data science. Journal of Computational and Graphical Statistics, 26(4):745–766. [find](https://scholar.google.com/scholar?q=David+Donoho%2E+2017%2E+50+years+of+data+science%2E+Journal+of+Computational+and+Graphical+Statistics%2C+26%284%29%3A745%E2%80%93766%2E)
7. Sebastian Farquhar, Jannik Kossen, Lorenz Kuhn, and Yarin Gal. 2024. Detecting hallucinations in large language models using semantic entropy. Nature, 630(8017):625–630. [find](https://scholar.google.com/scholar?q=Sebastian+Farquhar%2C+Jannik+Kossen%2C+Lorenz+Kuhn%2C+and+Yarin+Gal%2E+2024%2E+Detecting+hallucinations+in+large+language+models+using+semantic+entropy%2E+Nature%2C+630%288017%29%3A625%E2%80%93630%2E)
8. Chengquan Guo, Xun Liu, Chulin Xie, Andy Zhou, Yi Zeng, Zinan Lin, Dawn Song, and Bo Li. 2024a. Redcode: Risky code execution and generation benchmark for code agents. Advances in Neural Information Processing Systems, 37:106190–106236. [find](https://scholar.google.com/scholar?q=Chengquan+Guo%2C+Xun+Liu%2C+Chulin+Xie%2C+Andy+Zhou%2C+Yi+Zeng%2C+Zinan+Lin%2C+Dawn+Song%2C+and+Bo+Li%2E+2024a%2E+Redcode%3A+Risky+code+execution+and+generation+benchmark+for+code+agents%2E+Advances+in+Neural+Information+P)
9. Siyuan Guo, Cheng Deng, Ying Wen, Hechang Chen, Yi Chang, and Jun Wang. 2024b. Ds-agent: Automated data science by empowering large language models with case-based reasoning. arXiv preprint arXiv:2402.17453. [find](https://scholar.google.com/scholar?q=Siyuan+Guo%2C+Cheng+Deng%2C+Ying+Wen%2C+Hechang+Chen%2C+Yi+Chang%2C+and+Jun+Wang%2E+2024b%2E+Ds%2Dagent%3A+Automated+data+science+by+empowering+large+language+models+with+case%2Dbased+reasoning%2E+arXiv+preprint+arXiv%3A2402)
10. Shibo Hao, Yi Gu, Haodi Ma, Joshua Hong, Zhen Wang, Daisy Wang, and Zhiting Hu. 2023. Reasoning with language model is planning with world model. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 8154–8173. [find](https://scholar.google.com/scholar?q=Shibo+Hao%2C+Yi+Gu%2C+Haodi+Ma%2C+Joshua+Hong%2C+Zhen+Wang%2C+Daisy+Wang%2C+and+Zhiting+Hu%2E+2023%2E+Reasoning+with+language+model+is+planning+with+world+model%2E+In+Proceedings+of+the+2023+Conference+on+Empirical+Met)
11. Md Mahadi Hassan, Alex Knipper, and Shubhra Kanti Karmaker Santu. 2023. Chatgpt as your personal data scientist. arXiv preprint arXiv:2305.13657. [find](https://scholar.google.com/scholar?q=Md+Mahadi+Hassan%2C+Alex+Knipper%2C+and+Shubhra+Kanti+Karmaker+Santu%2E+2023%2E+Chatgpt+as+your+personal+data+scientist%2E+arXiv+preprint+arXiv%3A2305%2E13657%2E)
12. Noah Hollmann, Samuel Müller, and Frank Hutter. 2023. Large language models for automated data science: Introducing caafe for context-aware automated feature engineering. Advances in Neural Information Processing Systems, 36:44753–44775. [find](https://scholar.google.com/scholar?q=Noah+Hollmann%2C+Samuel+M%C3%BCller%2C+and+Frank+Hutter%2E+2023%2E+Large+language+models+for+automated+data+science%3A+Introducing+caafe+for+context%2Daware+automated+feature+engineering%2E+Advances+in+Neural+Informatio)
13. Sirui Hong, Yizhang Lin, Bang Liu, Bangbang Liu, Binhao Wu, Ceyao Zhang, Danyang Li, Jiaqi Chen, Jiayi Zhang, Jinlin Wang, et al. 2025. [Data interpreter: An llm agent for data science](https://md.research.elamur.ai/free/en/papers/hong-2025-data-interpreter-llm-agent-data/). In Findings of the Association for Computational Linguistics: ACL 2025, pages 19796–19821.
14. Sirui Hong, Mingchen Zhuge, Jonathan Chen, Xiawu Zheng, Yuheng Cheng, Jinlin Wang, Ceyao Zhang, Zili Wang, Steven Ka Shing Yau, Zijuan Lin, et al. 2023. [Metagpt: Meta programming for a multi-agent collaborative framework](https://md.research.elamur.ai/free/en/papers/hong-2023-metagpt-meta-programming-multi/). In The Twelfth International Conference on Learning Representations.
15. Xueyu Hu, Ziyu Zhao, Shuang Wei, Ziwei Chai, Qianli Ma, Guoyin Wang, Xuwu Wang, Jing Su, Jingjing Xu, Ming Zhu, et al. 2024. Infiagent-dabench: Evaluating agents on data analysis tasks. arXiv preprint arXiv:2401.05507. — [arXiv:2401.05507](https://arxiv.org/abs/2401.05507) [find](https://scholar.google.com/scholar?q=Xueyu+Hu%2C+Ziyu+Zhao%2C+Shuang+Wei%2C+Ziwei+Chai%2C+Qianli+Ma%2C+Guoyin+Wang%2C+Xuwu+Wang%2C+Jing+Su%2C+Jingjing+Xu%2C+Ming+Zhu%2C+et+al%2E+2024%2E+Infiagent%2Ddabench%3A+Evaluating+agents+on+data+analysis+tasks%2E+arXiv+preprint)
16. Qian Huang, Jian Vora, Percy Liang, and Jure Leskovec. 2023. [Mlagentbench: Evaluating language agents on machine learning experimentation](https://md.research.elamur.ai/free/en/papers/huang-2023-mlagentbench-evaluating-language-agents/). arXiv preprint arXiv:2310.03302.
17. Michael Janner, Yilun Du, Joshua B Tenenbaum, and Sergey Levine. 2022. Planning with diffusion for flexible behavior synthesis. arXiv preprint arXiv:2205.09991. — [arXiv:2205.09991](https://arxiv.org/abs/2205.09991) [find](https://scholar.google.com/scholar?q=Michael+Janner%2C+Yilun+Du%2C+Joshua+B+Tenenbaum%2C+and+Sergey+Levine%2E+2022%2E+Planning+with+diffusion+for+flexible+behavior+synthesis%2E+arXiv+preprint+arXiv%3A2205%2E09991%2E+%E2%80%94+%5BarXiv%3A2205%2E09991%5D%28https%3A%2F%2Farxiv%2Eorg%2F)
18. Liqiang Jing, Zhehui Huang, Xiaoyang Wang, Wenlin Yao, Wenhao Yu, Kaixin Ma, Hongming Zhang, Xinya Du, and Dong Yu. 2024. Dsbench: How far are data science agents from becoming data science experts? arXiv preprint arXiv:2409.07703. [find](https://scholar.google.com/scholar?q=Liqiang+Jing%2C+Zhehui+Huang%2C+Xiaoyang+Wang%2C+Wenlin+Yao%2C+Wenhao+Yu%2C+Kaixin+Ma%2C+Hongming+Zhang%2C+Xinya+Du%2C+and+Dong+Yu%2E+2024%2E+Dsbench%3A+How+far+are+data+science+agents+from+becoming+data+science+experts%3F+a)
19. Lorenz Kuhn, Yarin Gal, and Sebastian Farquhar. 2023. Semantic uncertainty: Linguistic invariances for uncertainty estimation in natural language generation. arXiv preprint arXiv:2302.09664. [find](https://scholar.google.com/scholar?q=Lorenz+Kuhn%2C+Yarin+Gal%2C+and+Sebastian+Farquhar%2E+2023%2E+Semantic+uncertainty%3A+Linguistic+invariances+for+uncertainty+estimation+in+natural+language+generation%2E+arXiv+preprint+arXiv%3A2302%2E09664%2E)
20. Jiaqi Li, Xinyi Dong, Yang Liu, Zhizhuo Yang, Quansen Wang, Xiaobo Wang, Song-Chun Zhu, Zixia Jia, and Zilong Zheng. 2025a. Reflectevo: Improving meta introspection of small llms by learning self-reflection. In Findings of the Association for Computational Linguistics: ACL 2025, pages 16948–16966. [find](https://scholar.google.com/scholar?q=Jiaqi+Li%2C+Xinyi+Dong%2C+Yang+Liu%2C+Zhizhuo+Yang%2C+Quansen+Wang%2C+Xiaobo+Wang%2C+Song%2DChun+Zhu%2C+Zixia+Jia%2C+and+Zilong+Zheng%2E+2025a%2E+Reflectevo%3A+Improving+meta+introspection+of+small+llms+by+learning+self%2Drefl)
21. Shuocheng Li, Yihao Liu, Silin Du, Wenxuan Zeng, Zhe Xu, Mengyu Zhou, Yeye He, Haoyu Dong, Shi Han, and Dongmei Zhang. 2025b. Jupiter: Enhancing llm data analysis capabilities via notebook and inference-time value-guided search. arXiv preprint arXiv:2509.09245. — [arXiv:2509.09245](https://arxiv.org/abs/2509.09245) [find](https://scholar.google.com/scholar?q=Shuocheng+Li%2C+Yihao+Liu%2C+Silin+Du%2C+Wenxuan+Zeng%2C+Zhe+Xu%2C+Mengyu+Zhou%2C+Yeye+He%2C+Haoyu+Dong%2C+Shi+Han%2C+and+Dongmei+Zhang%2E+2025b%2E+Jupiter%3A+Enhancing+llm+data+analysis+capabilities+via+notebook+and+inferen)
22. Yujia Li, David Choi, Junyoung Chung, Nate Kushman, Julian Schrittwieser, Rémi Leblond, Tom Eccles, James Keeling, Felix Gimeno, Agustin Dal Lago, et al. 2022. [Competition-level code generation with alphacode](https://md.research.elamur.ai/free/en/papers/li-2022-competition-level-code-generation-alphacode/). Science, 378(6624):1092–1097.
23. Ziming Li, Qianbo Zang, David Ma, Jiawei Guo, Tuney Zheng, Minghao Liu, Xinyao Niu, Yue Wang, Jian Yang, Jiaheng Liu, et al. 2024. Autokaggle: A multi-agent framework for autonomous data science competitions. arXiv preprint arXiv:2410.20424. [find](https://scholar.google.com/scholar?q=Ziming+Li%2C+Qianbo+Zang%2C+David+Ma%2C+Jiawei+Guo%2C+Tuney+Zheng%2C+Minghao+Liu%2C+Xinyao+Niu%2C+Yue+Wang%2C+Jian+Yang%2C+Jiaheng+Liu%2C+et+al%2E+2024%2E+Autokaggle%3A+A+multi%2Dagent+framework+for+autonomous+data+science+compe)
24. Pingchuan Ma, Rui Ding, Shuai Wang, Shi Han, and Dongmei Zhang. 2023. Demonstration of insightpilot: An llm-empowered automated data exploration system. arXiv preprint arXiv:2304.00477. [find](https://scholar.google.com/scholar?q=Pingchuan+Ma%2C+Rui+Ding%2C+Shuai+Wang%2C+Shi+Han%2C+and+Dongmei+Zhang%2E+2023%2E+Demonstration+of+insightpilot%3A+An+llm%2Dempowered+automated+data+exploration+system%2E+arXiv+preprint+arXiv%3A2304%2E00477%2E)
25. Junyuan Mao, Fanci Meng, Yifan Duan, Miao Yu, Xiaojun Jia, Junfeng Fang, Yuxuan Liang, Kun Wang, and Qingsong Wen. 2025. Agentsafe: Safeguarding large language model-based multi-agent systems via hierarchical data management. arXiv preprint arXiv:2503.04392. — [arXiv:2503.04392](https://arxiv.org/abs/2503.04392) [find](https://scholar.google.com/scholar?q=Junyuan+Mao%2C+Fanci+Meng%2C+Yifan+Duan%2C+Miao+Yu%2C+Xiaojun+Jia%2C+Junfeng+Fang%2C+Yuxuan+Liang%2C+Kun+Wang%2C+and+Qingsong+Wen%2E+2025%2E+Agentsafe%3A+Safeguarding+large+language+model%2Dbased+multi%2Dagent+systems+via+hier)
26. Tsendsuren Munkhdalai, Manaal Faruqui, and Siddharth Gopal. 2024. Leave no context behind: Efficient infinite context transformers with infini-attention. arXiv preprint arXiv:2404.07143, 101. [find](https://scholar.google.com/scholar?q=Tsendsuren+Munkhdalai%2C+Manaal+Faruqui%2C+and+Siddharth+Gopal%2E+2024%2E+Leave+no+context+behind%3A+Efficient+infinite+context+transformers+with+infini%2Dattention%2E+arXiv+preprint+arXiv%3A2404%2E07143%2C+101%2E)
27. Dang Nguyen, Ali Payani, and Baharan Mirzasoleiman. 2025. Beyond semantic entropy: Boosting llm uncertainty quantification with pairwise semantic similarity. arXiv preprint arXiv:2506.00245. [find](https://scholar.google.com/scholar?q=Dang+Nguyen%2C+Ali+Payani%2C+and+Baharan+Mirzasoleiman%2E+2025%2E+Beyond+semantic+entropy%3A+Boosting+llm+uncertainty+quantification+with+pairwise+semantic+similarity%2E+arXiv+preprint+arXiv%3A2506%2E00245%2E)
28. Yixin Ou, Yujie Luo, Jingsheng Zheng, Lanning Wei, Zhuoyun Yu, Shuofei Qiao, Jintian Zhang, Da Zheng, Yuren Mao, Yunjun Gao, et al. 2025. Automind: Adaptive knowledgeable agent for automated data science. arXiv preprint arXiv:2506.10974. — [arXiv:2506.10974](https://arxiv.org/abs/2506.10974) [find](https://scholar.google.com/scholar?q=Yixin+Ou%2C+Yujie+Luo%2C+Jingsheng+Zheng%2C+Lanning+Wei%2C+Zhuoyun+Yu%2C+Shuofei+Qiao%2C+Jintian+Zhang%2C+Da+Zheng%2C+Yuren+Mao%2C+Yunjun+Gao%2C+et+al%2E+2025%2E+Automind%3A+Adaptive+knowledgeable+agent+for+automated+data+scie)
29. Bo Qiao, Liqun Li, Xu Zhang, Shilin He, Yu Kang, Chaoyun Zhang, Fangkai Yang, Hang Dong, Jue Zhang, Lu Wang, et al. 2023. Taskweaver: A code-first agent framework. arXiv preprint arXiv:2311.17541. — [arXiv:2311.17541](https://arxiv.org/abs/2311.17541) [find](https://scholar.google.com/scholar?q=Bo+Qiao%2C+Liqun+Li%2C+Xu+Zhang%2C+Shilin+He%2C+Yu+Kang%2C+Chaoyun+Zhang%2C+Fangkai+Yang%2C+Hang+Dong%2C+Jue+Zhang%2C+Lu+Wang%2C+et+al%2E+2023%2E+Taskweaver%3A+A+code%2Dfirst+agent+framework%2E+arXiv+preprint+arXiv%3A2311%2E17541%2E+%E2%80%94+%5B)
30. Mizanur Rahman, Amran Bhuiyan, Mohammed Saidul Islam, Md Tahmid Rahman Laskar, Ridwan Mahbub, Ahmed Masry, Shafiq Joty, and Enamul Hoque. 2025. Llm-based data science agents: A survey of capabilities, challenges, and future directions. arXiv preprint arXiv:2510.04023. — [arXiv:2510.04023](https://arxiv.org/abs/2510.04023) [find](https://scholar.google.com/scholar?q=Mizanur+Rahman%2C+Amran+Bhuiyan%2C+Mohammed+Saidul+Islam%2C+Md+Tahmid+Rahman+Laskar%2C+Ridwan+Mahbub%2C+Ahmed+Masry%2C+Shafiq+Joty%2C+and+Enamul+Hoque%2E+2025%2E+Llm%2Dbased+data+science+agents%3A+A+survey+of+capabilities%2C)
31. Abdullah Vanlioglu. 2025. Entropy-guided sequence weighting for efficient exploration in rl-based llm fine-tuning. arXiv preprint arXiv:2503.22456. — [arXiv:2503.22456](https://arxiv.org/abs/2503.22456) [find](https://scholar.google.com/scholar?q=Abdullah+Vanlioglu%2E+2025%2E+Entropy%2Dguided+sequence+weighting+for+efficient+exploration+in+rl%2Dbased+llm+fine%2Dtuning%2E+arXiv+preprint+arXiv%3A2503%2E22456%2E+%E2%80%94+%5BarXiv%3A2503%2E22456%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2503%2E2245)
32. Ante Wang, Linfeng Song, Ye Tian, Dian Yu, Haitao Mi, Xiangyu Duan, Zhaopeng Tu, Jinsong Su, and Dong Yu. 2025a. Don’t get lost in the trees: Streamlining llm reasoning by overcoming tree search exploration pitfalls. arXiv preprint arXiv:2502.11183. [find](https://scholar.google.com/scholar?q=Ante+Wang%2C+Linfeng+Song%2C+Ye+Tian%2C+Dian+Yu%2C+Haitao+Mi%2C+Xiangyu+Duan%2C+Zhaopeng+Tu%2C+Jinsong+Su%2C+and+Dong+Yu%2E+2025a%2E+Don%E2%80%99t+get+lost+in+the+trees%3A+Streamlining+llm+reasoning+by+overcoming+tree+search+explo)
33. Chenglong Wang, Bongshin Lee, Steven M Drucker, Dan Marshall, and Jianfeng Gao. 2025b. Data formulator 2: Iterative creation of data visualizations, with ai transforming data along the way. In Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems, pages 1–17. [find](https://scholar.google.com/scholar?q=Chenglong+Wang%2C+Bongshin+Lee%2C+Steven+M+Drucker%2C+Dan+Marshall%2C+and+Jianfeng+Gao%2E+2025b%2E+Data+formulator+2%3A+Iterative+creation+of+data+visualizations%2C+with+ai+transforming+data+along+the+way%2E+In+Proceed)
34. Huichen Will Wang, Larry Birnbaum, and Vidya Setlur. 2025c. Jupybara: Operationalizing a design space for actionable data analysis and storytelling with llms. In Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems, pages 1–24. [find](https://scholar.google.com/scholar?q=Huichen+Will+Wang%2C+Larry+Birnbaum%2C+and+Vidya+Setlur%2E+2025c%2E+Jupybara%3A+Operationalizing+a+design+space+for+actionable+data+analysis+and+storytelling+with+llms%2E+In+Proceedings+of+the+2025+CHI+Conference)
35. Xiaobo Wang, Zixia Jia, Jiaqi Li, Qi Liu, and Zilong Zheng. 2025d. Adaptive preference optimization with uncertainty-aware utility anchor. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 19204–19225. [find](https://scholar.google.com/scholar?q=Xiaobo+Wang%2C+Zixia+Jia%2C+Jiaqi+Li%2C+Qi+Liu%2C+and+Zilong+Zheng%2E+2025d%2E+Adaptive+preference+optimization+with+uncertainty%2Daware+utility+anchor%2E+In+Findings+of+the+Association+for+Computational+Linguistics%3A)
36. Xingyao Wang, Yangyi Chen, Lifan Yuan, Yizhe Zhang, Yunzhu Li, Hao Peng, and Heng Ji. 2024. [Executable code actions elicit better llm agents](https://md.research.elamur.ai/free/en/papers/wang-2024-executable-code-actions-elicit-better/). In Forty-first International Conference on Machine Learning.
37. Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, Quoc V Le, Denny Zhou, et al. 2022. [Chain-of-thought prompting elicits reasoning in large language models](https://md.research.elamur.ai/free/en/papers/wei-2022-chain-thought-prompting-elicits-reasoning/). Advances in neural information processing systems, 35:24824–24837.
38. Nathaniel Weir, Muhammad Khalifa, Linlu Qiu, Orion Weller, and Peter Clark. 2024. Learning to reason via program generation, emulation, and search. Advances in Neural Information Processing Systems, 37:36390–36413. [find](https://scholar.google.com/scholar?q=Nathaniel+Weir%2C+Muhammad+Khalifa%2C+Linlu+Qiu%2C+Orion+Weller%2C+and+Peter+Clark%2E+2024%2E+Learning+to+reason+via+program+generation%2C+emulation%2C+and+search%2E+Advances+in+Neural+Information+Processing+Systems%2C+3)
39. Noah Shinn, Federico Cassano, Ashwin Gopinath, Karthik Narasimhan, and Shunyu Yao. 2023. [Reflexion: Language agents with verbal reinforcement learning](https://md.research.elamur.ai/free/en/papers/shinn-2023-reflexion-language-agents-verbal-reinforcement/). Advances in Neural Information Processing Systems, 36:8634–8652.
40. Muning Wen, Cheng Deng, Jun Wang, Weinan Zhang, and Ying Wen. 2024. Entropy-regularized token-level policy optimization for large language models. CoRR. [find](https://scholar.google.com/scholar?q=Muning+Wen%2C+Cheng+Deng%2C+Jun+Wang%2C+Weinan+Zhang%2C+and+Ying+Wen%2E+2024%2E+Entropy%2Dregularized+token%2Dlevel+policy+optimization+for+large+language+models%2E+CoRR%2E)
41. José Antonio Siqueira de Cerqueira, Mamia Agbese, Rebekah Rousi, Nannan Xi, Juho Hamari, and Pekka Abrahamsson. 2024. Can we trust ai agents? an experimental study towards trustworthy llm-based multi-agent systems for ai ethics. arXiv e-prints, pages arXiv–2411. [find](https://scholar.google.com/scholar?q=Jos%C3%A9+Antonio+Siqueira+de+Cerqueira%2C+Mamia+Agbese%2C+Rebekah+Rousi%2C+Nannan+Xi%2C+Juho+Hamari%2C+and+Pekka+Abrahamsson%2E+2024%2E+Can+we+trust+ai+agents%3F+an+experimental+study+towards+trustworthy+llm%2Dbased+multi%2D)
42. Qingyun Wu, Gagan Bansal, Jieyu Zhang, Yiran Wu, Beibin Li, Erkang Zhu, Li Jiang, Xiaoyun Zhang, Shaokun Zhang, Jiale Liu, et al. 2024. Autogen: Enabling next-gen llm applications via multi-agent conversations. In First Conference on Language Modeling. [find](https://scholar.google.com/scholar?q=Qingyun+Wu%2C+Gagan+Bansal%2C+Jieyu+Zhang%2C+Yiran+Wu%2C+Beibin+Li%2C+Erkang+Zhu%2C+Li+Jiang%2C+Xiaoyun+Zhang%2C+Shaokun+Zhang%2C+Jiale+Liu%2C+et+al%2E+2024%2E+Autogen%3A+Enabling+next%2Dgen+llm+applications+via+multi%2Dagent+conv)
43. Jia Ao Sun, Hao Yu, Fabrizio Gotti, Fengran Mo, Yihong Wu, Yuchen Hui, and Jian-Yun Nie. 2025. Search-on-graph: Iterative informed navigation for large language model reasoning on knowledge graphs. arXiv preprint arXiv:2510.08825. — [arXiv:2510.08825](https://arxiv.org/abs/2510.08825) [find](https://scholar.google.com/scholar?q=Jia+Ao+Sun%2C+Hao+Yu%2C+Fabrizio+Gotti%2C+Fengran+Mo%2C+Yihong+Wu%2C+Yuchen+Hui%2C+and+Jian%2DYun+Nie%2E+2025%2E+Search%2Don%2Dgraph%3A+Iterative+informed+navigation+for+large+language+model+reasoning+on+knowledge+graphs%2E+ar)
44. Yiran Wu, Feiran Jia, Shaokun Zhang, Hangyu Li, Erkang Zhu, Yue Wang, Yin Tat Lee, Richard Peng, Qingyun Wu, and Chi Wang. 2023. An empirical study on challenging math problem solving with gpt-4. arXiv e-prints, pages arXiv–2306. [find](https://scholar.google.com/scholar?q=Yiran+Wu%2C+Feiran+Jia%2C+Shaokun+Zhang%2C+Hangyu+Li%2C+Erkang+Zhu%2C+Yue+Wang%2C+Yin+Tat+Lee%2C+Richard+Peng%2C+Qingyun+Wu%2C+and+Chi+Wang%2E+2023%2E+An+empirical+study+on+challenging+math+problem+solving+with+gpt%2D4%2E+arXi)
45. Siqiao Xue, Caigao Jiang, Wenhui Shi, Fangyin Cheng, Keting Chen, Hongjun Yang, Zhiping Zhang, Jianshan He, Hongyang Zhang, Ganglin Wei, et al. 2023. Db-gpt: Empowering database interactions with private large language models. arXiv preprint arXiv:2312.17449. — [arXiv:2312.17449](https://arxiv.org/abs/2312.17449) [find](https://scholar.google.com/scholar?q=Siqiao+Xue%2C+Caigao+Jiang%2C+Wenhui+Shi%2C+Fangyin+Cheng%2C+Keting+Chen%2C+Hongjun+Yang%2C+Zhiping+Zhang%2C+Jianshan+He%2C+Hongyang+Zhang%2C+Ganglin+Wei%2C+et+al%2E+2023%2E+Db%2Dgpt%3A+Empowering+database+interactions+with+priv)
46. Andy Zhou, Kai Yan, Michal Shlapentokh-Rothman, Haohan Wang, and Yu-Xiong Wang. 2023. Language agent tree search unifies reasoning acting and planning in language models. arXiv preprint arXiv:2310.04406. [find](https://scholar.google.com/scholar?q=Andy+Zhou%2C+Kai+Yan%2C+Michal+Shlapentokh%2DRothman%2C+Haohan+Wang%2C+and+Yu%2DXiong+Wang%2E+2023%2E+Language+agent+tree+search+unifies+reasoning+acting+and+planning+in+language+models%2E+arXiv+preprint+arXiv%3A2310%2E044)
47. Shunyu Yao, Dian Yu, Jeffrey Zhao, Izhak Shafran, Tom Griffiths, Yuan Cao, and Karthik Narasimhan. 2023. Tree of thoughts: Deliberate problem solving with large language models. Advances in neural information processing systems, 36:11809–11822. [find](https://scholar.google.com/scholar?q=Shunyu+Yao%2C+Dian+Yu%2C+Jeffrey+Zhao%2C+Izhak+Shafran%2C+Tom+Griffiths%2C+Yuan+Cao%2C+and+Karthik+Narasimhan%2E+2023%2E+Tree+of+thoughts%3A+Deliberate+problem+solving+with+large+language+models%2E+Advances+in+neural+inf)
48. Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik R Narasimhan, and Yuan Cao. 2022. [React: Synergizing reasoning and acting in language models](https://md.research.elamur.ai/free/en/papers/yao-2022-react-synergizing-reasoning-acting-language/). In The eleventh international conference on learning representations.
49. Ziming You, Yumiao Zhang, Dexuan Xu, Yiwei Lou, Yandong Yan, Wei Wang, Huaming Zhang, and Yu Huang. 2025. Datawiseagent: A notebook-centric llm agent framework for automated data science. arXiv preprint arXiv:2503.07044. — [arXiv:2503.07044](https://arxiv.org/abs/2503.07044) [find](https://scholar.google.com/scholar?q=Ziming+You%2C+Yumiao+Zhang%2C+Dexuan+Xu%2C+Yiwei+Lou%2C+Yandong+Yan%2C+Wei+Wang%2C+Huaming+Zhang%2C+and+Yu+Huang%2E+2025%2E+Datawiseagent%3A+A+notebook%2Dcentric+llm+agent+framework+for+automated+data+science%2E+arXiv+prepri)
50. Xiaokang Zhang, Sijia Luo, Bohan Zhang, Zeyao Ma, Jing Zhang, Yang Li, Guanlin Li, Zijun Yao, Kangli Xu, Jinchang Zhou, et al. 2025a. Tablellm: Enabling tabular data manipulation by llms in real office usage scenarios. In Findings of the Association for Computational Linguistics: ACL 2025, pages 103… [find](https://scholar.google.com/scholar?q=Xiaokang+Zhang%2C+Sijia+Luo%2C+Bohan+Zhang%2C+Zeyao+Ma%2C+Jing+Zhang%2C+Yang+Li%2C+Guanlin+Li%2C+Zijun+Yao%2C+Kangli+Xu%2C+Jinchang+Zhou%2C+et+al%2E+2025a%2E+Tablellm%3A+Enabling+tabular+data+manipulation+by+llms+in+real+offic)
51. Yuge Zhang, Qiyang Jiang, XingyuHan XingyuHan, Nan Chen, Yuqing Yang, and Kan Ren. 2024. Benchmarking data science agents. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 5677–5700. [find](https://scholar.google.com/scholar?q=Yuge+Zhang%2C+Qiyang+Jiang%2C+XingyuHan+XingyuHan%2C+Nan+Chen%2C+Yuqing+Yang%2C+and+Kan+Ren%2E+2024%2E+Benchmarking+data+science+agents%2E+In+Proceedings+of+the+62nd+Annual+Meeting+of+the+Association+for+Computationa)
52. Zhenkui Zhang, Wendong Bu, Kaihang Pan, Bingchen Miao, Wenqiao Zhang, Guoming Wang, Wei Ji, Rui Tang, Juncheng Li, and Siliang Tang. 2026. Evolving generalist virtual agents with generative and associative memory. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 40, pages 130… [find](https://scholar.google.com/scholar?q=Zhenkui+Zhang%2C+Wendong+Bu%2C+Kaihang+Pan%2C+Bingchen+Miao%2C+Wenqiao+Zhang%2C+Guoming+Wang%2C+Wei+Ji%2C+Rui+Tang%2C+Juncheng+Li%2C+and+Siliang+Tang%2E+2026%2E+Evolving+generalist+virtual+agents+with+generative+and+associ)
53. Zhenliang Zhang, Xinyu Hu, Huixuan Zhang, Junzhe Zhang, and Xiaojun Wan. 2025b. [Icr probe: Tracking hidden state dynamics for reliable hallucination detection in llms](https://md.research.elamur.ai/free/en/papers/zhang-2025-icr-probe-tracking-hidden-state/). In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 17986– 180…
54. Jinjin Zhao and Sanjay Krishnan. 2025. Metadata management for ai-augmented data workflows. arXiv preprint arXiv:2508.06814. — [arXiv:2508.06814](https://arxiv.org/abs/2508.06814) [find](https://scholar.google.com/scholar?q=Jinjin+Zhao+and+Sanjay+Krishnan%2E+2025%2E+Metadata+management+for+ai%2Daugmented+data+workflows%2E+arXiv+preprint+arXiv%3A2508%2E06814%2E+%E2%80%94+%5BarXiv%3A2508%2E06814%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2508%2E06814%29)
55. Tianyu Zheng, Ge Zhang, Tianhao Shen, Xueling Liu, Bill Yuchen Lin, Jie Fu, Wenhu Chen, and Xiang Yue. 2024. Opencodeinterpreter: Integrating code generation with execution and refinement. arXiv preprint arXiv:2402.14658. [find](https://scholar.google.com/scholar?q=Tianyu+Zheng%2C+Ge+Zhang%2C+Tianhao+Shen%2C+Xueling+Liu%2C+Bill+Yuchen+Lin%2C+Jie+Fu%2C+Wenhu+Chen%2C+and+Xiang+Yue%2E+2024%2E+Opencodeinterpreter%3A+Integrating+code+generation+with+execution+and+refinement%2E+arXiv+prepr)

*Updated 1 November 2026*