---
title: "DSMentor — paper by Wang et al. (2026) — summary and ideas"
description: "LLM agents that write code for data-science problems usually handle tasks in whatever order they arrive and do not use what… 38 references."
authors: ["He Wang", "Alexander Hanbo Li", "Yiqun Hu", "Sheng Zhang", "Hideo Kobayashi", "Jiani Zhang", "Henghui Zhu", "Chung-Wei Hang", "Patrick Ng"]
year: 2026
venue: "Proceedings of the First Workshop on Structured Understanding, Retrieval, and Generation in the LLM Era (SURGeLLM 2026)"
source: "https://aclanthology.org/2026.surgellm-1.12/"
doi: "10.18653/v1/2026.surgellm-1.12"
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/wang-2026-dsmentor-curriculum-guided-inference-online/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/wang-2026-dsmentor-curriculum-guided-inference-online/)

[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/28/) / DSMentor: Curriculum-Guided Inference with Online Memory for Data-Science LLM Agents

# DSMentor: Curriculum-Guided Inference with Online Memory for Data-Science LLM Agents

**Authors:** [He Wang](https://md.research.elamur.ai/free/en/authors/he-wang/), Alexander Hanbo Li, [Yiqun Hu](https://md.research.elamur.ai/free/en/authors/yiqun-hu/), [Sheng Zhang](https://md.research.elamur.ai/free/en/authors/sheng-zhang/), [Hideo Kobayashi](https://md.research.elamur.ai/free/en/authors/hideo-kobayashi/), Jiani Zhang, [Henghui Zhu](https://md.research.elamur.ai/free/en/authors/henghui-zhu/), [Chung-Wei Hang](https://md.research.elamur.ai/free/en/authors/chung-wei-hang/) and [Patrick Ng](https://md.research.elamur.ai/free/en/authors/patrick-ng/) · **Year:** 2026 · **Venue:** [Proceedings of the First Workshop on Structured Understanding, Retrieval, and Generation in the LLM Era (SURGeLLM 2026)](https://md.research.elamur.ai/free/en/venues/surgellm/) ([Workshop on Structured Understanding, Retrieval, and Generation in the LLM Era 2026](https://md.research.elamur.ai/free/en/venues/surgellm/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.surgellm-1.12/) · [PDF](https://aclanthology.org/2026.surgellm-1.12.pdf) · [DOI 10.18653/v1/2026.surgellm-1.12](https://doi.org/10.18653/v1/2026.surgellm-1.12) · [OpenAlex](https://openalex.org/W7166811387)

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

## Summary
LLM agents that write code for data-science problems usually handle tasks in whatever order they arrive and do not use what they learned from earlier tasks. DSMentor is an inference-time framework that applies curriculum learning to fix this. A Mentor agent estimates how hard each problem is and arranges the problems from simplest to hardest. A Student agent then generates code for each problem in that order. An environment checks the code, and every attempt is added to a growing long-term memory together with a correct/incorrect tag. For each new problem, the Student retrieves related, easier examples from this memory, ordered by increasing similarity. The authors tested DSMentor with Claude-3.5-Sonnet and Llama-3.1-70b on DSEval and QRData. With Claude-3.5-Sonnet, it outperformed baseline agents by as much as 5.2% in pass rate and beat GPT-4 with Program-of-Thoughts prompting by 8.8%. The work shows that task order and online memory can improve agents without any extra training.

## Key points
- **Setup:** Benchmarks are DSEval (subsets LeetCode, SO, Exercise, Kaggle) and QRData, a causal/quantitative reasoning benchmark. Backbone models are Claude-3.5-Sonnet and Llama-3.1-70b.
- **Ordering ablation:** Easy-to-hard curricula with similarity-ordered examples usually performed best. For example, DSMentor-Claude scored 0.892 on DSEval-LeetCode, compared with 0.833 for hard-to-easy and 0.850 for random order. DSEval-Kaggle was the exception, where hard-to-easy was slightly better.
- **Incorrect examples in memory:** Keeping failed attempts in memory helped Llama-3.1-70b. Pass rates rose from 0.733 to 0.792 on LeetCode and from 0.475 to 0.508 on QRData. Gains were small on larger subsets such as SO and Kaggle.
- **Limitations:** The method works only at inference time. It also assumes the whole task set is available in advance, so it does not directly fit streaming settings. It has been evaluated only on data-science benchmarks.

*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

- [Carnegie Mellon University](https://md.research.elamur.ai/free/en/universities/carnegie-mellon-university/) — University, Pittsburgh, United States · 539 works · 179,533 citations
- [Amazon](https://md.research.elamur.ai/free/en/companies/amazon/) — Company, Seattle, United States · 112 works · 40,565 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 · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 16,039 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 15,891 works · [🗄️ Information Systems](https://md.research.elamur.ai/free/en/shelves/computer-science/information-systems/) · 1,437 works

## Cite

Cite as: He Wang, Alexander Hanbo Li, Yiqun Hu, Sheng Zhang, Hideo Kobayashi, Jiani Zhang, Henghui Zhu, Chung-Wei Hang and Patrick Ng. 2026. DSMentor: Curriculum-Guided Inference with Online Memory for Data-Science LLM Agents. Proceedings of the First Workshop on Structured Understanding, Retrieval, and Generation in the LLM Era (SURGeLLM 2026).

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

```bibtex
@inproceedings{wang2026dsmentor,
  title = {{DSMentor: Curriculum-Guided Inference with Online Memory for Data-Science LLM Agents}},
  author = {He Wang, Alexander Hanbo Li, Yiqun Hu, Sheng Zhang, Hideo Kobayashi, Jiani Zhang, Henghui Zhu, Chung-Wei Hang and Patrick Ng},
  booktitle = {Proceedings of the First Workshop on Structured Understanding, Retrieval, and Generation in the LLM Era (SURGeLLM 2026)},
  year = {2026},
  doi = {10.18653/v1/2026.surgellm-1.12},
  url = {https://doi.org/10.18653/v1/2026.surgellm-1.12}
}
```

- [← previous DS@GT ARC at CheckThat! 2026: LLM-Based Trace Ranking and Grouped Reward Modeling for Multilingual Numerical Claim Verification](https://md.research.elamur.ai/free/en/papers/sinha-2026-ds-gt-arc-checkthat-2026/)
- [next → Dual Activation-Weight Sparsity: A Training-Free Framework for Efficient Large Language Model Compression](https://md.research.elamur.ai/free/en/papers/sun-2026-dual-activation-weight-sparsity-training/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/28/)

## References

38 references, 11 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Anthropic. 2023. Introducing Claude. [https://www.anthropic.com/news/introducing-claude](https://www.anthropic.com/news/introducing-claude). [↗](https://www.anthropic.com/news/introducing-claude)
2. Yoshua Bengio, Jérôme Louradour, Ronan Collobert, and Jason Weston. 2009. [Curriculum learning](https://md.research.elamur.ai/free/en/papers/bengio-2009-curriculum-learning/). In Proceedings of the 26th Annual International Conference on Machine Learning, ICML ’09, page 41–48.
3. Chapyter Developers. 2023. Chapyter: Chatgpt code interpreter in jupyter notebooks. [https://github.com/chapyter/chapyter](https://github.com/chapyter/chapyter). GitHub repository. [↗](https://github.com/chapyter/chapyter)
4. Mark Chen, Jerry Tworek, Heewoo Jun, Qiming Yuan, Henrique Ponde de Oliveira Pinto, Jared Kaplan, Harri Edwards, Yuri Burda, Nicholas Joseph, Greg Brockman, Alex Ray, Raul Puri, Gretchen Krueger, Michael Petrov, Heidy Khlaaf, Girish Sastry, Pamela Mishkin, Brooke Chan, Scott Gray, and 39 others. 202… — [Evaluating Large Language Models Trained on Code](https://md.research.elamur.ai/free/en/papers/chen-2021-evaluating-large-language-models-trained/)
5. Wenhu Chen, Xueguang Ma, Xinyi Wang, and William W. Cohen. 2023. Program of thoughts prompting: Disentangling computation from reasoning for numerical reasoning tasks. Transactions on Machine Learning Research. [find](https://scholar.google.com/scholar?q=Wenhu+Chen%2C+Xueguang+Ma%2C+Xinyi+Wang%2C+and+William+W%2E+Cohen%2E+2023%2E+Program+of+thoughts+prompting%3A+Disentangling+computation+from+reasoning+for+numerical+reasoning+tasks%2E+Transactions+on+Machine+Learning)
6. Liying Cheng, Xingxuan Li, and Lidong Bing. 2023. Is GPT-4 a good data analyst? In The 2023 Conference on Empirical Methods in Natural Language Processing. [find](https://scholar.google.com/scholar?q=Liying+Cheng%2C+Xingxuan+Li%2C+and+Lidong+Bing%2E+2023%2E+Is+GPT%2D4+a+good+data+analyst%3F+In+The+2023+Conference+on+Empirical+Methods+in+Natural+Language+Processing%2E)
7. Steve Chien and Kiri L. Wagstaff. 2017. Robotic space exploration agents. Science Robotics, 2(7):eaan4831. [find](https://scholar.google.com/scholar?q=Steve+Chien+and+Kiri+L%2E+Wagstaff%2E+2017%2E+Robotic+space+exploration+agents%2E+Science+Robotics%2C+2%287%29%3Aeaan4831%2E)
8. Code Interpreter API Contributors. 2023. Code interpreter api. [https://github.com/shroominic/](https://github.com/shroominic/) codeinterpreter-api. GitHub repository. [↗](https://github.com/shroominic/)
9. Sumanth Dathathri, Andrea Madotto, Janice Lan, Jane Hung, Eric Frank, Piero Molino, Jason Yosinski, and Rosanne Liu. 2020. [Plug and play language models: A simple approach to controlled text generation](https://md.research.elamur.ai/free/en/papers/dathathri-2019-plug-play-language-models-simple/). In International Conference on Learning Representations.
10. Siyuan Guo, Cheng Deng, Ying Wen, Hechang Chen, Yi Chang, and Jun Wang. 2024. DS-agent: automated data science by empowering large language models with case-based reasoning. In Proceedings of the 41st International Conference on Machine Learning, ICML’24. [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+2024%2E+DS%2Dagent%3A+automated+data+science+by+empowering+large+language+models+with+case%2Dbased+reasoning%2E+In+Proceedings+of+the+41st)
11. Guy Hacohen and Daphna Weinshall. 2019. On the power of curriculum learning in training deep networks. In Proceedings of the 36th International Conference on Machine Learning, volume 97 of Proceedings of Machine Learning Research, pages 2535– 2544. PMLR. [find](https://scholar.google.com/scholar?q=Guy+Hacohen+and+Daphna+Weinshall%2E+2019%2E+On+the+power+of+curriculum+learning+in+training+deep+networks%2E+In+Proceedings+of+the+36th+International+Conference+on+Machine+Learning%2C+volume+97+of+Proceedings)
12. J. B. Heaton, N. G. Polson, and J. H. Witte. 2017. Deep learning for finance: deep portfolios. Applied Stochastic Models in Business and Industry, 33(1):3– 12. [find](https://scholar.google.com/scholar?q=J%2E+B%2E+Heaton%2C+N%2E+G%2E+Polson%2C+and+J%2E+H%2E+Witte%2E+2017%2E+Deep+learning+for+finance%3A+deep+portfolios%2E+Applied+Stochastic+Models+in+Business+and+Industry%2C+33%281%29%3A3%E2%80%93+12%2E)
13. Sirui Hong, Yizhang Lin, Bang Liu, Bangbang Liu, Binhao Wu, Ceyao Zhang, Danyang Li, Jiaqi Chen, Jiayi Zhang, Jinlin Wang, Li Zhang, Lingyao Zhang, Min Yang, Mingchen Zhuge, Taicheng Guo, Tuo Zhou, Wei Tao, Robert Tang, Xiangtao Lu, and 9 others. 2025. [Data interpreter: An LLM agent for data science](https://md.research.elamur.ai/free/en/papers/hong-2025-data-interpreter-llm-agent-data/)…
14. Sirui Hong, Mingchen Zhuge, Jonathan Chen, Xiawu Zheng, Yuheng Cheng, Jinlin Wang, Ceyao Zhang, Zili Wang, Steven Ka Shing Yau, Zijuan Lin, Liyang Zhou, Chenyu Ran, Lingfeng Xiao, Chenglin Wu, and Jürgen Schmidhuber. 2024. [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 T…
15. Zhengyao Jiang, Dominik Schmidt, Dhruv Srikanth, Dixing Xu, Ian Kaplan, Deniss Jacenko, and Yuxiang Wu. 2025. AIDE: Ai-driven exploration in the space of code. [find](https://scholar.google.com/scholar?q=Zhengyao+Jiang%2C+Dominik+Schmidt%2C+Dhruv+Srikanth%2C+Dixing+Xu%2C+Ian+Kaplan%2C+Deniss+Jacenko%2C+and+Yuxiang+Wu%2E+2025%2E+AIDE%3A+Ai%2Ddriven+exploration+in+the+space+of+code%2E)
16. JupyterLab. 2023. Jupyter AI. [https://github.com/](https://github.com/) jupyterlab/jupyter-ai. [↗](https://github.com/)
17. Akbir Khan, John Hughes, Dan Valentine, Laura Ruis, Kshitij Sachan, Ansh Radhakrishnan, Edward Grefenstette, Samuel R. Bowman, Tim Rocktäschel, and Ethan Perez. 2024. Debating with more persuasive llms leads to more truthful answers. In Proceedings of the 41st International Conference on Machine Lea… [find](https://scholar.google.com/scholar?q=Akbir+Khan%2C+John+Hughes%2C+Dan+Valentine%2C+Laura+Ruis%2C+Kshitij+Sachan%2C+Ansh+Radhakrishnan%2C+Edward+Grefenstette%2C+Samuel+R%2E+Bowman%2C+Tim+Rockt%C3%A4schel%2C+and+Ethan+Perez%2E+2024%2E+Debating+with+more+persuasive+llm)
18. Lucy Xiaoyang Shi, Yunfan Jiang, Jake Grigsby, Linxi Jim Fan, and Yuke Zhu. 2023. Cross-episodic curriculum for transformer agents. In Proceedings of the 37th International Conference on Neural Information Processing Systems, NIPS ’23. [find](https://scholar.google.com/scholar?q=Lucy+Xiaoyang+Shi%2C+Yunfan+Jiang%2C+Jake+Grigsby%2C+Linxi+Jim+Fan%2C+and+Yuke+Zhu%2E+2023%2E+Cross%2Depisodic+curriculum+for+transformer+agents%2E+In+Proceedings+of+the+37th+International+Conference+on+Neural+Inform)
19. Noah Shinn, Federico Cassano, Ashwin Gopinath, Karthik R 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/).
20. Haoran Sun, Lixin Liu, Junjie Li, Fengyu Wang, Baohua Dong, Ran Lin, and Ruohui Huang. 2024. [Conifer: Improving complex constrained instruction-following ability of large language models](https://md.research.elamur.ai/free/en/papers/sun-2024-conifer-improving-complex-constrained-instruction/). arxiv preprint arXiv:2404.02823.
21. Yuhang Lai, Chengxi Li, Yiming Wang, Tianyi Zhang, Ruiqi Zhong, Luke Zettlemoyer, Wen-tau Yih, Daniel Fried, Sida Wang, and Tao Yu. 2023. DS-1000: a natural and reliable benchmark for data science code generation. In Proceedings of the 40th International Conference on Machine Learning, ICML’23. [find](https://scholar.google.com/scholar?q=Yuhang+Lai%2C+Chengxi+Li%2C+Yiming+Wang%2C+Tianyi+Zhang%2C+Ruiqi+Zhong%2C+Luke+Zettlemoyer%2C+Wen%2Dtau+Yih%2C+Daniel+Fried%2C+Sida+Wang%2C+and+Tao+Yu%2E+2023%2E+DS%2D1000%3A+a+natural+and+reliable+benchmark+for+data+science+cod)
22. Guohao Li, Hasan Abed Al Kader Hammoud, Hani Itani, Dmitrii Khizbullin, and Bernard Ghanem. 2023. [CAMEL: Communicative agents for ”mind” exploration of large language model society](https://md.research.elamur.ai/free/en/papers/li-2023-camel-communicative-agents-mind/). In Thirty-seventh Conference on Neural Information Processing Systems.
23. Xiao Liu, Zirui Wu, Xueqing Wu, Pan Lu, Kai-Wei Chang, and Yansong Feng. 2024a. Are LLMs capable of data-based statistical and causal reasoning? benchmarking advanced quantitative reasoning with data. In Findings of the Association for Computational Linguistics: ACL 2024, pages 9215–9235, Bangkok, T… [find](https://scholar.google.com/scholar?q=Xiao+Liu%2C+Zirui+Wu%2C+Xueqing+Wu%2C+Pan+Lu%2C+Kai%2DWei+Chang%2C+and+Yansong+Feng%2E+2024a%2E+Are+LLMs+capable+of+data%2Dbased+statistical+and+causal+reasoning%3F+benchmarking+advanced+quantitative+reasoning+with+data%2E)
24. Guanzhi Wang, Yuqi Xie, Yunfan Jiang, Ajay Mandlekar, Chaowei Xiao, Yuke Zhu, Linxi Fan, and Anima Anandkumar. 2024a. Voyager: An open-ended embodied agent with large language models. Transactions on Machine Learning Research. [find](https://scholar.google.com/scholar?q=Guanzhi+Wang%2C+Yuqi+Xie%2C+Yunfan+Jiang%2C+Ajay+Mandlekar%2C+Chaowei+Xiao%2C+Yuke+Zhu%2C+Linxi+Fan%2C+and+Anima+Anandkumar%2E+2024a%2E+Voyager%3A+An+open%2Dended+embodied+agent+with+large+language+models%2E+Transactions+on+)
25. Haotian Wang, Xiyuan Du, Weijiang Yu, Qianglong Chen, Kun Zhu, Zheng Chu, Lian Yan, and Yi Guan. 2024b. Learning to break: Knowledge-enhanced reasoning in multi-agent debate system. Preprint, arXiv:2312.04854. — [arXiv:2312.04854](https://arxiv.org/abs/2312.04854) [find](https://scholar.google.com/scholar?q=Haotian+Wang%2C+Xiyuan+Du%2C+Weijiang+Yu%2C+Qianglong+Chen%2C+Kun+Zhu%2C+Zheng+Chu%2C+Lian+Yan%2C+and+Yi+Guan%2E+2024b%2E+Learning+to+break%3A+Knowledge%2Denhanced+reasoning+in+multi%2Dagent+debate+system%2E+Preprint%2C+arXiv%3A23)
26. Xin Wang, Yudong Chen, and Wenwu Zhu. 2022. A Survey on Curriculum Learning . IEEE Transactions on Pattern Analysis & Machine Intelligence, 44(09):4555–4576. [find](https://scholar.google.com/scholar?q=Xin+Wang%2C+Yudong+Chen%2C+and+Wenwu+Zhu%2E+2022%2E+A+Survey+on+Curriculum+Learning+%2E+IEEE+Transactions+on+Pattern+Analysis+%26+Machine+Intelligence%2C+44%2809%29%3A4555%E2%80%934576%2E)
27. Yinpeng Liu, Jiawei Liu, Xiang Shi, Qikai Cheng, Yong Huang, and Wei Lu. 2024b. Let’s learn step by step: Enhancing in-context learning ability with curriculum learning. Preprint, arXiv:2402.10738. — [arXiv:2402.10738](https://arxiv.org/abs/2402.10738) [find](https://scholar.google.com/scholar?q=Yinpeng+Liu%2C+Jiawei+Liu%2C+Xiang+Shi%2C+Qikai+Cheng%2C+Yong+Huang%2C+and+Wei+Lu%2E+2024b%2E+Let%E2%80%99s+learn+step+by+step%3A+Enhancing+in%2Dcontext+learning+ability+with+curriculum+learning%2E+Preprint%2C+arXiv%3A2402%2E10738%2E+%E2%80%94+)
28. Yiru Wang, Weihao Gan, Jie Yang, Wei Wu, and Junjie Yan. 2019. Dynamic curriculum learning for imbalanced data classification. In 2019 IEEE/CVF International Conference on Computer Vision (ICCV), pages 5016–5025. [find](https://scholar.google.com/scholar?q=Yiru+Wang%2C+Weihao+Gan%2C+Jie+Yang%2C+Wei+Wu%2C+and+Junjie+Yan%2E+2019%2E+Dynamic+curriculum+learning+for+imbalanced+data+classification%2E+In+2019+IEEE%2FCVF+International+Conference+on+Computer+Vision+%28ICCV%29%2C+page)
29. Jianqiao Lu, Wanjun Zhong, Yufei Wang, Zhijiang Guo, Qi Zhu, Wenyong Huang, Yanlin Wang, Fei Mi, Baojun Wang, Yasheng Wang, Lifeng Shang, Xin Jiang, and Qun Liu. 2024. YODA: Teacher-student progressive learning for language models. Preprint, arXiv:2401.15670. — [arXiv:2401.15670](https://arxiv.org/abs/2401.15670) [find](https://scholar.google.com/scholar?q=Jianqiao+Lu%2C+Wanjun+Zhong%2C+Yufei+Wang%2C+Zhijiang+Guo%2C+Qi+Zhu%2C+Wenyong+Huang%2C+Yanlin+Wang%2C+Fei+Mi%2C+Baojun+Wang%2C+Yasheng+Wang%2C+Lifeng+Shang%2C+Xin+Jiang%2C+and+Qun+Liu%2E+2024%2E+YODA%3A+Teacher%2Dstudent+progressiv)
30. Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, brian ichter, Fei Xia, Ed H. Chi, Quoc V Le, and Denny Zhou. 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/). In Advances in Neural Information Processing Systems.
31. Riccardo Miotto, Fei Wang, Shuang Wang, Xiaoqian Jiang, and Joel T Dudley. 2018. Deep learning for healthcare: review, opportunities and challenges. Briefings in Bioinformatics, 19(6):1236–1246. [find](https://scholar.google.com/scholar?q=Riccardo+Miotto%2C+Fei+Wang%2C+Shuang+Wang%2C+Xiaoqian+Jiang%2C+and+Joel+T+Dudley%2E+2018%2E+Deep+learning+for+healthcare%3A+review%2C+opportunities+and+challenges%2E+Briefings+in+Bioinformatics%2C+19%286%29%3A1236%E2%80%931246%2E)
32. Emmanouil Antonios Platanios, Otilia Stretcu, Graham Neubig, Barnabas Poczos, and Tom Mitchell. 2019. Competence-based curriculum learning for neural machine translation. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Langu… [find](https://scholar.google.com/scholar?q=Emmanouil+Antonios+Platanios%2C+Otilia+Stretcu%2C+Graham+Neubig%2C+Barnabas+Poczos%2C+and+Tom+Mitchell%2E+2019%2E+Competence%2Dbased+curriculum+learning+for+neural+machine+translation%2E+In+Proceedings+of+the+2019+Co)
33. Rémy Portelas, Cédric Colas, Lilian Weng, Katja Hofmann, and Pierre-Yves Oudeyer. 2021. Automatic curriculum learning for deep rl: a short survey. In Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence, IJCAI’20. [find](https://scholar.google.com/scholar?q=R%C3%A9my+Portelas%2C+C%C3%A9dric+Colas%2C+Lilian+Weng%2C+Katja+Hofmann%2C+and+Pierre%2DYves+Oudeyer%2E+2021%2E+Automatic+curriculum+learning+for+deep+rl%3A+a+short+survey%2E+In+Proceedings+of+the+Twenty%2DNinth+International+Join)
34. Yunchao Wei, Xiaodan Liang, Yunpeng Chen, Xiaohui Shen, Ming-Ming Cheng, Jiashi Feng, Yao Zhao, and Shuicheng Yan. 2017. STC: A simple to complex framework for weakly-supervised semantic segmentation. IEEE Trans. Pattern Anal. Mach. Intell., 39(11):2314–2320. [find](https://scholar.google.com/scholar?q=Yunchao+Wei%2C+Xiaodan+Liang%2C+Yunpeng+Chen%2C+Xiaohui+Shen%2C+Ming%2DMing+Cheng%2C+Jiashi+Feng%2C+Yao+Zhao%2C+and+Shuicheng+Yan%2E+2017%2E+STC%3A+A+simple+to+complex+framework+for+weakly%2Dsupervised+semantic+segmentation%2E)
35. Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik R Narasimhan, and Yuan Cao. 2023. [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.
36. Lei Zhang, Yuge Zhang, Kan Ren, Dongsheng Li, and Yuqing Yang. 2024a. [MLCopilot: Unleashing the power of large language models in solving machine learning tasks](https://md.research.elamur.ai/free/en/papers/zhang-2024-mlcopilot-unleashing-power-large-language/). In Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), pa…
37. Wenqi Zhang, Yongliang Shen, Weiming Lu, and Yueting Zhuang. 2024b. Data-Copilot: Bridging billions of data and humans with autonomous workflow. In ICLR 2024 Workshop on Large Language Model (LLM) Agents. [find](https://scholar.google.com/scholar?q=Wenqi+Zhang%2C+Yongliang+Shen%2C+Weiming+Lu%2C+and+Yueting+Zhuang%2E+2024b%2E+Data%2DCopilot%3A+Bridging+billions+of+data+and+humans+with+autonomous+workflow%2E+In+ICLR+2024+Workshop+on+Large+Language+Model+%28LLM%29+Age)
38. Yuge Zhang, Qiyang Jiang, XingyuHan XingyuHan, Nan Chen, Yuqing Yang, and Kan Ren. 2024c. Benchmarking data science agents. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 5677–5700, Bangkok, Thailand. Association for Computat… [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+2024c%2E+Benchmarking+data+science+agents%2E+In+Proceedings+of+the+62nd+Annual+Meeting+of+the+Association+for+Computation)

*Updated 1 November 2026*