---
title: "Automatic Slide Updating with User-Defined Dynamic Templates"
description: "The authors define a new task: refreshing a user-supplied deck according to a natural-language instruction while keeping its… 31 references."
authors: ["Kun Zhou", "Jiakai He", "Wenmian Yang", "Zhensheng Wang", "Yiquan Zhang", "Weijia Jia"]
year: 2026
venue: "Findings of the Association for Computational Linguistics: ACL 2026"
source: "https://aclanthology.org/2026.findings-acl.909/"
doi: "10.18653/v1/2026.findings-acl.909"
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/zhou-2026-automatic-slide-updating-user-defined/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/zhou-2026-automatic-slide-updating-user-defined/)

[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/23/) / Automatic Slide Updating with User-Defined Dynamic Templates and Natural Language Instructions

# Automatic Slide Updating with User-Defined Dynamic Templates and Natural Language Instructions

**Authors:** [Kun Zhou](https://md.research.elamur.ai/free/en/authors/kun-zhou/), Jiakai He, [Wenmian Yang](https://md.research.elamur.ai/free/en/authors/wenmian-yang/), [Zhensheng Wang](https://md.research.elamur.ai/free/en/authors/zhensheng-wang/), [Yiquan Zhang](https://md.research.elamur.ai/free/en/authors/yiquan-zhang/) and [Weijia Jia](https://md.research.elamur.ai/free/en/authors/weijia-jia/) · **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.909/) · [PDF](https://aclanthology.org/2026.findings-acl.909.pdf) · [DOI 10.18653/v1/2026.findings-acl.909](https://doi.org/10.18653/v1/2026.findings-acl.909) · [OpenAlex](https://openalex.org/W7166811033)

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

## Summary
Recurring business reports, such as weekly or quarterly decks, often keep the same structure and change only their numbers and conclusions. Updating them by hand is slow repetitive work. Earlier automation mostly pours content into rigid predefined templates and cannot work with arbitrary decks that users have designed themselves. The authors define a new task: refreshing a user-supplied deck according to a natural-language instruction while keeping its layout and style intact. To support this task, they release DynaSlide, a benchmark built on Chinese real-estate transaction data stored in PostgreSQL. They also propose SlideAgent, a baseline in which an LLM acts as controller. SlideAgent parses slides into a hierarchical element representation, maps instructions to data queries and document edits, and calls tools for computation, chart re-rendering and summary rewriting. Experiments show that performance depends strongly on model capability, and closed-source models beat open-weight ones. Most errors come from mistakes compounding along the pipeline and from imprecise numbers in rewritten summaries. The resource gives a first testbed for template-preserving, data-consistent report updating.

## Key points
- DynaSlide contains 20,036 triples (source slide, instruction, target slide). All are tied to one shared PostgreSQL database built from 1.79 million cleaned housing transactions in Beijing, Guangzhou and Shenzhen (2020–2024). The data are split into six tables by city and by new versus resale market.
- Slides are composed of four element types: Title, Table, Chart and Summary. They come from six expert-chosen themes and 34 sub-templates, with executable metadata (SQL templates, statistical functions, layout) stored in YAML. All slide text is in English.
- SlideAgent works in two stages: slide parsing/representation, then instruction-driven content synchronization with tool use. It keeps structured action logs that support error analysis.
- The evaluation protocols are end-to-end and module-level. On 500 sampled cases, results on human-authored slides follow trends similar to the template-generated ones, which suggests the benchmark measures general ability rather than template matching.
- Limitations: the benchmark covers a single domain (real estate), uses curated rather than wild slides, assumes an existing structured database, and ignores decorative graphics.

*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

- [Beijing Normal University](https://md.research.elamur.ai/free/en/universities/beijing-normal-university/) — University, Beijing, China · 22 works · 3,177 citations
- [Beijing Normal-Hong Kong Baptist University](https://md.research.elamur.ai/free/en/universities/beijing-normal-hong-kong-baptist-university/) — University, Zhuhai, China · 5 works · 536 citations
- [Beijing Normal University, Zhuhai](https://md.research.elamur.ai/free/en/universities/beijing-normal-university-zhuhai/) — University, Zhuhai, China · 4 works

📚 Shelves (5): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 17,965 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 17,450 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 17,296 works · [👁️ Computer Vision and Pattern Recognition](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · 3,486 works

## Cite

Cite as: Kun Zhou, Jiakai He, Wenmian Yang, Zhensheng Wang, Yiquan Zhang and Weijia Jia. 2026. Automatic Slide Updating with User-Defined Dynamic Templates and Natural Language Instructions. 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{zhou2026automatic,
  title = {{Automatic Slide Updating with User-Defined Dynamic Templates and Natural Language Instructions}},
  author = {Kun Zhou, Jiakai He, Wenmian Yang, Zhensheng Wang, Yiquan Zhang and Weijia Jia},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.909},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.909}
}
```

- [← previous Automatic scoring of ENEM essays: an empirical study of linguistic and contextual representations](https://md.research.elamur.ai/free/en/papers/matos-2026-avaliacao-automatica-de-redacoes-do/)
- [next → Automatic Speech Recognition for Child Reading: A Phonemic Approach using Isolated Words in Brazilian Portuguese](https://md.research.elamur.ai/free/en/papers/rodrigues-2026-automatic-speech-recognition-child-reading/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/23/)

## References

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

1. Sambaran Bandyopadhyay, Himanshu Maheshwari, Anandhavelu Natarajan, and Apoorv Saxena. 2024. Enhancing presentation slide generation by llms with a multi-staged end-to-end approach. arXiv preprint arXiv:2406.06556. [find](https://scholar.google.com/scholar?q=Sambaran+Bandyopadhyay%2C+Himanshu+Maheshwari%2C+Anandhavelu+Natarajan%2C+and+Apoorv+Saxena%2E+2024%2E+Enhancing+presentation+slide+generation+by+llms+with+a+multi%2Dstaged+end%2Dto%2Dend+approach%2E+arXiv+preprint+arX)
2. Qiguang Chen, Libo Qin, Jinhao Liu, Dengyun Peng, Jiannan Guan, Peng Wang, Mengkang Hu, Yuhang Zhou, Te Gao, and Wanxiang Che. 2025. [Towards reasoning era: A survey of long chain-of-thought for reasoning large language models](https://md.research.elamur.ai/free/en/papers/chen-2025-towards-reasoning-era-survey-long/). arXiv preprint arXiv:2503.09567.
3. Yew Ken Chia, Liying Cheng, Hou Pong Chan, Maojia Song, Chaoqun Liu, Mahani Aljunied, Soujanya Poria, and Lidong Bing. 2025. [M-longdoc: A benchmark for multimodal super-long document understanding and a retrieval-aware tuning framework](https://md.research.elamur.ai/free/en/papers/chia-2025-m-longdoc-benchmark-multimodal-super/). In Proceedings of the 2025 Conference on Empirical Methods in N…
4. Xuanwen Ding, Jie Zhou, Liang Dou, Qin Chen, Yuanbin Wu, Arlene Chen, and Liang He. 2024. Boosting large language models with continual learning for aspect-based sentiment analysis. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 4367–4377. [find](https://scholar.google.com/scholar?q=Xuanwen+Ding%2C+Jie+Zhou%2C+Liang+Dou%2C+Qin+Chen%2C+Yuanbin+Wu%2C+Arlene+Chen%2C+and+Liang+He%2E+2024%2E+Boosting+large+language+models+with+continual+learning+for+aspect%2Dbased+sentiment+analysis%2E+In+Findings+of+the)
5. Ali Farhadi, Joseph Redmon, and 1 others. 2018. Yolov3: An incremental improvement. In In Proceedings of the Computer Vision and Pattern Recognition Conference, pages 1–6. [find](https://scholar.google.com/scholar?q=Ali+Farhadi%2C+Joseph+Redmon%2C+and+1+others%2E+2018%2E+Yolov3%3A+An+incremental+improvement%2E+In+In+Proceedings+of+the+Computer+Vision+and+Pattern+Recognition+Conference%2C+pages+1%E2%80%936%2E)
6. Manuel Faysse, Hugues Sibille, Tony Wu, Bilel Omrani, Gautier Viaud, Céline Hudelot, and Pierre Colombo. 2024. [Colpali: Efficient document retrieval with vision language models](https://md.research.elamur.ai/free/en/papers/faysse-2024-colpali-efficient-document-retrieval-vision/). arXiv preprint arXiv:2407.01449.
7. Tsu-Jui Fu, William Yang Wang, Daniel McDuff, and Yale Song. 2022. Doc2ppt: Automatic presentation slides generation from scientific documents. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 36, pages 634–642. [find](https://scholar.google.com/scholar?q=Tsu%2DJui+Fu%2C+William+Yang+Wang%2C+Daniel+McDuff%2C+and+Yale+Song%2E+2022%2E+Doc2ppt%3A+Automatic+presentation+slides+generation+from+scientific+documents%2E+In+Proceedings+of+the+AAAI+Conference+on+Artificial+Inte)
8. Jiaxin Ge, Zora Zhiruo Wang, Xuhui Zhou, Yi-Hao Peng, Sanjay Subramanian, Qinyue Tan, Maarten Sap, Alane Suhr, Daniel Fried, Graham Neubig, and 1 others. 2025. Autopresent: Designing structured visuals from scratch. In Proceedings of the Computer Vision and Pattern Recognition Conference, pages 2902… [find](https://scholar.google.com/scholar?q=Jiaxin+Ge%2C+Zora+Zhiruo+Wang%2C+Xuhui+Zhou%2C+Yi%2DHao+Peng%2C+Sanjay+Subramanian%2C+Qinyue+Tan%2C+Maarten+Sap%2C+Alane+Suhr%2C+Daniel+Fried%2C+Graham+Neubig%2C+and+1+others%2E+2025%2E+Autopresent%3A+Designing+structured+visual)
9. Keshav Kumar and Ravindranath Chowdary. 2024. Slidespawn: An automatic slides generation system for research publications. arXiv preprint arXiv:2411.17719. — [arXiv:2411.17719](https://arxiv.org/abs/2411.17719) [find](https://scholar.google.com/scholar?q=Keshav+Kumar+and+Ravindranath+Chowdary%2E+2024%2E+Slidespawn%3A+An+automatic+slides+generation+system+for+research+publications%2E+arXiv+preprint+arXiv%3A2411%2E17719%2E+%E2%80%94+%5BarXiv%3A2411%2E17719%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2)
10. Wenhui Liao, Jiapeng Wang, Hongliang Li, Chengyu Wang, Jun Huang, and Lianwen Jin. 2025. Doclayllm: An efficient multi-modal extension of large language models for text-rich document understanding. In Proceedings of the Computer Vision and Pattern Recognition Conference, pages 4038–4049. [find](https://scholar.google.com/scholar?q=Wenhui+Liao%2C+Jiapeng+Wang%2C+Hongliang+Li%2C+Chengyu+Wang%2C+Jun+Huang%2C+and+Lianwen+Jin%2E+2025%2E+Doclayllm%3A+An+efficient+multi%2Dmodal+extension+of+large+language+models+for+text%2Drich+document+understanding%2E+In)
11. Nikolaos Livathinos, Christoph Auer, Maksym Lysak, Ahmed Nassar, Michele Dolfi, Panos Vagenas, Cesar Berrospi Ramis, Matteo Omenetti, Kasper Dinkla, Yusik Kim, and 1 others. 2025. Docling: An efficient open-source toolkit for ai-driven document conversion. arXiv preprint arXiv:2501.17887. — [arXiv:2501.17887](https://arxiv.org/abs/2501.17887) [find](https://scholar.google.com/scholar?q=Nikolaos+Livathinos%2C+Christoph+Auer%2C+Maksym+Lysak%2C+Ahmed+Nassar%2C+Michele+Dolfi%2C+Panos+Vagenas%2C+Cesar+Berrospi+Ramis%2C+Matteo+Omenetti%2C+Kasper+Dinkla%2C+Yusik+Kim%2C+and+1+others%2E+2025%2E+Docling%3A+An+efficien)
12. Boammani Aser Lompo and Marc Haraoui. 2025. Visual-tableqa: Open-domain benchmark for reasoning over table images. arXiv preprint arXiv:2509.07966. — [arXiv:2509.07966](https://arxiv.org/abs/2509.07966) [find](https://scholar.google.com/scholar?q=Boammani+Aser+Lompo+and+Marc+Haraoui%2E+2025%2E+Visual%2Dtableqa%3A+Open%2Ddomain+benchmark+for+reasoning+over+table+images%2E+arXiv+preprint+arXiv%3A2509%2E07966%2E+%E2%80%94+%5BarXiv%3A2509%2E07966%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2509%2E0796)
13. Ishani Mondal, S Shwetha, Anandhavelu Natarajan, Aparna Garimella, Sambaran Bandyopadhyay, and Jordan Boyd-Graber. 2024. Presentations by the humans and for the humans: Harnessing llms for generating persona-aware slides from documents. In Proceedings of the 18th Conference of the European Chapter o… [find](https://scholar.google.com/scholar?q=Ishani+Mondal%2C+S+Shwetha%2C+Anandhavelu+Natarajan%2C+Aparna+Garimella%2C+Sambaran+Bandyopadhyay%2C+and+Jordan+Boyd%2DGraber%2E+2024%2E+Presentations+by+the+humans+and+for+the+humans%3A+Harnessing+llms+for+generating+)
14. Linke Ouyang, Yuan Qu, Hongbin Zhou, Jiawei Zhu, Rui Zhang, Qunshu Lin, Bin Wang, Zhiyuan Zhao, Man Jiang, Xiaomeng Zhao, and 1 others. 2025. Omnidocbench: Benchmarking diverse pdf document parsing with comprehensive annotations. In Proceedings of the Computer Vision and Pattern Recognition Conferen… [find](https://scholar.google.com/scholar?q=Linke+Ouyang%2C+Yuan+Qu%2C+Hongbin+Zhou%2C+Jiawei+Zhu%2C+Rui+Zhang%2C+Qunshu+Lin%2C+Bin+Wang%2C+Zhiyuan+Zhao%2C+Man+Jiang%2C+Xiaomeng+Zhao%2C+and+1+others%2E+2025%2E+Omnidocbench%3A+Benchmarking+diverse+pdf+document+parsing+wi)
15. Wei Pang, Kevin Qinghong Lin, Xiangru Jian, Xi He, and Philip Torr. 2025. Paper2poster: Towards multimodal poster automation from scientific papers. arXiv preprint arXiv:2505.21497. — [arXiv:2505.21497](https://arxiv.org/abs/2505.21497) [find](https://scholar.google.com/scholar?q=Wei+Pang%2C+Kevin+Qinghong+Lin%2C+Xiangru+Jian%2C+Xi+He%2C+and+Philip+Torr%2E+2025%2E+Paper2poster%3A+Towards+multimodal+poster+automation+from+scientific+papers%2E+arXiv+preprint+arXiv%3A2505%2E21497%2E+%E2%80%94+%5BarXiv%3A2505%2E2149)
16. Libo Qin, Qiguang Chen, Xiachong Feng, Yang Wu, Yongheng Zhang, Yinghui Li, Min Li, Wanxiang Che, and Philip S Yu. 2026. Large language models meet nlp: A survey. Frontiers of Computer Science, 20(11):2011361. [find](https://scholar.google.com/scholar?q=Libo+Qin%2C+Qiguang+Chen%2C+Xiachong+Feng%2C+Yang+Wu%2C+Yongheng+Zhang%2C+Yinghui+Li%2C+Min+Li%2C+Wanxiang+Che%2C+and+Philip+S+Yu%2E+2026%2E+Large+language+models+meet+nlp%3A+A+survey%2E+Frontiers+of+Computer+Science%2C+20%2811%29)
17. Libo Qin, Zhouyang Li, Wanxiang Che, Minheng Ni, and Ting Liu. 2021. [Co-gat: A co-interactive graph attention network for joint dialog act recognition and sentiment classification](https://md.research.elamur.ai/free/en/papers/qin-2020-co-gat-co-interactive-graph/). In Proceedings of the AAAI conference on artificial intelligence, volume 35, pages 13709–13717.
18. Timo Schick, Jane Dwivedi-Yu, Roberto Dessì, Roberta Raileanu, Maria Lomeli, Eric Hambro, Luke Zettlemoyer, Nicola Cancedda, and Thomas Scialom. 2023. [Toolformer: Language models can teach themselves to use tools](https://md.research.elamur.ai/free/en/papers/schick-2023-toolformer-language-models-can-teach/). Advances in Neural Information Processing Systems, 36:68539–68551.
19. Zejiang Shen, Kyle Lo, Lucy Lu Wang, Bailey Kuehl, Daniel S Weld, and Doug Downey. 2022. Vila: Improving structured content extraction from scientific pdfs using visual layout groups. Transactions of the Association for Computational Linguistics, 10:376– 392. [find](https://scholar.google.com/scholar?q=Zejiang+Shen%2C+Kyle+Lo%2C+Lucy+Lu+Wang%2C+Bailey+Kuehl%2C+Daniel+S+Weld%2C+and+Doug+Downey%2E+2022%2E+Vila%3A+Improving+structured+content+extraction+from+scientific+pdfs+using+visual+layout+groups%2E+Transactions+of+)
20. Jinwei Su, Yinghui Xia, Qizhen Lan, Xinyuan Song, Yang Jingsong, Lewei He, and Tianyu Shi. 2025. Difficulty-aware agent orchestration in llm-powered workflows. arXiv e-prints, pages arXiv–2509. [find](https://scholar.google.com/scholar?q=Jinwei+Su%2C+Yinghui+Xia%2C+Qizhen+Lan%2C+Xinyuan+Song%2C+Yang+Jingsong%2C+Lewei+He%2C+and+Tianyu+Shi%2E+2025%2E+Difficulty%2Daware+agent+orchestration+in+llm%2Dpowered+workflows%2E+arXiv+e%2Dprints%2C+pages+arXiv%E2%80%932509%2E)
21. Lin Long, Rui Wang, Ruixuan Xiao, Junbo Zhao, Xiao Ding, Gang Chen, and Haobo Wang. 2024. [On llms-driven synthetic data generation, curation, and evaluation: A survey](https://md.research.elamur.ai/free/en/papers/long-2024-llms-driven-synthetic-data-generation/). arXiv preprint arXiv:2406.15126.
22. Abhigya Verma, Sriram Puttagunta, Seganrasan Subramanian, and Sravan Ramachandran. 2025. Graft: Graph and table reasoning for textual alignment–a benchmark for structured instruction following and visual reasoning. arXiv preprint arXiv:2508.15690. [find](https://scholar.google.com/scholar?q=Abhigya+Verma%2C+Sriram+Puttagunta%2C+Seganrasan+Subramanian%2C+and+Sravan+Ramachandran%2E+2025%2E+Graft%3A+Graph+and+table+reasoning+for+textual+alignment%E2%80%93a+benchmark+for+structured+instruction+following+and+vis)
23. Ahmed Masry, Megh Thakkar, Aayush Bajaj, Aaryaman Kartha, Enamul Hoque, and Shafiq Joty. 2025. Chartgemma: Visual instruction-tuning for chart reasoning in the wild. In Proceedings of the 31st International Conference on Computational Linguistics: Industry Track, pages 625–643. [find](https://scholar.google.com/scholar?q=Ahmed+Masry%2C+Megh+Thakkar%2C+Aayush+Bajaj%2C+Aaryaman+Kartha%2C+Enamul+Hoque%2C+and+Shafiq+Joty%2E+2025%2E+Chartgemma%3A+Visual+instruction%2Dtuning+for+chart+reasoning+in+the+wild%2E+In+Proceedings+of+the+31st+Interna)
24. Zhensheng Wang, Wenmian Yang, Kun Zhou, Yiquan Zhang, and Weijia Jia. 2025. Retqa: A large-scale open-domain tabular question answering dataset for real estate sector. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 39, pages 25452–25460. [find](https://scholar.google.com/scholar?q=Zhensheng+Wang%2C+Wenmian+Yang%2C+Kun+Zhou%2C+Yiquan+Zhang%2C+and+Weijia+Jia%2E+2025%2E+Retqa%3A+A+large%2Dscale+open%2Ddomain+tabular+question+answering+dataset+for+real+estate+sector%2E+In+Proceedings+of+the+AAAI+Confe)
25. Jeremy Warner, Amy Pavel, Tonya Nguyen, Maneesh Agrawala, and Bjoern Hartmann. 2023. Slidespecs: Automatic and interactive presentation feedback collation. In Proceedings of the 28th International Conference on Intelligent User Interfaces, pages 695– 709. [find](https://scholar.google.com/scholar?q=Jeremy+Warner%2C+Amy+Pavel%2C+Tonya+Nguyen%2C+Maneesh+Agrawala%2C+and+Bjoern+Hartmann%2E+2023%2E+Slidespecs%3A+Automatic+and+interactive+presentation+feedback+collation%2E+In+Proceedings+of+the+28th+International+Con)
26. Yuheng Yang, Wenjia Jiang, Yang Wang, Yiwei Wang, and Chi Zhang. 2025. Auto-slides: An interactive multi-agent system for creating and customizing research presentations. arXiv preprint arXiv:2509.11062. — [arXiv:2509.11062](https://arxiv.org/abs/2509.11062) [find](https://scholar.google.com/scholar?q=Yuheng+Yang%2C+Wenjia+Jiang%2C+Yang+Wang%2C+Yiwei+Wang%2C+and+Chi+Zhang%2E+2025%2E+Auto%2Dslides%3A+An+interactive+multi%2Dagent+system+for+creating+and+customizing+research+presentations%2E+arXiv+preprint+arXiv%3A2509%2E110)
27. Zhengyuan Yang, Linjie Li, Jianfeng Wang, Kevin Lin, Ehsan Azarnasab, Faisal Ahmed, Zicheng Liu, Ce Liu, Michael Zeng, and Lijuan Wang. 2023. [Mm-react: Prompting chatgpt for multimodal reasoning and action](https://md.research.elamur.ai/free/en/papers/yang-2023-mm-react-prompting-chatgpt-multimodal/). arXiv preprint arXiv:2303.11381.
28. 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.
29. Murong Yue, Wenlin Yao, Haitao Mi, Dian Yu, Ziyu Yao, and Dong Yu. 2024. Dots: Learning to reason dynamically in llms via optimal reasoning trajectories search. arXiv preprint arXiv:2410.03864. — [arXiv:2410.03864](https://arxiv.org/abs/2410.03864) [find](https://scholar.google.com/scholar?q=Murong+Yue%2C+Wenlin+Yao%2C+Haitao+Mi%2C+Dian+Yu%2C+Ziyu+Yao%2C+and+Dong+Yu%2E+2024%2E+Dots%3A+Learning+to+reason+dynamically+in+llms+via+optimal+reasoning+trajectories+search%2E+arXiv+preprint+arXiv%3A2410%2E03864%2E+%E2%80%94+%5BarX)
30. Zhuosheng Zhang, Kehai Chen, Rui Wang, Masao Utiyama, Eiichiro Sumita, Zuchao Li, and Hai Zhao. 2023. Universal multimodal representation for language understanding. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(7):9169– 9185. [find](https://scholar.google.com/scholar?q=Zhuosheng+Zhang%2C+Kehai+Chen%2C+Rui+Wang%2C+Masao+Utiyama%2C+Eiichiro+Sumita%2C+Zuchao+Li%2C+and+Hai+Zhao%2E+2023%2E+Universal+multimodal+representation+for+language+understanding%2E+IEEE+Transactions+on+Pattern+Analy)
31. Hao Zheng, Xinyan Guan, Hao Kong, Wenkai Zhang, Jia Zheng, Weixiang Zhou, Hongyu Lin, Yaojie Lu, Xianpei Han, and Le Sun. 2025. [Pptagent: Generating and evaluating presentations beyond text-to-slides](https://md.research.elamur.ai/free/en/papers/zheng-2025-pptagent-generating-evaluating-presentations-beyond/). In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 14…

*Updated 2 November 2026*