---
title: "LLM Multi-Agent Systems for Long Triple Set Data-to-Text"
description: "The authors build a new dataset of 669 DBpedia triple sets, each with 8 to 199 triples, drawn from People, Geography and… 33 references."
authors: ["Chinonso Cynthia Osuji", "Simon Mille", "Mark Andrade", "Jane Adkins", "Ornait O'Connell", "Elaine Uí Dhonnchadha", "Bláithín Heffernan", "Fírinne Nic an tSaoir", "Anya Belz", "Thiago Castro Ferreira", "Brian Davis"]
year: 2026
venue: "Findings of the Association for Computational Linguistics: ACL 2026"
source: "https://aclanthology.org/2026.findings-acl.1712/"
doi: "10.18653/v1/2026.findings-acl.1712"
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/osuji-2026-llm-multi-agent-systems-long/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/osuji-2026-llm-multi-agent-systems-long/)

[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/39/) / LLM Multi-Agent Systems for Long Triple Set Data-to-Text Generation

# LLM Multi-Agent Systems for Long Triple Set Data-to-Text Generation

**Authors:** Chinonso Cynthia Osuji, [Simon Mille](https://md.research.elamur.ai/free/en/authors/simon-mille/), [Mark Andrade](https://md.research.elamur.ai/free/en/authors/mark-andrade/), [Jane Adkins](https://md.research.elamur.ai/free/en/authors/jane-lauren-adkins/), [Ornait O'Connell](https://md.research.elamur.ai/free/en/authors/ornait-o-connell/), [Elaine Uí Dhonnchadha](https://md.research.elamur.ai/free/en/authors/elaine-ui-dhonnchadha/), Bláithín Heffernan, Fírinne Nic an tSaoir, [Anya Belz](https://md.research.elamur.ai/free/en/authors/anya-belz/), [Thiago Castro Ferreira](https://md.research.elamur.ai/free/en/authors/thiago-castro-ferreira/) and [Brian Davis](https://md.research.elamur.ai/free/en/authors/brian-davis/) · **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.1712/) · [PDF](https://aclanthology.org/2026.findings-acl.1712.pdf) · [DOI 10.18653/v1/2026.findings-acl.1712](https://doi.org/10.18653/v1/2026.findings-acl.1712) · [OpenAlex](https://openalex.org/W7166824759)

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

## Summary
Most data-to-text (D2T) benchmarks pair short inputs with outputs of a few dozen tokens. As a result, it is unclear how LLMs handle large structured inputs, where single-pass generation tends to omit or invent facts. The authors build a new dataset of 669 DBpedia triple sets, each with 8 to 199 triples, drawn from People, Geography and History entities. They also propose a modular multi-agent pipeline running on GPT 4.1. The work is divided among dedicated agents that decide the order of content, organise the text and produce the final wording, while an orchestrator coordinates them, a guardrail verifies their output and a finalizer refines it. This setup is compared with a single-worker multi-task variant and an end-to-end baseline, producing multi-paragraph texts in English and in low-resource Irish. Human raters judged the multi-agent outputs slightly more coherent in both languages, but the differences were not statistically significant. Agreement among human raters was modest for English and absent for Irish. LLM-as-a-judge scores barely tracked human scores. The work highlights how hard it is to evaluate long, multilingual NLG at scale.

## Key points
- **Dataset:** 900 randomly chosen DBpedia entities were filtered down to 669 inputs of 8–199 triples. Each input has at most one level of chained relations. Code, prompts and data are released on GitHub (NonsoCynthia/D2T-Longer-Text-Agent-System).
- **Systems compared:**
  - Mul: three workers (CO, TS, SR).
  - Sng: one worker with the same control loop.
  - e2e: a single GPT 4.1 call.
  
  All run at temperature 0. Only closed-source models (GPT, Claude) were usable because they are the only ones reliable in Irish.
- **Human evaluation:** 30 texts per system and language, two raters each, scored for Grammaticality, Fluency and Coherence. English inter-rater Pearson correlation was 0.3–0.5 and significant; Irish showed no significant agreement.
- **Human vs. LLM judging:** human–LLM correlation was weak and non-significant (around 0.1). This suggests LLM judges may be unreliable above roughly 100 triples. Semantic criteria such as No-Omissions were checked with LLM-as-a-judge plus truncation-based sanity tests.
- **Limitations:** high inference cost, no ablations, a small evaluation sample (system differences not significant under Tukey HSD), and some noisy DBpedia triples.

*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

- [Dublin City University](https://md.research.elamur.ai/free/en/universities/dublin-city-university/) — University, Dublin, Ireland · 72 works · 9,746 citations
- [Trinity College Dublin](https://md.research.elamur.ai/free/en/universities/trinity-college-dublin/) — University, Dublin, Ireland · 25 works · 1,313 citations
- [ADAPT - Centre for Digital Content Technology](https://md.research.elamur.ai/free/en/labs/adapt-centre-for-digital-content-technology/) — Research institute, Dublin, Ireland · 10 works · 976 citations

📚 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

🧭 Topics (1): [✍️ Text generation](https://md.research.elamur.ai/free/en/topics/text-generation/) · 214 works

## Cite

Cite as: Chinonso Cynthia Osuji, Simon Mille, Mark Andrade, Jane Adkins, Ornait O'Connell, Elaine Uí Dhonnchadha, Bláithín Heffernan, Fírinne Nic an tSaoir, Anya Belz, Thiago Castro Ferreira and Brian Davis. 2026. LLM Multi-Agent Systems for Long Triple Set Data-to-Text Generation. 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{osuji2026llm,
  title = {{LLM Multi-Agent Systems for Long Triple Set Data-to-Text Generation}},
  author = {Chinonso Cynthia Osuji, Simon Mille, Mark Andrade, Jane Adkins, Ornait O'Connell, Elaine Uí Dhonnchadha, Bláithín Heffernan, Fírinne Nic an tSaoir, Anya Belz, Thiago Castro Ferreira and Brian Davis},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.1712},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.1712}
}
```

- [← previous LLM Beliefs Are in Their Heads](https://md.research.elamur.ai/free/en/papers/mendozza-2026-llm-beliefs-are-their-heads/)
- [next → LLM Probe: Evaluating LLMs for Low-Resource Languages](https://md.research.elamur.ai/free/en/papers/teklehaymanot-2026-llm-probe-evaluating-llms-low/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/39/)

## References

33 references, 16 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Anja Belz, Eric Kow, Jette Viethen, and Albert Gatt. 2009. The GREC main subject reference generation challenge 2009: Overview and evaluation results. In Proceedings of the 2009 Workshop on Language Generation and Summarisation (UCNLG+Sum 2009), pages 79–87, Suntec, Singapore. Association for Comput… [find](https://scholar.google.com/scholar?q=Anja+Belz%2C+Eric+Kow%2C+Jette+Viethen%2C+and+Albert+Gatt%2E+2009%2E+The+GREC+main+subject+reference+generation+challenge+2009%3A+Overview+and+evaluation+results%2E+In+Proceedings+of+the+2009+Workshop+on+Language+G)
2. Anya Belz, Simon Mille, and Craig Thomson. 2025. The qcet taxonomy of standard quality criterion names and definitions for the evaluation of nlp systems. [find](https://scholar.google.com/scholar?q=Anya+Belz%2C+Simon+Mille%2C+and+Craig+Thomson%2E+2025%2E+The+qcet+taxonomy+of+standard+quality+criterion+names+and+definitions+for+the+evaluation+of+nlp+systems%2E)
3. Thiago Castro Ferreira, Claire Gardent, Nikolai Ilinykh, Chris van der Lee, Simon Mille, Diego Moussallem, and Anastasia Shimorina. 2020. [find](https://scholar.google.com/scholar?q=Thiago+Castro+Ferreira%2C+Claire+Gardent%2C+Nikolai+Ilinykh%2C+Chris+van+der+Lee%2C+Simon+Mille%2C+Diego+Moussallem%2C+and+Anastasia+Shimorina%2E+2020%2E)
4. [The 2020 Bilingual, Bi-Directional WebNLG+ Shared Task: Overview and Evaluation Results (WebNLG+ 2020)](https://md.research.elamur.ai/free/en/papers/ferreira-2020-2020-bilingual-bi-directional-webnlg/). In Proceedings of the 3rd International Workshop on Natural Language Generation from the Semantic Web (WebNLG+), pages 55–76, Dublin, Ireland (Virtual). Association for Computational Linguistics.
5. Shangheng Du, Jiabao Zhao, Jinxin Shi, Zhentao Xie, Xin Jiang, Yanhong Bai, and Liang He. 2025. A survey on the optimization of large language model-based agents. arXiv preprint arXiv:2503.12434. — [arXiv:2503.12434](https://arxiv.org/abs/2503.12434) [find](https://scholar.google.com/scholar?q=Shangheng+Du%2C+Jiabao+Zhao%2C+Jinxin+Shi%2C+Zhentao+Xie%2C+Xin+Jiang%2C+Yanhong+Bai%2C+and+Liang+He%2E+2025%2E+A+survey+on+the+optimization+of+large+language+model%2Dbased+agents%2E+arXiv+preprint+arXiv%3A2503%2E12434%2E+%E2%80%94+%5Ba)
6. Tianyu Gao, Alexander Wettig, Howard Yen, and Danqi Chen. 2025. [How to train long-context language models (effectively)](https://md.research.elamur.ai/free/en/papers/gao-2025-how-train-long-context-language/). In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 7376– 7399.
7. Claire Gardent, Anastasia Shimorina, Shashi Narayan, and Laura Perez-Beltrachini. 2017. [The WebNLG challenge: Generating text from RDF data](https://md.research.elamur.ai/free/en/papers/gardent-2017-webnlg-challenge-generating-text-rdf/).
8. INLG 2017 - 10th International Natural Language Generation Conference, Proceedings of the Conference, 298:124–133. [find](https://scholar.google.com/scholar?q=INLG+2017+%2D+10th+International+Natural+Language+Generation+Conference%2C+Proceedings+of+the+Conference%2C+298%3A124%E2%80%93133%2E)
9. Nelson F Liu, Kevin Lin, John Hewitt, Ashwin Paranjape, Michele Bevilacqua, Fabio Petroni, and Percy Liang. 2024a. [Lost in the middle: How language models use long contexts](https://md.research.elamur.ai/free/en/papers/liu-2023-lost-middle-language-models-use/). Transactions of the Association for Computational Linguistics, 12:157–173.
10. Jiawei Gu, Xuhui Jiang, Zhichao Shi, Hexiang Tan, Xuehao Zhai, Chengjin Xu, Wei Li, Yinghan Shen, Shengjie Ma, Honghao Liu, et al. 2024. A survey on llm-as-a-judge. arXiv preprint arXiv:2411.15594. [find](https://scholar.google.com/scholar?q=Jiawei+Gu%2C+Xuhui+Jiang%2C+Zhichao+Shi%2C+Hexiang+Tan%2C+Xuehao+Zhai%2C+Chengjin+Xu%2C+Wei+Li%2C+Yinghan+Shen%2C+Shengjie+Ma%2C+Honghao+Liu%2C+et+al%2E+2024%2E+A+survey+on+llm%2Das%2Da%2Djudge%2E+arXiv+preprint+arXiv%3A2411%2E15594%2E)
11. Xiang Liu, Peijie Dong, Xuming Hu, and Xiaowen Chu. 2024b. Longgenbench: Long-context generation benchmark. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 865–883. [find](https://scholar.google.com/scholar?q=Xiang+Liu%2C+Peijie+Dong%2C+Xuming+Hu%2C+and+Xiaowen+Chu%2E+2024b%2E+Longgenbench%3A+Long%2Dcontext+generation+benchmark%2E+In+Findings+of+the+Association+for+Computational+Linguistics%3A+EMNLP+2024%2C+pages+865%E2%80%93883%2E)
12. Taicheng Guo, Xiuying Chen, Yaqi Wang, Ruidi Chang, Shichao Pei, Nitesh V Chawla, Olaf Wiest, and Xiangliang Zhang. 2024. [Large language model based multi-agents: a survey of progress and challenges](https://md.research.elamur.ai/free/en/papers/guo-2024-large-language-model-based/). In Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence, pages…
13. Jekaterina Novikova, Ondřej Dušek, and Verena Rieser. 2017. [The E2E dataset: New challenges for end-to-end generation](https://md.research.elamur.ai/free/en/papers/novikova-2017-e2e-dataset-new-challenges-end/). In Proceedings of the 18th Annual SIGdial Meeting on Discourse and Dialogue, pages 201–206, Saarbrücken, Germany. Association for Computational Linguistics.
14. Mateusz Lango and Ondřej Dušek. 2025. Llm agents implement an nlg system from scratch: Building interpretable rule-based rdf-to-text generators. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track. [find](https://scholar.google.com/scholar?q=Mateusz+Lango+and+Ondr%CC%8Cej+Du%C5%A1ek%2E+2025%2E+Llm+agents+implement+an+nlg+system+from+scratch%3A+Building+interpretable+rule%2Dbased+rdf%2Dto%2Dtext+generators%2E+In+Proceedings+of+the+2025+Conference+on+Empirical+Met)
15. Chinonso Cynthia Osuji, Simon Mille, Ornait O’Connell, Thiago Castro Ferreira, Anja Belz, and Brian Davis. 2025a. Scaling up data-to-text generation to longer sequences: A new dataset and benchmark results for generation from large triple sets. In Proceedings of the 18th International Natural Langua… [find](https://scholar.google.com/scholar?q=Chinonso+Cynthia+Osuji%2C+Simon+Mille%2C+Ornait+O%E2%80%99Connell%2C+Thiago+Castro+Ferreira%2C+Anja+Belz%2C+and+Brian+Davis%2E+2025a%2E+Scaling+up+data%2Dto%2Dtext+generation+to+longer+sequences%3A+A+new+dataset+and+benchmark+re)
16. Rémi Lebret, David Grangier, and Michael Auli. 2016. [Neural Text Generation from Structured Data with Application to the Biography Domain](https://md.research.elamur.ai/free/en/papers/lebret-2016-neural-text-generation-structured-data/).
17. EMNLP 2016 - Conference on Empirical Methods in Natural Language Processing, Proceedings, pages 1203–1213. [find](https://scholar.google.com/scholar?q=EMNLP+2016+%2D+Conference+on+Empirical+Methods+in+Natural+Language+Processing%2C+Proceedings%2C+pages+1203%E2%80%931213%2E)
18. Jiaqi Li, Mengmeng Wang, Zilong Zheng, and Muhan Zhang. 2024a. [LooGLE: Can long-context language models understand long contexts?](https://md.research.elamur.ai/free/en/papers/li-2023-loogle-long-context-language-models/) In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 16304–16333, Bangkok, Thailand. Association for…
19. Xinyi Li, Sai Wang, Siqi Zeng, Yu Wu, and Yi Yang. 2024b. A survey on llm-based multi-agent systems: workflow, infrastructure, and challenges. Vicinagearth, 1(1):9. [find](https://scholar.google.com/scholar?q=Xinyi+Li%2C+Sai+Wang%2C+Siqi+Zeng%2C+Yu+Wu%2C+and+Yi+Yang%2E+2024b%2E+A+survey+on+llm%2Dbased+multi%2Dagent+systems%3A+workflow%2C+infrastructure%2C+and+challenges%2E+Vicinagearth%2C+1%281%29%3A9%2E)
20. Percy Liang, Michael Jordan, and Dan Klein. 2009. [Learning semantic correspondences with less supervision](https://md.research.elamur.ai/free/en/papers/liang-2009-learning-semantic-correspondences-less-supervision/). In Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP, pages 91–99, Suntec, Singapo…
21. Jiaheng Liu, Dawei Zhu, Zhiqi Bai, Yancheng He, Huanxuan Liao, Haoran Que, Zekun Wang, Chenchen Zhang, Ge Zhang, Jiebin Zhang, Yuanxing Zhang, Zhuo Chen, Hangyu Guo, Shilong Li, Ziqiang Liu, Yong Shan, Yifan Song, Jiayi Tian, Wenhao Wu, Zhejian Zhou, Ruijie Zhu, Junlan Feng, Yang Gao, Shizhu He, Zho… — [A Comprehensive Survey on Long Context Language Modeling](https://md.research.elamur.ai/free/en/papers/liu-2025-comprehensive-survey-long-context-language/)
22. Chinonso Cynthia Osuji, Brian Timoney, Mark Andrade, Thiago Castro Ferreira, and Brian Davis. 2025b. Are multi-agents the new pipeline architecture for data-to-text systems? In Proceedings of the 18th International Natural Language Generation Conference, pages 542–553. [find](https://scholar.google.com/scholar?q=Chinonso+Cynthia+Osuji%2C+Brian+Timoney%2C+Mark+Andrade%2C+Thiago+Castro+Ferreira%2C+and+Brian+Davis%2E+2025b%2E+Are+multi%2Dagents+the+new+pipeline+architecture+for+data%2Dto%2Dtext+systems%3F+In+Proceedings+of+the+18th)
23. Ankur P. Parikh, Xuezhi Wang, Sebastian Gehrmann, Manaal Faruqui, Bhuwan Dhingra, Diyi Yang, and Dipanjan Das. 2020. [ToTTo: A controlled table-to-text generation dataset](https://md.research.elamur.ai/free/en/papers/parikh-2020-totto-controlled-table-text-generation/).
24. EMNLP 2020 - 2020 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference, pages 1173–1186. [find](https://scholar.google.com/scholar?q=EMNLP+2020+%2D+2020+Conference+on+Empirical+Methods+in+Natural+Language+Processing%2C+Proceedings+of+the+Conference%2C+pages+1173%E2%80%931186%2E)
25. Kaiyang Wan, Honglin Mu, Rui Hao, Haoran Luo, Tianle Gu, and Xiuying Chen. 2025. A cognitive writing perspective for constrained long-form text generation. arXiv preprint arXiv:2502.12568. [find](https://scholar.google.com/scholar?q=Kaiyang+Wan%2C+Honglin+Mu%2C+Rui+Hao%2C+Haoran+Luo%2C+Tianle+Gu%2C+and+Xiuying+Chen%2E+2025%2E+A+cognitive+writing+perspective+for+constrained+long%2Dform+text+generation%2E+arXiv+preprint+arXiv%3A2502%2E12568%2E)
26. Zhao Wang, Sota Moriyama, Wei-Yao Wang, Briti Gangopadhyay, and Shingo Takamatsu. 2025. Talk structurally, act hierarchically: A collaborative framework for llm multi-agent systems. arXiv preprint arXiv:2502.11098. — [arXiv:2502.11098](https://arxiv.org/abs/2502.11098) [find](https://scholar.google.com/scholar?q=Zhao+Wang%2C+Sota+Moriyama%2C+Wei%2DYao+Wang%2C+Briti+Gangopadhyay%2C+and+Shingo+Takamatsu%2E+2025%2E+Talk+structurally%2C+act+hierarchically%3A+A+collaborative+framework+for+llm+multi%2Dagent+systems%2E+arXiv+preprint+arX)
27. Sam Wiseman, Stuart Shieber, and Alexander Rush. 2017. [Challenges in data-to-document generation](https://md.research.elamur.ai/free/en/papers/wiseman-2017-challenges-data-document-generation/). In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 2253–2263, Copenhagen, Denmark. Association for Computational Linguistics.
28. Yuhao Wu, Yushi Bai, Zhiqiang Hu, Juanzi Li, and Roy Ka-Wei Lee. 2025a. [Superwriter: Reflection-driven long-form generation with large language models](https://md.research.elamur.ai/free/en/papers/wu-2026-superwriter-reflection-driven-long-form/). arXiv preprint arXiv:2506.04180. *Figure 3: Sample input triple set of size 9 (small triple set for better readability)* Yuhao Wu, Yushi Bai, Zhiqin…
29. Zhiheng Xi, Wenxiang Chen, Xin Guo, Wei He, Yiwen Ding, Boyang Hong, Ming Zhang, Junzhe Wang, Senjie Jin, Enyu Zhou, et al. 2025. [The rise and potential of large language model based agents: A survey](https://md.research.elamur.ai/free/en/papers/xi-2023-rise-potential-large-language/). Science China Information Sciences, 68(2):121101.
30. Ruibin Xiong, Yimeng Chen, Dmitrii Khizbullin, Mingchen Zhuge, and Jürgen Schmidhuber. 2025. [Beyond outlining: Heterogeneous recursive planning for adaptive long-form writing with language models](https://md.research.elamur.ai/free/en/papers/xiong-2025-beyond-outlining-heterogeneous-recursive-planning/). arXiv preprint arXiv:2503.08275.
31. Peng Xu, Wei Ping, Xianchao Wu, Lawrence McAfee, Chen Zhu, Zihan Liu, Sandeep Subramanian, Evelina Bakhturina, Mohammad Shoeybi, and Bryan Catanzaro. 2023. [Retrieval meets long context large language models](https://md.research.elamur.ai/free/en/papers/xu-2023-retrieval-meets-long-context-large/). arXiv preprint arXiv:2310.03025.
32. Joonho Yang, Seunghyun Yoon, Hwan Chang, Byeongjeong Kim, and Hwanhee Lee. 2025. Hallucinate at the last in long response generation: A case study on long document summarization. arXiv preprint arXiv:2505.15291. — [arXiv:2505.15291](https://arxiv.org/abs/2505.15291) [find](https://scholar.google.com/scholar?q=Joonho+Yang%2C+Seunghyun+Yoon%2C+Hwan+Chang%2C+Byeongjeong+Kim%2C+and+Hwanhee+Lee%2E+2025%2E+Hallucinate+at+the+last+in+long+response+generation%3A+A+case+study+on+long+document+summarization%2E+arXiv+preprint+arXiv%3A)
33. Algorithm 1 Multi-agent LLM framework for data-to-text generation Require: Structured input X (triples), target language ℓ, configuration θ Ensure: Document level text Y 1: S ← I NIT S TATE (X, ℓ, θ) 2: H ← ∅ 3: k ← 0 4: while not C ONVERGED (S) and k \\< θ.max_iterations do 5: k ← k + 1 6: if k = θ.m… [find](https://scholar.google.com/scholar?q=Algorithm+1+Multi%2Dagent+LLM+framework+for+data%2Dto%2Dtext+generation+Require%3A+Structured+input+X+%28triples%29%2C+target+language+%E2%84%93%2C+configuration+%CE%B8+Ensure%3A+Document+level+text+Y+1%3A+S+%E2%86%90+I+NIT+S+TATE+%28X%2C+%E2%84%93%2C+%CE%B8%29+)

*Updated 1 November 2026*