---
title: "Think in Sentences — paper by Liu et al. (2026)"
description: "Large language models read text as a flat stream of tokens, even though the human writing they learn… 34 references, cited by 1 paper here."
authors: ["Zhichen Liu", "Yongyuan Li", "Yang Xu"]
year: 2026
venue: "Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)"
source: "https://aclanthology.org/2026.acl-long.104/"
doi: "10.18653/v1/2026.acl-long.104"
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/liu-2026-think-sentences-explicit-sentence-boundaries/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/liu-2026-think-sentences-explicit-sentence-boundaries/)

[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/18/) / Think in Sentences: Explicit Sentence Boundaries Enhance Language Model's Capabilities

# Think in Sentences: Explicit Sentence Boundaries Enhance Language Model's Capabilities

**Authors:** [Zhichen Liu](https://md.research.elamur.ai/free/en/authors/zhichen-liu/), Yongyuan Li and [Yang Xu](https://md.research.elamur.ai/free/en/authors/yang-xu/) · **Year:** 2026 · **Venue:** [Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)](https://md.research.elamur.ai/free/en/venues/acl/) ([ACL 2026](https://md.research.elamur.ai/free/en/venues/acl/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.acl-long.104/) · [PDF](https://aclanthology.org/2026.acl-long.104.pdf) · [DOI 10.18653/v1/2026.acl-long.104](https://doi.org/10.18653/v1/2026.acl-long.104) · [OpenAlex](https://openalex.org/W7166821047)

**Citations:** 0 citations (OpenAlex, 2026-10-14) · [1](https://md.research.elamur.ai/free/en/papers/liu-2026-think-sentences-explicit-sentence-boundaries/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary

Large language models read text as a flat stream of tokens, even though the human writing they learn from is organized sentence by sentence. Earlier "pause token" methods inserted dummy tokens to give models extra computation at no inference cost, but they placed those tokens without linguistic guidance and needed per-task tuning. Liu, Li and Xu instead insert a dedicated delimiter token after every sentence, using the SaT neural segmenter, so the model gets a natural point to consolidate context before continuing. They test two variants. The first is in-context learning, where few-shot exemplars contain the delimiters and model weights stay frozen. The second is supervised fine-tuning on corpora segmented with delimiters, with the delimiter added as a new special token. Across models from 7B parameters up to DeepSeek-V3, both variants improve results on math, reading-comprehension and knowledge benchmarks. Attention analysis shows the delimiters act as information hubs. The approach matters because it adds almost no cost, and it also yields sentence-segmented output natively, which helps pipelines such as TTS and RAG.

## Key points

- **Reported gains:** improvements reach up to 7.7% on GSM8k and 12.5% on DROP. For Llama3-8B-Instruct specifically, the gains are about 4.4% on GSM8k and 6.8% on DROP.
- **Models and setup:**
  - In-context learning was tested on LLaMA3-8B-Instruct, Qwen2-7B-Instruct, Qwen2.5-72B-Instruct and DeepSeek-V3 (via API).
  - Supervised fine-tuning was full-parameter training of LLaMA3-8B-Base on 8×NVIDIA L40 GPUs.
- **Benchmarks:** GSM8k, MATH, DROP, MMLU and MMLU-Pro.
- **Ablations:**
  - A distinct, non-semantic delimiter works better than arbitrary tokens.
  - Sentence-level chunking beats both finer and coarser segmentation.
  - The gains come from interplay with Chain-of-Thought reasoning.
- **Attention analysis:** the delimiter draws far more attention than an average token, and also more than natural punctuation such as periods or newlines.
- **Code and limitations:** a demo is available at github.com/CLCS-SUSTech/think-in-sentence. Open questions include other segmenters, applying the method at pre-training scale, and low-resource languages.

*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

- [Southern University of Science and Technology](https://md.research.elamur.ai/free/en/universities/southern-university-of-science-and-technology/) — University, Shenzhen, China · 19 works · 1,337 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 · [👁️ Computer Vision and Pattern Recognition](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · 2,869 works

🧭 Topics (1): [🧠 Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/) · 3,320 works

## Cite

Cite as: Zhichen Liu, Yongyuan Li and Yang Xu. 2026. Think in Sentences: Explicit Sentence Boundaries Enhance Language Model's Capabilities. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).

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

```bibtex
@inproceedings{liu2026think,
  title = {{Think in Sentences: Explicit Sentence Boundaries Enhance Language Model's Capabilities}},
  author = {Zhichen Liu, Yongyuan Li and Yang Xu},
  booktitle = {Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2026},
  doi = {10.18653/v1/2026.acl-long.104},
  url = {https://doi.org/10.18653/v1/2026.acl-long.104}
}
```

- [← previous The Thin Line Between Comprehension and Persuasion in LLMs](https://md.research.elamur.ai/free/en/papers/wynter-2026-thin-line-between-comprehension-persuasion/)
- [next → ThinkBrake: Efficient Reasoning via Log-Probability Margin Guided Decoding](https://md.research.elamur.ai/free/en/papers/song-2026-thinkbrake-efficient-reasoning-log-probability/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/18/)

## References

34 references, 22 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Tom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared Kaplan, Prafulla Dhariwal, Arvind Mark Chen, Jerry Tworek, Heewoo Jun, Qiming Yuan, Henrique Ponde de Oliveira Pinto, Jared Kaplan, Harri Edwards, Yuri Burda, Nicholas Joseph, et al. 2021. [Evaluating large language models trained on cod…](https://md.research.elamur.ai/free/en/papers/chen-2021-evaluating-large-language-models-trained/)
2. Aakanksha Chowdhery, Sharan Narang, Jacob Devlin, Maarten Bosma, Gaurav Mishra, Adam Roberts, Paul Barham, Hyung Won Chung, et al. 2022. [Palm: Scaling language modeling with pathways](https://md.research.elamur.ai/free/en/papers/chowdhery-2022-palm-scaling-language-modeling-pathways/). Preprint, arXiv:2204.02311.
3. Karl Cobbe, Vineet Kosaraju, Mohammad Bavarian, Mark Chen, Heewoo Jun, Lukasz Kaiser, Matthias Plappert, Jerry Tworek, Jacob Hilton, Reiichiro Nakano, Christopher Hesse, and John Schulman. 2021. [Training verifiers to solve math word problems](https://md.research.elamur.ai/free/en/papers/cobbe-2021-training-verifiers-solve-math-word/). Preprint, arXiv:2110.14168.
4. DeepSeek-AI, Daya Guo, Dejian Yang, Haowei Zhang, Junxiao Song, Ruoyu Zhang, Runxin Xu, Qihao Zhu, Shirong Ma, Peiyi Wang, Xiao Bi, Xiaokang Zhang, et al. 2025a. [Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning](https://md.research.elamur.ai/free/en/papers/deepseek-ai-2025-deepseek-r1-incentivizing-reasoning-capability/). Preprint, arXiv:2501.12948.
5. DeepSeek-AI, Aixin Liu, Bei Feng, Bing Xue, Bingxuan Wang, Bochao Wu, Chengda Lu, Chenggang Zhao, Chengqi Deng, Chenyu Zhang, et al. 2025b. Deepseek-v3 technical report. Preprint, arXiv:2412.19437. [find](https://scholar.google.com/scholar?q=DeepSeek%2DAI%2C+Aixin+Liu%2C+Bei+Feng%2C+Bing+Xue%2C+Bingxuan+Wang%2C+Bochao+Wu%2C+Chengda+Lu%2C+Chenggang+Zhao%2C+Chengqi+Deng%2C+Chenyu+Zhang%2C+et+al%2E+2025b%2E+Deepseek%2Dv3+technical+report%2E+Preprint%2C+arXiv%3A2412%2E19437%2E)
6. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. [Bert: Pre-training of deep bidirectional transformers for language understanding](https://md.research.elamur.ai/free/en/papers/devlin-2019-bert-pre-training-deep-bidirectional/). Preprint, arXiv:1810.04805.
7. Qingxiu Dong, Lei Li, Damai Dai, Ce Zheng, Jingyuan Ma, Rui Li, Heming Xia, Jingjing Xu, Zhiyong Wu, Tianyu Liu, Baobao Chang, Xu Sun, Lei Li, and Zhifang Sui. 2024. [A survey on in-context learning](https://md.research.elamur.ai/free/en/papers/dong-2023-survey-context-learning/). Preprint, arXiv:2301.00234.
8. Dheeru Dua, Yizhong Wang, Pradeep Dasigi, Gabriel Stanovsky, Sameer Singh, and Matt Gardner. 2019. [Drop: A reading comprehension benchmark requiring discrete reasoning over paragraphs](https://md.research.elamur.ai/free/en/papers/dua-2019-drop-reading-comprehension-benchmark-requiring/). Preprint, arXiv:1903.00161.
9. Markus Frohmann, Igor Sterner, Ivan Vulić, Benjamin Minixhofer, and Markus Schedl. 2024. Segment any text: A universal approach for robust, efficient and adaptable sentence segmentation. Preprint, arXiv:2406.16678. [find](https://scholar.google.com/scholar?q=Markus+Frohmann%2C+Igor+Sterner%2C+Ivan+Vulic%CC%81%2C+Benjamin+Minixhofer%2C+and+Markus+Schedl%2E+2024%2E+Segment+any+text%3A+A+universal+approach+for+robust%2C+efficient+and+adaptable+sentence+segmentation%2E+Preprint%2C+ar)
10. Sachin Goyal, Ziwei Ji, Ankit Singh Rawat, Aditya Krishna Menon, Sanjiv Kumar, and Vaishnavh Nagarajan. 2024. Think before you speak: Training language models with pause tokens. Preprint, arXiv:2310.02226. [find](https://scholar.google.com/scholar?q=Sachin+Goyal%2C+Ziwei+Ji%2C+Ankit+Singh+Rawat%2C+Aditya+Krishna+Menon%2C+Sanjiv+Kumar%2C+and+Vaishnavh+Nagarajan%2E+2024%2E+Think+before+you+speak%3A+Training+language+models+with+pause+tokens%2E+Preprint%2C+arXiv%3A2310%2E0)
11. Aaron Grattafiori, Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Alex Vaughan, Amy Yang, Angela Fan, Anirudh Goyal, et al. 2024. [The llama 3 herd of models](https://md.research.elamur.ai/free/en/papers/grattafiori-2024-llama-3-herd-models/). Preprint, arXiv:2407.21783.
12. Dan Hendrycks, Collin Burns, Steven Basart, Andy Zou, Mantas Mazeika, Dawn Song, and Jacob Steinhardt. 2021a. [Measuring massive multitask language understanding](https://md.research.elamur.ai/free/en/papers/hendrycks-2020-measuring-massive-multitask-language-understanding/). Preprint, arXiv:2009.03300.
13. Dan Hendrycks, Collin Burns, Saurav Kadavath, Akul Arora, Steven Basart, Eric Tang, Dawn Song, and Jacob Steinhardt. 2021b. [Measuring mathematical problem solving with the math dataset](https://md.research.elamur.ai/free/en/papers/hendrycks-2021-measuring-mathematical-problem-solving-math/). NeurIPS.
14. Jordan Hoffmann, Sebastian Borgeaud, Arthur Mensch, Elena Buchatskaya, Trevor Cai, Eliza Rutherford, Diego de Las Casas, et al. 2022. [Training compute-optimal large language models](https://md.research.elamur.ai/free/en/papers/hoffmann-2022-training-compute-optimal-large-language/). Preprint, arXiv:2203.15556.
15. Jared Kaplan, Sam McCandlish, Tom Henighan, Tom B. Brown, Benjamin Chess, Rewon Child, Scott Gray, Alec Radford, Jeffrey Wu, and Dario Amodei. 2020. [Scaling laws for neural language models](https://md.research.elamur.ai/free/en/papers/kaplan-2020-scaling-laws-neural-language-models/). Preprint, arXiv:2001.08361.
16. Ryan Kiros, Yukun Zhu, Russ R Salakhutdinov, Richard Zemel, Raquel Urtasun, Antonio Torralba, and Sanja Fidler. 2015. Skip-thought vectors. Advances in Neural Information Processing Systems, 28. [find](https://scholar.google.com/scholar?q=Ryan+Kiros%2C+Yukun+Zhu%2C+Russ+R+Salakhutdinov%2C+Richard+Zemel%2C+Raquel+Urtasun%2C+Antonio+Torralba%2C+and+Sanja+Fidler%2E+2015%2E+Skip%2Dthought+vectors%2E+Advances+in+Neural+Information+Processing+Systems%2C+28%2E)
17. Anton Bulle Labate and Fabio Gagliardi Cozman. 2024. Infusing prompts with syntax and semantics. Preprint, arXiv:2412.06107. — [arXiv:2412.06107](https://arxiv.org/abs/2412.06107) [find](https://scholar.google.com/scholar?q=Anton+Bulle+Labate+and+Fabio+Gagliardi+Cozman%2E+2024%2E+Infusing+prompts+with+syntax+and+semantics%2E+Preprint%2C+arXiv%3A2412%2E06107%2E+%E2%80%94+%5BarXiv%3A2412%2E06107%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2412%2E06107%29)
18. Nathan Lambert, Jacob Morrison, Valentina Pyatkin, Shengyi Huang, Hamish Ivison, Faeze Brahman, Lester James V. Miranda, Alisa Liu, et al. 2025. [Tulu 3: Pushing frontiers in open language model post-training](https://md.research.elamur.ai/free/en/papers/lambert-2024-tulu-3-pushing-frontiers-open/). Preprint, arXiv:2411.15124.
19. Long Ouyang, Jeff Wu, Xu Jiang, Diogo Almeida, et al. 2022. [Training language models to follow instructions with human feedback](https://md.research.elamur.ai/free/en/papers/ouyang-2022-training-language-models-follow-instructions/). Preprint, arXiv:2203.02155.
20. Zhenting Qi, Mingyuan Ma, Jiahang Xu, Li Lyna Zhang, Fan Yang, and Mao Yang. 2024. Mutual reasoning makes smaller llms stronger problem-solvers. Preprint, arXiv:2408.06195. [find](https://scholar.google.com/scholar?q=Zhenting+Qi%2C+Mingyuan+Ma%2C+Jiahang+Xu%2C+Li+Lyna+Zhang%2C+Fan+Yang%2C+and+Mao+Yang%2E+2024%2E+Mutual+reasoning+makes+smaller+llms+stronger+problem%2Dsolvers%2E+Preprint%2C+arXiv%3A2408%2E06195%2E)
21. Wenjie Qiu, Yi-Chen Li, Xuqin Zhang, Tianyi Zhang, Yihang Zhang, Zongzhang Zhang, and Yang Yu. 2025. Sentence-level reward model can generalize better for aligning llm from human preference. Preprint, arXiv:2503.04793. — [arXiv:2503.04793](https://arxiv.org/abs/2503.04793) [find](https://scholar.google.com/scholar?q=Wenjie+Qiu%2C+Yi%2DChen+Li%2C+Xuqin+Zhang%2C+Tianyi+Zhang%2C+Yihang+Zhang%2C+Zongzhang+Zhang%2C+and+Yang+Yu%2E+2025%2E+Sentence%2Dlevel+reward+model+can+generalize+better+for+aligning+llm+from+human+preference%2E+Preprint%2C)
22. Qwen, :, An Yang, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chengyuan Li, Dayiheng Liu, Fei Huang, et al. 2025. Qwen2.5 technical report. Preprint, arXiv:2412.15115. [find](https://scholar.google.com/scholar?q=Qwen%2C+%3A%2C+An+Yang%2C+Baosong+Yang%2C+Beichen+Zhang%2C+Binyuan+Hui%2C+Bo+Zheng%2C+Bowen+Yu%2C+Chengyuan+Li%2C+Dayiheng+Liu%2C+Fei+Huang%2C+et+al%2E+2025%2E+Qwen2%2E5+technical+report%2E+Preprint%2C+arXiv%3A2412%2E15115%2E)
23. David Rein, Betty Li Hou, Asa Cooper Stickland, Jackson Petty, Richard Yuanzhe Pang, Julien Dirani, Julian Michael, and Samuel R. Bowman. 2024. [GPQA: A graduate-level google-proof q&a benchmark](https://md.research.elamur.ai/free/en/papers/rein-2023-gpqa-graduate-level-google-proof/). In First Conference on Language Modeling.
24. Matthew Renze and Erhan Guven. 2024. The benefits of a concise chain of thought on problem-solving in large language models. In 2024 2nd International Conference on Foundation and Large Language Models (FLLM), page 476–483. IEEE. [find](https://scholar.google.com/scholar?q=Matthew+Renze+and+Erhan+Guven%2E+2024%2E+The+benefits+of+a+concise+chain+of+thought+on+problem%2Dsolving+in+large+language+models%2E+In+2024+2nd+International+Conference+on+Foundation+and+Large+Language+Model)
25. Zhihong Shao, Peiyi Wang, Qihao Zhu, Runxin Xu, Junxiao Song, Xiao Bi, Haowei Zhang, Mingchuan Zhang, Y. K. Li, Y. Wu, and Daya Guo. 2024. [Deepseekmath: Pushing the limits of mathematical reasoning in open language models](https://md.research.elamur.ai/free/en/papers/shao-2024-deepseekmath-pushing-limits-mathematical-reasoning/). Preprint, arXiv:2402.03300.
26. Kimi Team, Angang Du, Bofei Gao, Bowei Xing, Changjiu Jiang, Cheng Chen, Cheng Li, Chenjun Xiao, Chenzhuang Du, Chonghua Liao, et al. 2025. [Kimi k1.5: Scaling reinforcement learning with llms](https://md.research.elamur.ai/free/en/papers/kimi-team-2025-kimi-k1-5-scaling-reinforcement/). Preprint, arXiv:2501.12599.
27. Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timothée Lacroix, Baptiste Rozière, Naman Goyal, et al. 2023. [Llama: Open and efficient foundation language models](https://md.research.elamur.ai/free/en/papers/touvron-2023-llama-open-efficient-foundation-language/). Preprint, arXiv:2302.13971.
28. Yubo Wang, Xueguang Ma, Ge Zhang, Yuansheng Ni, Abhranil Chandra, Shiguang Guo, Weiming Ren, Aaran Arulraj, Xuan He, Ziyan Jiang, et al. 2024. [Mmlu-pro: A more robust and challenging multi-task language understanding benchmark](https://md.research.elamur.ai/free/en/papers/wang-2024-mmlu-pro-more-robust-challenging/). arXiv preprint arXiv:2406.01574.
29. Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, brian ichter, Fei Xia, Ed 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, volume 35, pages 24824–24837. Curran Associates, Inc.
30. An Yang, Baosong Yang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Zhou, Chengpeng Li, Chengyuan Li, Dayiheng Liu, Fei Huang, Guanting Dong, Haoran Wei, et al. 2024. Qwen2 technical report. Preprint, arXiv:2407.10671. [find](https://scholar.google.com/scholar?q=An+Yang%2C+Baosong+Yang%2C+Binyuan+Hui%2C+Bo+Zheng%2C+Bowen+Yu%2C+Chang+Zhou%2C+Chengpeng+Li%2C+Chengyuan+Li%2C+Dayiheng+Liu%2C+Fei+Huang%2C+Guanting+Dong%2C+Haoran+Wei%2C+et+al%2E+2024%2E+Qwen2+technical+report%2E+Preprint%2C+arXiv)
31. Shunyu Yao, Dian Yu, Jeffrey Zhao, Izhak Shafran, Thomas L. Griffiths, Yuan Cao, and Karthik Narasimhan. 2023. Tree of thoughts: Deliberate problem solving with large language models. Preprint, arXiv:2305.10601. [find](https://scholar.google.com/scholar?q=Shunyu+Yao%2C+Dian+Yu%2C+Jeffrey+Zhao%2C+Izhak+Shafran%2C+Thomas+L%2E+Griffiths%2C+Yuan+Cao%2C+and+Karthik+Narasimhan%2E+2023%2E+Tree+of+thoughts%3A+Deliberate+problem+solving+with+large+language+models%2E+Preprint%2C+arXiv%3A)
32. Wen Yin, Cencen Liu, Yi Xu, Ahmad Raza Wahla, Huang Yiting, and Dezhang Zheng. 2024. Syn-Prompt: Syntax-aware enhanced prompt engineering for aspect-based sentiment analysis. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LR… [find](https://scholar.google.com/scholar?q=Wen+Yin%2C+Cencen+Liu%2C+Yi+Xu%2C+Ahmad+Raza+Wahla%2C+Huang+Yiting%2C+and+Dezhang+Zheng%2E+2024%2E+Syn%2DPrompt%3A+Syntax%2Daware+enhanced+prompt+engineering+for+aspect%2Dbased+sentiment+analysis%2E+In+Proceedings+of+the+202)
33. Dan Zhang, Sining Zhoubian, Ziniu Hu, Yisong Yue, Yuxiao Dong, and Jie Tang. 2024. [Rest-mcts*: Llm self-training via process reward guided tree search](https://md.research.elamur.ai/free/en/papers/zhang-2024-rest-mcts-llm-self-training/). Preprint, arXiv:2406.03816.
34. Chujie Zheng, Shixuan Liu, Mingze Li, Xiong-Hui Chen, Bowen Yu, Chang Gao, Kai Dang, Yuqiong Liu, Rui Men, An Yang, Jingren Zhou, and Junyang Lin. 2025. [Group sequence policy optimization](https://md.research.elamur.ai/free/en/papers/zheng-2025-group-sequence-policy-optimization/). Preprint, arXiv:2507.18071.

*Updated 1 November 2026*