---
title: "Parallel Test-Time Scaling for Latent Reasoning Models (2026)"
description: "Parallel test-time scaling (TTS) improves LLMs by sampling many chains-of-thought and… 32. accuracy on GSM-Test. 41 references."
authors: ["Runyang You", "Yongqi Li", "Meng Liu", "Wenjie Wang", "Liqiang Nie", "Wenjie Li"]
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.2069/"
doi: "10.18653/v1/2026.acl-long.2069"
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/you-2026-parallel-test-time-scaling-latent/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/you-2026-parallel-test-time-scaling-latent/)

[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/44/) / Parallel Test-Time Scaling for Latent Reasoning Models

# Parallel Test-Time Scaling for Latent Reasoning Models

**Authors:** Runyang You, [Yongqi Li](https://md.research.elamur.ai/free/en/authors/yongqi-li/), Meng Liu, [Wenjie Wang](https://md.research.elamur.ai/free/en/authors/wenjie-wang/), [Liqiang Nie](https://md.research.elamur.ai/free/en/authors/liqiang-nie/) and [Wenjie Li](https://md.research.elamur.ai/free/en/authors/wenjie-li/) · **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.2069/) · [PDF](https://aclanthology.org/2026.acl-long.2069.pdf) · [DOI 10.18653/v1/2026.acl-long.2069](https://doi.org/10.18653/v1/2026.acl-long.2069) · [OpenAlex](https://openalex.org/W4416398391)

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

## Summary

Parallel test-time scaling (TTS) improves LLMs by sampling many chains-of-thought and combining them through voting or search. Latent reasoning models, which reason through continuous hidden-state vectors instead of tokens, could not use this approach. They have no token distribution to sample from and no likelihoods for ranking trajectories. The authors fill both gaps. For sampling, they borrow from uncertainty estimation and use two strategies. Monte Carlo Dropout keeps dropout active at inference and reflects epistemic uncertainty. Additive Gaussian Noise perturbs each latent thought and mimics aleatoric uncertainty. For aggregation, they train a Latent Reward Model (LatentRM) that scores every intermediate latent step using a step-wise contrastive objective. On arithmetic benchmarks, both samplers improve as compute grows, but they explore differently. MC-dropout pushes in directed ways toward unusual solutions and reaches higher coverage. Gaussian noise spreads evenly around the deterministic path. LatentRM gives consistent gains with best-of-N and beam search. The work matters because it brings inference-time compute scaling, previously limited to token-based reasoning, to continuous-space models.

## Key points

- **Evaluation setup:** Experiments use GSM8K-Test, GSM8K-Hard and MultiArith. Compute budgets range from N = 2⁰ to 2⁶, and results are averaged over three runs. Aggregation is compared across majority voting, best-of-N and beam search. Background latent models discussed include COCONUT, CODI and CoLaR.
- **Main result:** Best-of-N with LatentRM is the most effective aggregation route. Its gains are largest on MultiArith.
- **Ablation results (Table 2):** The text says N = 8, while the table caption says N = 32. Accuracy on GSM-Test / GSM-Hard was:
  - full LatentRM: 35.4 / 7.8
  - BCE in place of the contrastive loss: 33.5 / 7.4
  - without stochastic rollouts: 30.7 / 6.0
  - untrained random head: 28.9 / 5.8, which falls below majority voting at 33.6 / 6.1
- **Training labels:** Step-level labels for LatentRM come from Monte Carlo rollout estimates. Removing these rollouts noticeably hurts selection quality.
- **Limitations:** Results depend on tuning the dropout rate p and the noise scale σ, and real-time deployment would need further engineering. Suggested future directions are RL-based optimization and ensemble methods for latent reasoning.

*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

- [Harbin Institute of Technology](https://md.research.elamur.ai/free/en/universities/harbin-institute-of-technology/) — University, Harbin, China · 185 works · 29,140 citations
- [University of Science and Technology of China](https://md.research.elamur.ai/free/en/universities/university-of-science-and-technology-of-china/) — University, Hefei, China · 145 works · 114,409 citations
- [Hong Kong Polytechnic University](https://md.research.elamur.ai/free/en/universities/hong-kong-polytechnic-university/) — University, Hong Kong, China · 106 works · 5,190 citations

Also on the byline: [Shandong Jianzhu University](https://ror.org/01gbfax37).

📚 Shelves (4): [🖥️ 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

🧭 Topics (1): [🧮 Reasoning](https://md.research.elamur.ai/free/en/topics/reasoning/) · 1,685 works

## Cite

Cite as: Runyang You, Yongqi Li, Meng Liu, Wenjie Wang, Liqiang Nie and Wenjie Li. 2026. Parallel Test-Time Scaling for Latent Reasoning Models. 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{you2026parallel,
  title = {{Parallel Test-Time Scaling for Latent Reasoning Models}},
  author = {Runyang You, Yongqi Li, Meng Liu, Wenjie Wang, Liqiang Nie and Wenjie Li},
  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.2069},
  url = {https://doi.org/10.18653/v1/2026.acl-long.2069}
}
```

- [← previous Parallel Corpus Filtering Based on Semantic Similarity and Surface Dissimilarity for Japanese Text Simplification with LLMs](https://md.research.elamur.ai/free/en/papers/maekawa-2026-parallel-corpus-filtering-based-semantic/)
- [next → Parallel Universes, Parallel Languages: A Comprehensive Study on LLM-based Multilingual Counterfactual Example Generation](https://md.research.elamur.ai/free/en/papers/wang-2026-parallel-universes-parallel-languages-comprehensive/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/44/)

## References

41 references, 19 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Bradley Brown, Jordan Juravsky, Ryan Ehrlich, Ronald Clark, Quoc V. Le, Christopher Ré, and Azalia Mirhoseini. 2024. [Large Language Monkeys: Scaling Inference Compute with Repeated Sampling](https://md.research.elamur.ai/free/en/papers/brown-2024-large-language-monkeys-scaling-inference/). arXiv preprint.
2. Xinghao Chen, Anhao Zhao, Heming Xia, Xuan Lu, Hanlin Wang, Yanjun Chen, Wei Zhang, Jian Wang, Wenjie Li, and Xiaoyu Shen. 2025a. Reasoning Beyond Language: A Comprehensive Survey on Latent Chain-of-Thought Reasoning. arXiv preprint. [find](https://scholar.google.com/scholar?q=Xinghao+Chen%2C+Anhao+Zhao%2C+Heming+Xia%2C+Xuan+Lu%2C+Hanlin+Wang%2C+Yanjun+Chen%2C+Wei+Zhang%2C+Jian+Wang%2C+Wenjie+Li%2C+and+Xiaoyu+Shen%2E+2025a%2E+Reasoning+Beyond+Language%3A+A+Comprehensive+Survey+on+Latent+Chain%2Dof%2DT)
3. Yilong Chen, Junyuan Shang, Zhenyu Zhang, Yanxi Xie, Jiawei Sheng, Tingwen Liu, Shuohuan Wang, Yu Sun, Hua Wu, and Haifeng Wang. 2025b. [Inner Thinking Transformer: Leveraging Dynamic Depth Scaling to Foster Adaptive Internal Thinking](https://md.research.elamur.ai/free/en/papers/chen-2025-inner-thinking-transformer-leveraging-dynamic/). In Proceedings of the 63rd Annual Meeting of the Association for…
4. Yuxin Chen, Yiran Zhao, Yang Zhang, An Zhang, Kenji Kawaguchi, Shafiq Joty, Junnan Li, Tat-Seng Chua, Michael Qizhe Shieh, and Wenxuan Zhang. 2025c. The Emergence of Abstract Thought in Large Language Models Beyond Any Language. arXiv preprint. [find](https://scholar.google.com/scholar?q=Yuxin+Chen%2C+Yiran+Zhao%2C+Yang+Zhang%2C+An+Zhang%2C+Kenji+Kawaguchi%2C+Shafiq+Joty%2C+Junnan+Li%2C+Tat%2DSeng+Chua%2C+Michael+Qizhe+Shieh%2C+and+Wenxuan+Zhang%2E+2025c%2E+The+Emergence+of+Abstract+Thought+in+Large+Language)
5. DeepSeek-AI, Aixin Liu, Bei Feng, Bing Xue, Bingxuan Wang, Bochao Wu, Chengda Lu, Chenggang Zhao, Chengqi Deng, Chenyu Zhang, Chong Ruan, Damai Dai, Daya Guo, Dejian Yang, Deli Chen, Dongjie Ji, Erhang Li, Fangyun Lin, Fucong Dai, and 181 others. 2024. DeepSeek-V3 Technical Report. arXiv preprint. [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+Chong+Ruan%2C+Damai+Dai%2C+Daya+Guo%2C+Dejian+Yang%2C+Deli+Chen%2C+Dongjie+Ji%2C+Erhan)
6. Jingcheng Deng, Liang Pang, Zihao Wei, Shichen Xu, Zenghao Duan, Kun Xu, Yang Song, Huawei Shen, and Xueqi Cheng. 2025. Latent reasoning in llms as a vocabulary-space superposition. Preprint, arXiv:2510.15522. — [arXiv:2510.15522](https://arxiv.org/abs/2510.15522) [find](https://scholar.google.com/scholar?q=Jingcheng+Deng%2C+Liang+Pang%2C+Zihao+Wei%2C+Shichen+Xu%2C+Zenghao+Duan%2C+Kun+Xu%2C+Yang+Song%2C+Huawei+Shen%2C+and+Xueqi+Cheng%2E+2025%2E+Latent+reasoning+in+llms+as+a+vocabulary%2Dspace+superposition%2E+Preprint%2C+arXiv%3A25)
7. Yichao Fu, Xuewei Wang, Yuandong Tian, and Jiawei Zhao. 2025. [Deep Think with Confidence](https://md.research.elamur.ai/free/en/papers/fu-2025-deep-think-confidence/). arXiv preprint.
8. Yarin Gal and Zoubin Ghahramani. 2016. Dropout as a Bayesian approximation: representing model uncertainty in deep learning. In Proceedings of the 33rd international conference on international conference on machine learning - volume 48, ICML’16, pages 1050–1059, New York, NY, USA. JMLR.org. [find](https://scholar.google.com/scholar?q=Yarin+Gal+and+Zoubin+Ghahramani%2E+2016%2E+Dropout+as+a+Bayesian+approximation%3A+representing+model+uncertainty+in+deep+learning%2E+In+Proceedings+of+the+33rd+international+conference+on+international+confer)
9. Luyu Gao, Aman Madaan, Shuyan Zhou, Uri Alon, Pengfei Liu, Yiming Yang, Jamie Callan, and Graham Neubig. 2022. PAL: Program-aided language models. arXiv preprint arXiv:2211.10435. [find](https://scholar.google.com/scholar?q=Luyu+Gao%2C+Aman+Madaan%2C+Shuyan+Zhou%2C+Uri+Alon%2C+Pengfei+Liu%2C+Yiming+Yang%2C+Jamie+Callan%2C+and+Graham+Neubig%2E+2022%2E+PAL%3A+Program%2Daided+language+models%2E+arXiv+preprint+arXiv%3A2211%2E10435%2E)
10. Tianyu Gao, Xingcheng Yao, and Danqi Chen. 2021. [SimCSE: Simple Contrastive Learning of Sentence Embeddings](https://md.research.elamur.ai/free/en/papers/gao-2021-simcse-simple-contrastive-learning-sentence/). In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 6894–6910, Online and Punta Cana, Dominican Republic. Association for Computational Linguistic…
11. Jakob Gawlikowski, Cedrique Rovile Njieutcheu Tassi, Mohsin Ali, Jongseok Lee, Matthias Humt, Jianxiang Feng, Anna Kruspe, Rudolph Triebel, Peter Jung, Ribana Roscher, Muhammad Shahzad, Wen Yang, Richard Bamler, and Xiao Xiang Zhu. 2023. A survey of uncertainty in deep neural networks. Artificial In… [find](https://scholar.google.com/scholar?q=Jakob+Gawlikowski%2C+Cedrique+Rovile+Njieutcheu+Tassi%2C+Mohsin+Ali%2C+Jongseok+Lee%2C+Matthias+Humt%2C+Jianxiang+Feng%2C+Anna+Kruspe%2C+Rudolph+Triebel%2C+Peter+Jung%2C+Ribana+Roscher%2C+Muhammad+Shahzad%2C+Wen+Yang%2C+Rich)
12. Jonas Geiping, Sean McLeish, Neel Jain, John Kirchenbauer, Siddharth Singh, Brian R. Bartoldson, Bhavya Kailkhura, Abhinav Bhatele, and Tom Goldstein. 2025. Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach. arXiv preprint. [find](https://scholar.google.com/scholar?q=Jonas+Geiping%2C+Sean+McLeish%2C+Neel+Jain%2C+John+Kirchenbauer%2C+Siddharth+Singh%2C+Brian+R%2E+Bartoldson%2C+Bhavya+Kailkhura%2C+Abhinav+Bhatele%2C+and+Tom+Goldstein%2E+2025%2E+Scaling+up+Test%2DTime+Compute+with+Latent+Re)
13. Shibo Hao, Sainbayar Sukhbaatar, DiJia Su, Xian Li, Zhiting Hu, Jason Weston, and Yuandong Tian. 2024. Training Large Language Models to Reason in a Continuous Latent Space. arXiv preprint. [find](https://scholar.google.com/scholar?q=Shibo+Hao%2C+Sainbayar+Sukhbaatar%2C+DiJia+Su%2C+Xian+Li%2C+Zhiting+Hu%2C+Jason+Weston%2C+and+Yuandong+Tian%2E+2024%2E+Training+Large+Language+Models+to+Reason+in+a+Continuous+Latent+Space%2E+arXiv+preprint%2E)
14. Kuang-Huei Lee, Ian Fischer, Yueh-Hua Wu, Dave Marwood, Shumeet Baluja, Dale Schuurmans, and Xinyun Chen. 2025. Evolving Deeper LLM Thinking. arXiv preprint. [find](https://scholar.google.com/scholar?q=Kuang%2DHuei+Lee%2C+Ian+Fischer%2C+Yueh%2DHua+Wu%2C+Dave+Marwood%2C+Shumeet+Baluja%2C+Dale+Schuurmans%2C+and+Xinyun+Chen%2E+2025%2E+Evolving+Deeper+LLM+Thinking%2E+arXiv+preprint%2E)
15. Jindong Li, Yali Fu, Li Fan, Jiahong Liu, Yao Shu, Chengwei Qin, Menglin Yang, Irwin King, and Rex Ying. 2025. [Implicit Reasoning in Large Language Models: A Comprehensive Survey](https://md.research.elamur.ai/free/en/papers/li-2025-implicit-reasoning-large-language-models/). arXiv preprint.
16. Jeremiah Liu, John Paisley, Marianthi-Anna Kioumourt-zoglou, and Brent Coull. 2019. Accurate uncertainty estimation and decomposition in ensemble learning. In Advances in neural information processing systems, volume 32. Curran Associates, Inc. [find](https://scholar.google.com/scholar?q=Jeremiah+Liu%2C+John+Paisley%2C+Marianthi%2DAnna+Kioumourt%2Dzoglou%2C+and+Brent+Coull%2E+2019%2E+Accurate+uncertainty+estimation+and+decomposition+in+ensemble+learning%2E+In+Advances+in+neural+information+processing)
17. Amirkeivan Mohtashami, Matteo Pagliardini, and Martin Jaggi. 2024. CoTFormer: A Chain-of-Thought Driven Architecture with Budget-Adaptive Computation Cost at Inference. arXiv preprint. [find](https://scholar.google.com/scholar?q=Amirkeivan+Mohtashami%2C+Matteo+Pagliardini%2C+and+Martin+Jaggi%2E+2024%2E+CoTFormer%3A+A+Chain%2Dof%2DThought+Driven+Architecture+with+Budget%2DAdaptive+Computation+Cost+at+Inference%2E+arXiv+preprint%2E)
18. Niklas Muennighoff, Zitong Yang, Weijia Shi, Xiang Lisa Li, Li Fei-Fei, Hannaneh Hajishirzi, Luke Zettlemoyer, Percy Liang, Emmanuel Candès, and Tatsunori Hashimoto. 2025. [s1: Simple test-time scaling](https://md.research.elamur.ai/free/en/papers/muennighoff-2025-s1-simple-test-time-scaling/). arXiv preprint.
19. Yuxiao Qu, Matthew Y. R. Yang, Amrith Setlur, Lewis Tunstall, Edward Emanuel Beeching, Ruslan Salakhutdinov, and Aviral Kumar. 2025. Optimizing Test-Time Compute via Meta Reinforcement Fine-Tuning. arXiv preprint. [find](https://scholar.google.com/scholar?q=Yuxiao+Qu%2C+Matthew+Y%2E+R%2E+Yang%2C+Amrith+Setlur%2C+Lewis+Tunstall%2C+Edward+Emanuel+Beeching%2C+Ruslan+Salakhutdinov%2C+and+Aviral+Kumar%2E+2025%2E+Optimizing+Test%2DTime+Compute+via+Meta+Reinforcement+Fine%2DTuning%2E+ar)
20. Alec Radford, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei, and Ilya Sutskever. Language Models are Unsupervised Multitask Learners. [find](https://scholar.google.com/scholar?q=Alec+Radford%2C+Jeffrey+Wu%2C+Rewon+Child%2C+David+Luan%2C+Dario+Amodei%2C+and+Ilya+Sutskever%2E+Language+Models+are+Unsupervised+Multitask+Learners%2E)
21. Zhenyi Shen, Hanqi Yan, Linhai Zhang, Zhanghao Hu, Yali Du, and Yulan He. 2025. [CODI: Compressing Chain-of-Thought into Continuous Space via Self-Distillation](https://md.research.elamur.ai/free/en/papers/shen-2025-codi-compressing-chain-thought-into/). arXiv preprint.
22. Charlie Snell, Jaehoon Lee, Kelvin Xu, and Aviral Kumar. 2024. [Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters](https://md.research.elamur.ai/free/en/papers/snell-2024-scaling-llm-test-time-compute/). arXiv preprint.
23. Yetong Sun and 1 others. 2024. Breaking the ceiling of the llm community by treating token generation as a classification for ensembling. In Findings of the Association for Computational Linguistics: EMNLP 2024. [find](https://scholar.google.com/scholar?q=Yetong+Sun+and+1+others%2E+2024%2E+Breaking+the+ceiling+of+the+llm+community+by+treating+token+generation+as+a+classification+for+ensembling%2E+In+Findings+of+the+Association+for+Computational+Linguistics%3A+)
24. Wenhui Tan, Jiaze Li, Jianzhong Ju, Zhenbo Luo, Jian Luan, and Ruihua Song. 2025. [Think Silently, Think Fast: Dynamic Latent Compression of LLM Reasoning Chains](https://md.research.elamur.ai/free/en/papers/tan-2025-think-silently-think-fast-dynamic/). arXiv preprint.
25. Jonathan Uesato, Nate Kushman, Ramana Kumar, Francis Song, Noah Siegel, Lisa Wang, Antonia Creswell, Geoffrey Irving, and Irina Higgins. 2022. [Solving math word problems with process- and outcome-based feedback](https://md.research.elamur.ai/free/en/papers/uesato-2022-solving-math-word-problems-process/). arXiv preprint.
26. Kaiyan Zhang, Jiayuan Zhang, Haoxin Li, Xuekai Zhu, Ermo Hua, Xingtai Lv, Ning Ding, Biqing Qi, and Bowen Zhou. 2024. OpenPRM: Building Open-domain Process-based Reward Models with Preference Trees. [find](https://scholar.google.com/scholar?q=Kaiyan+Zhang%2C+Jiayuan+Zhang%2C+Haoxin+Li%2C+Xuekai+Zhu%2C+Ermo+Hua%2C+Xingtai+Lv%2C+Ning+Ding%2C+Biqing+Qi%2C+and+Bowen+Zhou%2E+2024%2E+OpenPRM%3A+Building+Open%2Ddomain+Process%2Dbased+Reward+Models+with+Preference+Trees%2E)
27. Jian Wang, Boyan Zhu, Chak Tou Leong, Yongqi Li, and Wenjie Li. 2025. Scaling over Scaling: Exploring Test-Time Scaling Plateau in Large Reasoning Models. arXiv preprint. [find](https://scholar.google.com/scholar?q=Jian+Wang%2C+Boyan+Zhu%2C+Chak+Tou+Leong%2C+Yongqi+Li%2C+and+Wenjie+Li%2E+2025%2E+Scaling+over+Scaling%3A+Exploring+Test%2DTime+Scaling+Plateau+in+Large+Reasoning+Models%2E+arXiv+preprint%2E)
28. Zhen Zhang, Xuehai He, Weixiang Yan, Ao Shen, Chenyang Zhao, Shuohang Wang, Yelong Shen, and Xin Eric Wang. 2025. [Soft Thinking: Unlocking the Reasoning Potential of LLMs in Continuous Concept Space](https://md.research.elamur.ai/free/en/papers/zhang-2025-soft-thinking-unlocking-reasoning-potential/). arXiv preprint.
29. Peiyi Wang, Lei Li, Zhihong Shao, Runxin Xu, Damai Dai, Yifei Li, Deli Chen, Yu Wu, and Zhifang Sui. 2024. [Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations](https://md.research.elamur.ai/free/en/papers/wang-2024-math-shepherd-verify-reinforce-llms/). In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Paper…
30. Xuezhi Wang, Jason Wei, Dale Schuurmans, Quoc V. Le, Ed H. Chi, Sharan Narang, Aakanksha Chowdhery, and Denny Zhou. 2022. [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://md.research.elamur.ai/free/en/papers/wang-2022-self-consistency-improves-chain-thought/).
31. Yifan Wang, Shiyu Li, Peiming Li, Xiaochen Yang, Yang Tang, and Zheng Wei. 2026. [Render-of-thought: Rendering textual chain-of-thought as images for visual latent reasoning](https://md.research.elamur.ai/free/en/papers/wang-2026-render-thought-rendering-textual-chain/). Preprint, arXiv:2601.14750.
32. 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/).
33. Haoyi Wu, Zhihao Teng, and Kewei Tu. 2025a. Parallel Continuous Chain-of-Thought with Jacobi Iteration. arXiv preprint. [find](https://scholar.google.com/scholar?q=Haoyi+Wu%2C+Zhihao+Teng%2C+and+Kewei+Tu%2E+2025a%2E+Parallel+Continuous+Chain%2Dof%2DThought+with+Jacobi+Iteration%2E+arXiv+preprint%2E)
34. Junhong Wu, Jinliang Lu, Zixuan Ren, Gangqiang Hu, Zhi Wu, Dai Dai, and Hua Wu. 2025b. Llms are single-threaded reasoners: Demystifying the working mechanism of soft thinking. arXiv preprint arXiv:2508.03440. — [arXiv:2508.03440](https://arxiv.org/abs/2508.03440) [find](https://scholar.google.com/scholar?q=Junhong+Wu%2C+Jinliang+Lu%2C+Zixuan+Ren%2C+Gangqiang+Hu%2C+Zhi+Wu%2C+Dai+Dai%2C+and+Hua+Wu%2E+2025b%2E+Llms+are+single%2Dthreaded+reasoners%3A+Demystifying+the+working+mechanism+of+soft+thinking%2E+arXiv+preprint+arXiv%3A250)
35. Yangyifan Xu, Jianghao Chen, Junhong Wu, and Jiajun Zhang. 2025a. [Hit the sweet spot! span-level ensemble for large language models](https://md.research.elamur.ai/free/en/papers/xu-2025-hit-sweet-spot-span-level/). In Proceedings of the 31st International Conference on Computational Linguistics (COLING).
36. Yige Xu, Xu Guo, Zhiwei Zeng, and Chunyan Miao. 2025b. SoftCoT++: Test-Time Scaling with Soft Chain-of-Thought Reasoning. arXiv preprint. [find](https://scholar.google.com/scholar?q=Yige+Xu%2C+Xu+Guo%2C+Zhiwei+Zeng%2C+and+Chunyan+Miao%2E+2025b%2E+SoftCoT%2B%2B%3A+Test%2DTime+Scaling+with+Soft+Chain%2Dof%2DThought+Reasoning%2E+arXiv+preprint%2E)
37. An Yang, Anfeng Li, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Gao, Chengen Huang, Chenxu Lv, Chujie Zheng, Dayiheng Liu, Fan Zhou, Fei Huang, Feng Hu, Hao Ge, Haoran Wei, Huan Lin, Jialong Tang, and 41 others. 2025. [Qwen3 Technical Report](https://md.research.elamur.ai/free/en/papers/yang-2025-qwen3-technical-report/). arXiv preprint.
38. Runyang You, Yongqi Li, Xinyu Lin, Xin Zhang, Wenjie Wang, Wenjie Li, and Liqiang Nie. 2025. $\\text{R}^2\\text{ec}$: Towards Large Recommender Models with Reasoning. arXiv preprint. [find](https://scholar.google.com/scholar?q=Runyang+You%2C+Yongqi+Li%2C+Xinyu+Lin%2C+Xin+Zhang%2C+Wenjie+Wang%2C+Wenjie+Li%2C+and+Liqiang+Nie%2E+2025%2E+%24%5C%5Ctext%7BR%7D%5E2%5C%5Ctext%7Bec%7D%24%3A+Towards+Large+Recommender+Models+with+Reasoning%2E+arXiv+preprint%2E)
39. Yilun Zhao and 1 others. 2024. Bridging the gap between different vocabularies for llm ensemble. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics (NAACL). [find](https://scholar.google.com/scholar?q=Yilun+Zhao+and+1+others%2E+2024%2E+Bridging+the+gap+between+different+vocabularies+for+llm+ensemble%2E+In+Proceedings+of+the+2024+Conference+of+the+North+American+Chapter+of+the+Association+for+Computationa)
40. Denny Zhou, Nathanael Schärli, Le Hou, Jason Wei, Nathan Scales, Xuezhi Wang, Dale Schuurmans, Claire Cui, Olivier Bousquet, Quoc V. Le, and Ed H. Chi. 2022. [Least-to-Most Prompting Enables Complex Reasoning in Large Language Models](https://md.research.elamur.ai/free/en/papers/al-2022-least-most-prompting-enables-complex/).
41. Rui-Jie Zhu, Tianhao Peng, Tianhao Cheng, Xingwei Qu, Jinfa Huang, Dawei Zhu, Hao Wang, Kaiwen Xue, Xuanliang Zhang, Yong Shan, Tianle Cai, Taylor Kergan, Assel Kembay, Andrew Smith, Chenghua Lin, Binh Nguyen, Yuqi Pan, Yuhong Chou, Zefan Cai, and 14 others. 2025. [A Survey on Latent Reasoning](https://md.research.elamur.ai/free/en/papers/zhu-2025-survey-latent-reasoning/). arXiv…

*Updated 2 November 2026*