---
title: "No One Fits All — paper by Wu et al. (2026) — summary and ideas"
description: "The authors first compare six zero-shot prompting strategies on Global-MMLU across ten languages divided into three… 33 references."
authors: ["Wei-Chi Wu", "Sheng-Lun Wei", "Hen-Hsen Huang", "Hsin-Hsi Chen"]
year: 2026
venue: "Findings of the Association for Computational Linguistics: ACL 2026"
source: "https://aclanthology.org/2026.findings-acl.1864/"
doi: "10.18653/v1/2026.findings-acl.1864"
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/wu-2026-no-one-fits-all-fixed/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/wu-2026-no-one-fits-all-fixed/)

[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/43/) / No One Fits All: From Fixed Prompting to Learned Routing in Multilingual LLMs

# No One Fits All: From Fixed Prompting to Learned Routing in Multilingual LLMs

**Authors:** Wei-Chi Wu, [Sheng-Lun Wei](https://md.research.elamur.ai/free/en/authors/sheng-lun-wei/), [Hen-Hsen Huang](https://md.research.elamur.ai/free/en/authors/hen-hsen-huang/) and [Hsin-Hsi Chen](https://md.research.elamur.ai/free/en/authors/hsin-hsi-chen/) · **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.1864/) · [PDF](https://aclanthology.org/2026.findings-acl.1864.pdf) · [DOI 10.18653/v1/2026.findings-acl.1864](https://doi.org/10.18653/v1/2026.findings-acl.1864) · [OpenAlex](https://openalex.org/W7166834077)

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

## Summary
Translating non-English inputs into English before querying a multilingual LLM is a common trick, but it does not help every language or task equally. The authors first compare six zero-shot prompting strategies on Global-MMLU across ten languages divided into three resource tiers: ZH, ES, DE and HI count as high-resource, BN, ID and KO as mid-resource, and SI, SW and YO as low-resource. No strategy wins everywhere. Translation helps low-resource languages a lot and high-resource ones barely at all, and letting the model pick its own route through a prompt performs worse than always translating. They therefore treat the choice between NATIVE and TRANSLATE prompting as a per-instance classification task. Lightweight classifiers (XGBoost, MLP) use features that compare the native and translated questions and the answers produced under each strategy. Tested with DeepSeek-v3.1 and Llama-3.3-70B, the classifiers beat both fixed strategies by small but statistically significant margins. They also transfer to task formats never seen in training. A further analysis indicates that a language's resource level, more than translation quality, decides when translation pays off.

## Key points
- **Evaluation setup:** Global-MMLU is the main benchmark, with 10% of it used to train the router. Generalization is tested on MMLU-ProX and on three out-of-domain formats: XQuAD (extractive QA), mCSQA and XCOPA. Training labels come only from cases where exactly one of the two strategies answers correctly.
- **Fixed strategies (Llama-3.3-70B, Global-MMLU):**
  - English Strategic CoT has the best average at about 84.0%, yet different strategies win for individual languages.
  - Model self-routing (82.8%) falls short of plain TRANSLATE (84.0%).
  - Korean shows an extreme gap of roughly 50 points between native and translated prompting.
- **Router results (XGBoost on DeepSeek-v3.1):**
  - Global-MMLU: 82.3%, compared with 81.7% for TRANSLATE and 72.5% for NATIVE.
  - Out-of-domain: XQuAD 87.6%, XCOPA 95.7%, and mCSQA 33.8% versus 33.4%.
  - Wilcoxon signed-rank tests give p \< 0.001 for XGBoost and p \< 0.05 for MLP.
- **What drives the decisions:** word-overlap features are the most important group for both models. When the data are split into chrF quality deciles, the router picks translation most often where translation quality is lowest (about 83.5% vs. 75.2% on DeepSeek). This pattern reflects low-resource languages clustering in those bins.
- **Main limitation:** both native and translated outputs must be generated before routing, which doubles inference cost. The study also covers only ten languages and does not test culturally grounded tasks.

*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

- [Academia Sinica](https://md.research.elamur.ai/free/en/labs/academia-sinica/) — Research institute, Taipei, Taiwan · 13 works · 11,163 citations
- [National Taiwan University](https://md.research.elamur.ai/free/en/universities/national-taiwan-university/) — University, Taipei, Taiwan · 32 works · 2,116 citations
- [Institute of Information Science, Academia Sinica](https://md.research.elamur.ai/free/en/labs/institute-of-information-science-academia-sinica/) — Research institute, Taipei, Taiwan · 8 works · 51 citations

📚 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 (2): [🧠 Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/) · 3,894 works · [🌍 Multilingual & cross-lingual NLP](https://md.research.elamur.ai/free/en/topics/multilingual-nlp/) · 882 works

## Cite

Cite as: Wei-Chi Wu, Sheng-Lun Wei, Hen-Hsen Huang and Hsin-Hsi Chen. 2026. No One Fits All: From Fixed Prompting to Learned Routing in Multilingual LLMs. 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{wu2026no,
  title = {{No One Fits All: From Fixed Prompting to Learned Routing in Multilingual LLMs}},
  author = {Wei-Chi Wu, Sheng-Lun Wei, Hen-Hsen Huang and Hsin-Hsi Chen},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.1864},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.1864}
}
```

- [← previous No Label? No Problem: Unsupervised Continual Learning for Adaptive Medical ASR](https://md.research.elamur.ai/free/en/papers/liu-2026-no-label-no-problem-unsupervised/)
- [next → No Overfit at NakbaArchiveClassifier Shared Task: A Swin Transformer-Based System for Destruction Image Classification](https://md.research.elamur.ai/free/en/papers/mohamed-2026-no-overfit-nakbaarchiveclassifier-shared-task/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/43/)

## References

33 references, 17 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. AI@Meta. 2024. Llama 3 model card. [find](https://scholar.google.com/scholar?q=AI%40Meta%2E+2024%2E+Llama+3+model+card%2E)
2. Takuya Akiba, Shotaro Sano, Toshihiko Yanase, Takeru Ohta, and Masanori Koyama. 2019. [Optuna: A next-generation hyperparameter optimization framework](https://md.research.elamur.ai/free/en/papers/akiba-2019-optuna-next-generation-hyperparameter-optimization/). Preprint, arXiv:1907.10902.
3. Mikel Artetxe, Sebastian Ruder, and Dani Yogatama. 2020. [On the cross-lingual transferability of monolingual representations](https://md.research.elamur.ai/free/en/papers/artetxe-2020-cross-lingual-transferability-monolingual-representations/). In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics.
4. Satanjeev Banerjee and Alon Lavie. 2005. [METEOR: An automatic metric for MT evaluation with improved correlation with human judgments](https://md.research.elamur.ai/free/en/papers/banerjee-2005-meteor-automatic-metric-mt-evaluation/). In Proceedings of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and/or Summarization, pages 65–72, Ann Arbor, Michigan. Ass…
5. Tianqi Chen and Carlos Guestrin. 2016. Xgboost: A scalable tree boosting system. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD ’16, page 785–794. ACM. [find](https://scholar.google.com/scholar?q=Tianqi+Chen+and+Carlos+Guestrin%2E+2016%2E+Xgboost%3A+A+scalable+tree+boosting+system%2E+In+Proceedings+of+the+22nd+ACM+SIGKDD+International+Conference+on+Knowledge+Discovery+and+Data+Mining%2C+KDD+%E2%80%9916%2C+page+78)
6. DeepSeek-AI. 2024. Deepseek-v3 technical report. Preprint, arXiv:2412.19437. [find](https://scholar.google.com/scholar?q=DeepSeek%2DAI%2E+2024%2E+Deepseek%2Dv3+technical+report%2E+Preprint%2C+arXiv%3A2412%2E19437%2E)
7. Fangxiaoyu Feng, Yinfei Yang, Daniel Cer, Naveen Arivazhagan, and Wei Wang. 2022. [Language-agnostic BERT sentence embedding](https://md.research.elamur.ai/free/en/papers/feng-2020-language-agnostic-bert-sentence-embedding/). In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 878–891, Dublin, Ireland. Association for Computation…
8. Akash Ghosh, Debayan Datta, Sriparna Saha, and Chirag Agarwal. 2025. A survey of multilingual reasoning in language models. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 8920–8936, Suzhou, China. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Akash+Ghosh%2C+Debayan+Datta%2C+Sriparna+Saha%2C+and+Chirag+Agarwal%2E+2025%2E+A+survey+of+multilingual+reasoning+in+language+models%2E+In+Findings+of+the+Association+for+Computational+Linguistics%3A+EMNLP+2025%2C+pa)
9. Simon Haykin. 1994. Neural networks: a comprehensive foundation. Prentice Hall PTR. [find](https://scholar.google.com/scholar?q=Simon+Haykin%2E+1994%2E+Neural+networks%3A+a+comprehensive+foundation%2E+Prentice+Hall+PTR%2E)
10. Haoyang Huang, Tianyi Tang, Dongdong Zhang, Xin Zhao, Ting Song, Yan Xia, and Furu Wei. 2023. [Not all languages are created equal in LLMs: Improving multilingual capability by cross-lingual-thought prompting](https://md.research.elamur.ai/free/en/papers/huang-2023-all-languages-created-equal-llms/). In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 12365– 1239…
11. Yotam Intrator, Matan Halfon, Roman Goldenberg, Reut Tsarfaty, Matan Eyal, Ehud Rivlin, Yossi Matias, and Natalia Aizenberg. 2024. Breaking the language barrier: Can direct inference outperform pre-translation in multilingual LLM applications? In Proceedings of the 2024 Conference of the North Ameri… [find](https://scholar.google.com/scholar?q=Yotam+Intrator%2C+Matan+Halfon%2C+Roman+Goldenberg%2C+Reut+Tsarfaty%2C+Matan+Eyal%2C+Ehud+Rivlin%2C+Yossi+Matias%2C+and+Natalia+Aizenberg%2E+2024%2E+Breaking+the+language+barrier%3A+Can+direct+inference+outperform+pre%2Dtr)
12. Philipp Koehn and Rebecca Knowles. 2017. Six challenges for neural machine translation. In Proceedings of the First Workshop on Neural Machine Translation, pages 28–39, Vancouver. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Philipp+Koehn+and+Rebecca+Knowles%2E+2017%2E+Six+challenges+for+neural+machine+translation%2E+In+Proceedings+of+the+First+Workshop+on+Neural+Machine+Translation%2C+pages+28%E2%80%9339%2C+Vancouver%2E+Association+for+Comp)
13. Nidhi Kowtal, Tejas Deshpande, and Raviraj Joshi. 2024. Chain-of-translation prompting (CoTR): A novel prompting technique for low resource languages. In Proceedings of the 38th Pacific Asia Conference on Language, Information and Computation, pages 645– 655, Tokyo, Japan. Tokyo University of Foreig… [find](https://scholar.google.com/scholar?q=Nidhi+Kowtal%2C+Tejas+Deshpande%2C+and+Raviraj+Joshi%2E+2024%2E+Chain%2Dof%2Dtranslation+prompting+%28CoTR%29%3A+A+novel+prompting+technique+for+low+resource+languages%2E+In+Proceedings+of+the+38th+Pacific+Asia+Conferenc)
14. Huiyuan Lai and Malvina Nissim. 2024. [mCoT: Multilingual instruction tuning for reasoning consistency in language models](https://md.research.elamur.ai/free/en/papers/lai-2024-mcot-multilingual-instruction-tuning-reasoning/). In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 12012– 12026, Bangkok, Thailand. Association for Computa…
15. Zihao Li, Yucheng Shi, Zirui Liu, Fan Yang, Ali Payani, Ninghao Liu, and Mengnan Du. 2024. [Language ranker: A metric for quantifying llm performance across high and low-resource languages](https://md.research.elamur.ai/free/en/papers/li-2024-language-ranker-metric-quantifying-llm/). Preprint, arXiv:2404.11553.
16. Chaoqun Liu, Wenxuan Zhang, Yiran Zhao, Anh Tuan Luu, and Lidong Bing. 2025. [Is translation all you need? a study on solving multilingual tasks with large language models](https://md.research.elamur.ai/free/en/papers/liu-2025-is-translation-all-you-need/). In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: H…
17. Itai Mondshine, Tzuf Paz-Argaman, and Reut Tsarfaty. 2025. Beyond English: The impact of prompt translation strategies across languages and tasks in multilingual LLMs. In Findings of the Association for Computational Linguistics: NAACL 2025, pages 1331– 1354, Albuquerque, New Mexico. Association for… [find](https://scholar.google.com/scholar?q=Itai+Mondshine%2C+Tzuf+Paz%2DArgaman%2C+and+Reut+Tsarfaty%2E+2025%2E+Beyond+English%3A+The+impact+of+prompt+translation+strategies+across+languages+and+tasks+in+multilingual+LLMs%2E+In+Findings+of+the+Association+f)
18. Jean De Dieu Nyandwi, Yueqi Song, Simran Khanuja, and Graham Neubig. 2025. [Grounding multilingual multimodal LLMs with cultural knowledge](https://md.research.elamur.ai/free/en/papers/nyandwi-2025-grounding-multilingual-multimodal-llms-cultural/). In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 24198– 24242, Suzhou, China. Association for Computational Lingu…
19. Rakesh Paul, Anusha Kamath, Kanishk Singla, Raviraj Joshi, Utkarsh Vaidya, Sanjay Singh Chauhan, and Niranjan Wartikar. 2025. Aligning large language models to low-resource languages through llm-based selective translation: A systematic study. Preprint, arXiv:2507.14304. [find](https://scholar.google.com/scholar?q=Rakesh+Paul%2C+Anusha+Kamath%2C+Kanishk+Singla%2C+Raviraj+Joshi%2C+Utkarsh+Vaidya%2C+Sanjay+Singh+Chauhan%2C+and+Niranjan+Wartikar%2E+2025%2E+Aligning+large+language+models+to+low%2Dresource+languages+through+llm%2Dbased)
20. Edoardo Maria Ponti, Goran Glavaš, Olga Majewska, Qianchu Liu, Ivan Vulić, and Anna Korhonen. 2020. [XCOPA: A multilingual dataset for causal commonsense reasoning](https://md.research.elamur.ai/free/en/papers/ponti-2020-xcopa-multilingual-dataset-causal-commonsense/). In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 2362–2376, Online. Association…
21. Maja Popović. 2015. [chrF: character n-gram F-score for automatic MT evaluation](https://md.research.elamur.ai/free/en/papers/popovic-2015-chrf-character-n-gram-f/). In Proceedings of the Tenth Workshop on Statistical Machine Translation, pages 392–395, Lisbon, Portugal. Association for Computational Linguistics.
22. Peng Qi, Yuhao Zhang, Yuhui Zhang, Jason Bolton, and Christopher D. Manning. 2020. [Stanza: A python natural language processing toolkit for many human languages](https://md.research.elamur.ai/free/en/papers/qi-2020-stanza-python-natural-language-processing/). In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations, pages 101–108, Online.…
23. Yusuke Sakai, Hidetaka Kamigaito, and Taro Watanabe. 2024. mCSQA: Multilingual commonsense reasoning dataset with unified creation strategy by language models and humans. In Findings of the Association for Computational Linguistics: ACL 2024, pages 14182–14214, Bangkok, Thailand. Association for Com… [find](https://scholar.google.com/scholar?q=Yusuke+Sakai%2C+Hidetaka+Kamigaito%2C+and+Taro+Watanabe%2E+2024%2E+mCSQA%3A+Multilingual+commonsense+reasoning+dataset+with+unified+creation+strategy+by+language+models+and+humans%2E+In+Findings+of+the+Associatio)
24. Thibault Sellam, Dipanjan Das, and Ankur Parikh. 2020. [BLEURT: Learning robust metrics for text generation](https://md.research.elamur.ai/free/en/papers/sellam-2020-bleurt-learning-robust-metrics-text/). In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 7881–7892, Online. Association for Computational Linguistics.
25. Uri Shaham, Jonathan Herzig, Roee Aharoni, Idan Szpektor, Reut Tsarfaty, and Matan Eyal. 2024. [Multilingual instruction tuning with just a pinch of multilinguality](https://md.research.elamur.ai/free/en/papers/shaham-2024-multilingual-instruction-tuning-just-pinch/). In Findings of the Association for Computational Linguistics: ACL 2024, pages 2304–2317, Bangkok, Thailand. Association for Computation…
26. Shivalika Singh, Angelika Romanou, Clémentine Fourrier, David Ifeoluwa Adelani, Jian Gang Ngui, Daniel Vila-Suero, Peerat Limkonchotiwat, Kelly Marchisio, Wei Qi Leong, Yosephine Susanto, Raymond Ng, Shayne Longpre, Sebastian Ruder, Wei-Yin Ko, Antoine Bosselut, Alice Oh, Andre Martins, Leshem Chosh… — [Global MMLU: Understanding and Addressing Cultural and Linguistic Biases in Multilingual Evaluation](https://md.research.elamur.ai/free/en/papers/singh-2025-global-mmlu-understanding-addressing-cultural/)
27. Zhi Rui Tam, Cheng-Kuang Wu, Yu Ying Chiu, Chieh-Yen Lin, Yun-Nung Chen, and Hung yi Lee. 2025. [Language matters: How do multilingual input and reasoning paths affect large reasoning models?](https://md.research.elamur.ai/free/en/papers/tam-2025-language-matters-multilingual-input-reasoning/) Preprint, arXiv:2505.17407.
28. NLLB Team, Marta R. Costa-jussà, James Cross, Onur Çelebi, Maha Elbayad, Kenneth Heafield, Kevin Heffernan, Elahe Kalbassi, Janice Lam, Daniel Licht, Jean Maillard, Anna Sun, Skyler Wang, Guillaume Wenzek, Al Youngblood, Bapi Akula, Loic Barrault, Gabriel Mejia Gonzalez, Prangthip Hansanti, and 20 o… [find](https://scholar.google.com/scholar?q=NLLB+Team%2C+Marta+R%2E+Costa%2Djuss%C3%A0%2C+James+Cross%2C+Onur+%C3%87elebi%2C+Maha+Elbayad%2C+Kenneth+Heafield%2C+Kevin+Heffernan%2C+Elahe+Kalbassi%2C+Janice+Lam%2C+Daniel+Licht%2C+Jean+Maillard%2C+Anna+Sun%2C+Skyler+Wang%2C+Guillaume+We)
29. Yu Wang, Shiwan Zhao, Zhihu Wang, Heyuan Huang, Ming Fan, Yubo Zhang, Zhixing Wang, Haijun Wang, and Ting Liu. 2024. Strategic chain-of-thought: Guiding accurate reasoning in LLMs through strategy elicitation. Computing Research Repository, arXiv:2409.03271. — [arXiv:2409.03271](https://arxiv.org/abs/2409.03271) [find](https://scholar.google.com/scholar?q=Yu+Wang%2C+Shiwan+Zhao%2C+Zhihu+Wang%2C+Heyuan+Huang%2C+Ming+Fan%2C+Yubo+Zhang%2C+Zhixing+Wang%2C+Haijun+Wang%2C+and+Ting+Liu%2E+2024%2E+Strategic+chain%2Dof%2Dthought%3A+Guiding+accurate+reasoning+in+LLMs+through+strategy+eli)
30. Frank Wilcoxon. 1945. Individual comparisons by ranking methods. Biometrics Bulletin, 1(6):80–83. [find](https://scholar.google.com/scholar?q=Frank+Wilcoxon%2E+1945%2E+Individual+comparisons+by+ranking+methods%2E+Biometrics+Bulletin%2C+1%286%29%3A80%E2%80%9383%2E)
31. Weihao Xuan, Rui Yang, Heli Qi, Qingcheng Zeng, Yunze Xiao, Aosong Feng, Dairui Liu, Yun Xing, Junjue Wang, Fan Gao, Jinghui Lu, Yuang Jiang, Huitao Li, Xin Li, Kunyu Yu, Ruihai Dong, Shangding Gu, Yuekang Li, Xiaofei Xie, and 13 others. 2025. [MMLU-ProX: A multilingual benchmark for advanced large l…](https://md.research.elamur.ai/free/en/papers/xuan-2025-mmlu-prox-multilingual-benchmark-advanced/)
32. Wenhao Zhu, Shujian Huang, Fei Yuan, Shuaijie She, Jiajun Chen, and Alexandra Birch. 2024. Question translation training for better multilingual reasoning. In Findings of the Association for Computational Linguistics: ACL 2024, pages 8411–8423, Bangkok, Thailand. Association for Computational Lingui… [find](https://scholar.google.com/scholar?q=Wenhao+Zhu%2C+Shujian+Huang%2C+Fei+Yuan%2C+Shuaijie+She%2C+Jiajun+Chen%2C+and+Alexandra+Birch%2E+2024%2E+Question+translation+training+for+better+multilingual+reasoning%2E+In+Findings+of+the+Association+for+Computati)
33. Peng Shu, Junhao Chen, Zhengliang Liu, Hui Wang, Zihao Wu, Tianyang Zhong, Yiwei Li, Huaqin Zhao, Hanqi Jiang, Yi Pan, Yifan Zhou, Constance Owl, Xiaoming Zhai, Ninghao Liu, Claudio Saunt, and Tianming Liu. 2024. Transcending language boundaries: Harnessing llms for low-resource language translation… — [arXiv:2411.11295](https://arxiv.org/abs/2411.11295) [find](https://scholar.google.com/scholar?q=Peng+Shu%2C+Junhao+Chen%2C+Zhengliang+Liu%2C+Hui+Wang%2C+Zihao+Wu%2C+Tianyang+Zhong%2C+Yiwei+Li%2C+Huaqin+Zhao%2C+Hanqi+Jiang%2C+Yi+Pan%2C+Yifan+Zhou%2C+Constance+Owl%2C+Xiaoming+Zhai%2C+Ninghao+Liu%2C+Claudio+Saunt%2C+and+Tianmin)

*Updated 2 November 2026*