---
title: "T1: Advancing Language Model Reasoning through"
description: "Open LLMs trained mainly by imitating curated reasoning traces gain little from extra test-time compute. 40 references, cited by 28 papers here."
authors: ["Zhenyu Hou", "Xin Lv", "Rui Lu", "Jiajie Zhang", "Yujiang Li", "Zijun Yao", "Juanzi Li", "Jie Tang", "Yuxiao Dong"]
year: 2025
venue: "arXiv:2501.11651"
source: "https://arxiv.org/abs/2501.11651"
doi: "10.48550/arxiv.2501.11651"
arxiv: "2501.11651"
licence: "CC BY 4.0 (arXiv)"
licence_url: "http://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/hou-2025-t1-advancing-language-model-reasoning/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/hou-2025-t1-advancing-language-model-reasoning/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2025](https://md.research.elamur.ai/free/en/papers/2025/page/5/) / T1: Advancing Language Model Reasoning through Reinforcement Learning and Inference Scaling

# T1: Advancing Language Model Reasoning through Reinforcement Learning and Inference Scaling

**Authors:** [Zhenyu Hou](https://md.research.elamur.ai/free/en/authors/zhenyu-hou/), [Xin Lv](https://md.research.elamur.ai/free/en/authors/xin-lv/), [Rui Lu](https://md.research.elamur.ai/free/en/authors/rui-lu/), [Jiajie Zhang](https://md.research.elamur.ai/free/en/authors/jiajie-zhang/), [Yujiang Li](https://md.research.elamur.ai/free/en/authors/yujiang-li/), [Zijun Yao](https://md.research.elamur.ai/free/en/authors/zijun-yao/), [Juanzi Li](https://md.research.elamur.ai/free/en/authors/juanzi-li/), [Jie Tang](https://md.research.elamur.ai/free/en/authors/jie-tang/) and [Yuxiao Dong](https://md.research.elamur.ai/free/en/authors/yuxiao-dong/) · **Year:** 2025 · **Venue:** arXiv:2501.11651 · **Licence:** [CC BY 4.0 (arXiv)](http://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://arxiv.org/abs/2501.11651) · [PDF](https://arxiv.org/pdf/2501.11651) · [DOI 10.48550/arxiv.2501.11651](https://doi.org/10.48550/arxiv.2501.11651) · [arXiv 2501.11651](https://arxiv.org/abs/2501.11651) · [OpenAlex](https://openalex.org/W4406735891)

**Citations:** 0 citations (OpenAlex, 2026-10-14) · [28](https://md.research.elamur.ai/free/en/papers/hou-2025-t1-advancing-language-model-reasoning/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
Open LLMs trained mainly by imitating curated reasoning traces gain little from extra test-time compute. Earlier RL attempts on hard reasoning produced only small gains that did not scale well. Repeated sampling with external verifiers also leaves the policy unchanged. T1, from Tsinghua University and ZhipuAI (ICML 2025), addresses this by putting exploration at the centre of RL.

The model is first fine-tuned on synthetic chain-of-thought data that deliberately includes failed attempts, retries and self-checks, which widens the space the policy can explore. RL then samples many high-temperature responses per prompt and adds a token-level entropy bonus and on-policy KL normalization. Penalties on repetitive or garbled output keep training stable.

The authors also split intermediate reasoning from the final answer, so the thinking budget can be truncated and its effect measured. Built on Qwen and GLM, T1 becomes more accurate on math benchmarks as generation length grows, without any verifier. This effect strengthens with more RL steps. The work shows that long-thinking behaviour can emerge without distilled o1-style traces.

## Key points
- T1 built on Qwen2.5-32B outperforms Qwen QwQ-32B-Preview on MATH500, AIME2024 and Omni-MATH-500.
- On AIME2024, budgets ranging from 1024 to 16,384 tokens show that inference scaling becomes stronger with more RL training. The T1-SFT model and early checkpoints (around 30% of RL steps) improve only marginally.
- RL scaling relies on four ingredients: oversampling at high temperature, an entropy bonus, on-policy KL normalization, and penalties for repetition or nonsense.
- Key reasoning steps often contain words such as "wait", "perhaps" and "alternate", which points to reflection as a driver of the gains.
- Model weights and the SFT and RL data are released at github.com/THUDM/T1.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 19,503 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 18,805 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 17,959 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 17,789 works

🧭 Topics (2): [🧠 Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/) · 4,145 works · [🧮 Reasoning](https://md.research.elamur.ai/free/en/topics/reasoning/) · 1,948 works

## Cite

Cite as: Zhenyu Hou, Xin Lv, Rui Lu, Jiajie Zhang, Yujiang Li, Zijun Yao, Juanzi Li, Jie Tang and Yuxiao Dong. 2025. T1: Advancing Language Model Reasoning through Reinforcement Learning and Inference Scaling. arXiv:2501.11651.

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

```bibtex
@misc{hou2025t1,
  title = {{T1: Advancing Language Model Reasoning through Reinforcement Learning and Inference Scaling}},
  author = {Zhenyu Hou, Xin Lv, Rui Lu, Jiajie Zhang, Yujiang Li, Zijun Yao, Juanzi Li, Jie Tang and Yuxiao Dong},
  year = {2025},
  doi = {10.48550/arxiv.2501.11651},
  eprint = {2501.11651},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2501.11651}
}
```

- [← previous Seed Diffusion: A Large-Scale Diffusion Language Model with High-Speed Inference](https://md.research.elamur.ai/free/en/papers/song-2025-seed-diffusion-large-scale/)
- [next → Which of These Best Describes Multiple Choice Evaluation with LLMs? A) Forced B) Flawed C) Fixable D) All of the Above](https://md.research.elamur.ai/free/en/papers/balepur-2025-which-these-best-describes-multiple/)
- [↑ back to papers of 2025](https://md.research.elamur.ai/free/en/papers/2025/page/5/)

## References

40 references, 30 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Achiam, J., Adler, S., Agarwal, S., Ahmad, L., Akkaya, I., Aleman, F. L., Almeida, D., Altenschmidt, J., Altman, S., Anadkat, S., et al. [Gpt-4 technical report](https://md.research.elamur.ai/free/en/papers/openai-2023-gpt-4-technical-report/). arXiv preprint arXiv:2303.08774, 2023.
2. Hendrycks, D., Burns, C., Kadavath, S., Arora, A., Basart, S., Tang, E., Song, D., and Steinhardt, J. [Measuring mathematical problem solving with the math dataset](https://md.research.elamur.ai/free/en/papers/hendrycks-2021-measuring-mathematical-problem-solving-math/). NeurIPS, 2021.
3. Ahmadian, A., Cremer, C., Gallé, M., Fadaee, M., Kreutzer, J., Üstün, A., and Hooker, S. Back to basics: Revisiting reinforce style optimization for learning from human feedback in llms. In ACL, 2024. [find](https://scholar.google.com/scholar?q=Ahmadian%2C+A%2E%2C+Cremer%2C+C%2E%2C+Gall%C3%A9%2C+M%2E%2C+Fadaee%2C+M%2E%2C+Kreutzer%2C+J%2E%2C+%C3%9Cst%C3%BCn%2C+A%2E%2C+and+Hooker%2C+S%2E+Back+to+basics%3A+Revisiting+reinforce+style+optimization+for+learning+from+human+feedback+in+llms%2E+In+ACL%2C+2024%2E)
4. Hoffmann, J., Borgeaud, S., Mensch, A., Buchatskaya, E., Cai, T., Rutherford, E., Casas, D. d. L., Hendricks, L. A., Welbl, J., Clark, A., et al. [Training compute-optimal large language models](https://md.research.elamur.ai/free/en/papers/hoffmann-2022-training-compute-optimal-large-language/). arXiv preprint arXiv:2203.15556, 2022.
5. An, S., Ma, Z., Lin, Z., Zheng, N., Lou, J.-G., and Chen, W. [Learning from mistakes makes llm better reasoner](https://md.research.elamur.ai/free/en/papers/an-2023-learning-mistakes-makes-llm-better/). arXiv preprint arXiv:2310.20689, 2023.
6. Bai, Y., Jones, A., Ndousse, K., Askell, A., Chen, A., Das-Sarma, N., Drain, D., Fort, S., Ganguli, D., Henighan, T., et al. Training a helpful and harmless assistant with reinforcement learning from human feedback. arXiv preprint arXiv:2204.05862, 2022. [find](https://scholar.google.com/scholar?q=Bai%2C+Y%2E%2C+Jones%2C+A%2E%2C+Ndousse%2C+K%2E%2C+Askell%2C+A%2E%2C+Chen%2C+A%2E%2C+Das%2DSarma%2C+N%2E%2C+Drain%2C+D%2E%2C+Fort%2C+S%2E%2C+Ganguli%2C+D%2E%2C+Henighan%2C+T%2E%2C+et+al%2E+Training+a+helpful+and+harmless+assistant+with+reinforcement+learning+from+)
7. Hou, Z., Du, P., Niu, Y., Du, Z., Zeng, A., Liu, X., Huang, M., Wang, H., Tang, J., and Dong, Y. Does rlhf scale? exploring the impacts from data, model, and method. arXiv preprint arXiv:2412.06000, 2024. — [arXiv:2412.06000](https://arxiv.org/abs/2412.06000) [find](https://scholar.google.com/scholar?q=Hou%2C+Z%2E%2C+Du%2C+P%2E%2C+Niu%2C+Y%2E%2C+Du%2C+Z%2E%2C+Zeng%2C+A%2E%2C+Liu%2C+X%2E%2C+Huang%2C+M%2E%2C+Wang%2C+H%2E%2C+Tang%2C+J%2E%2C+and+Dong%2C+Y%2E+Does+rlhf+scale%3F+exploring+the+impacts+from+data%2C+model%2C+and+method%2E+arXiv+preprint+arXiv%3A2412%2E06000%2C+2)
8. Kaplan, J., McCandlish, S., Henighan, T., Brown, T. B., Chess, B., Child, R., Gray, S., Radford, A., Wu, J., and Amodei, D. [Scaling laws for neural language models](https://md.research.elamur.ai/free/en/papers/kaplan-2020-scaling-laws-neural-language-models/). arXiv preprint arXiv:2001.08361, 2020.
9. Brown, B., Juravsky, J., Ehrlich, R., Clark, R., Le, Q. V., Ré, C., and Mirhoseini, A. [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 arXiv:2407.21787, 2024.
10. Kazemnejad, A., Aghajohari, M., Portelance, E., Sordoni, A., Reddy, S., Courville, A., and Roux, N. L. Vineppo: Unlocking rl potential for llm reasoning through refined credit assignment. arXiv preprint arXiv:2410.[01679, 2024](https://md.research.elamur.ai/free/en/papers/kazemnejad-2024-vineppo-refining-credit-assignment-rl/).
11. Cobbe, K., Kosaraju, V., Bavarian, M., Chen, M., Jun, H., Kaiser, L., Plappert, M., Tworek, J., Hilton, J., Nakano, R., et al. [Training verifiers to solve math word problems](https://md.research.elamur.ai/free/en/papers/cobbe-2021-training-verifiers-solve-math-word/). arXiv preprint arXiv:2110.14168, 2021.
12. Kumar, A., Zhuang, V., Agarwal, R., Su, Y., Co-Reyes, J. D., Singh, A., Baumli, K., Iqbal, S., Bishop, C., Roelofs, R., et al. [Training language models to self-correct via reinforcement learning](https://md.research.elamur.ai/free/en/papers/kumar-2024-training-language-models-self-correct/). arXiv preprint arXiv:2409.12917, 2024.
13. Rafailov, R., Chittepu, Y., Park, R., Sikchi, H., Hejna, J., Knox, B., Finn, C., and Niekum, S. Scaling laws for reward model overoptimization in direct alignment algorithms. arXiv preprint arXiv:2406.02900, 2024a. — [arXiv:2406.02900](https://arxiv.org/abs/2406.02900) [find](https://scholar.google.com/scholar?q=Rafailov%2C+R%2E%2C+Chittepu%2C+Y%2E%2C+Park%2C+R%2E%2C+Sikchi%2C+H%2E%2C+Hejna%2C+J%2E%2C+Knox%2C+B%2E%2C+Finn%2C+C%2E%2C+and+Niekum%2C+S%2E+Scaling+laws+for+reward+model+overoptimization+in+direct+alignment+algorithms%2E+arXiv+preprint+arXiv%3A2406)
14. Rafailov, R., Sharma, A., Mitchell, E., Manning, C. D., Ermon, S., and Finn, C. [Direct preference optimization: Your language model is secretly a reward model](https://md.research.elamur.ai/free/en/papers/rafailov-2023-direct-preference-optimization-language-model/). Advances in Neural Information Processing Systems, 2024b.
15. Lewkowycz, A., Andreassen, A., Dohan, D., Dyer, E., Michalewski, H., Ramasesh, V., Slone, A., Anil, C., Schlag, I., Gutman-Solo, T., et al. [Solving quantitative reasoning problems with language models](https://md.research.elamur.ai/free/en/papers/lewkowycz-2022-solving-quantitative-reasoning-problems-language/). Advances in Neural Information Processing Systems, 35:3843–3857, 2022.
16. Rein, D., Hou, B. L., Stickland, A. C., Petty, J., Pang, R. Y., Dirani, J., Michael, J., and Bowman, S. R. [Gpqa: A graduate-level google-proof q&a benchmark](https://md.research.elamur.ai/free/en/papers/rein-2023-gpqa-graduate-level-google-proof/). arXiv preprint arXiv:2311.12022, 2023.
17. Li, C., Wang, W., Hu, J., Wei, Y., Zheng, N., Hu, H., Zhang, Z., and Peng, H. [Common 7b language models already possess strong math capabilities](https://md.research.elamur.ai/free/en/papers/li-2024-common-7b-language-models-already/). arXiv preprint arXiv:2403.04706, 2024a.
18. Shao, Z., Wang, P., Zhu, Q., Xu, R., Song, J., Zhang, M., Li, Y., Wu, Y., and Guo, D. [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/). arXiv preprint arXiv:2402.03300, 2024.
19. Li, J., Beeching, E., Tunstall, L., Lipkin, B., Soletskyi, R., Huang, S. C., Rasul, K., Yu, L., Jiang, A., Shen, Z., Qin, Z., Dong, B., Zhou, L., Fleureau, Y., Lample, G., and Polu, S. Numinamath dataset. [https://github.com/project-numina/](https://github.com/project-numina/) aimo-progress-prize/blob/main/report/ numina_dataset.pdf, 20… [↗](https://github.com/project-numina/)
20. Snell, C., Lee, J., Xu, K., and Kumar, A. [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 arXiv:2408.03314, 2024.
21. Team, G., Anil, R., Borgeaud, S., Alayrac, J.-B., Yu, J., Soricut, R., Schalkwyk, J., Dai, A. M., Hauth, A., Millican, K., et al. [Gemini: a family of highly capable multimodal models](https://md.research.elamur.ai/free/en/papers/gemini-team-2023-gemini-family-highly-capable-multimodal/). arXiv preprint arXiv:2312.11805, 2023.
22. Lightman, H., Kosaraju, V., Burda, Y., Edwards, H., Baker, B., Lee, T., Leike, J., Schulman, J., Sutskever, I., and Cobbe, K. Let’s verify step by step. In The Twelfth International Conference on Learning Representations. Touvron, H., Martin, L., Stone, K., Albert, P., Almahairi, A., Babaei, Y., Bas… — [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://md.research.elamur.ai/free/en/papers/touvron-2023-llama-2-open-foundation-fine/)
23. Lozhkov, A., Li, R., Allal, L. B., Cassano, F., Lamy-Poirier, J., Tazi, N., Tang, A., Pykhtar, D., Liu, J., Wei, Y., et al. Starcoder 2 and the stack v2: The next generation. arXiv preprint arXiv:2402.19173, 2024. [find](https://scholar.google.com/scholar?q=Lozhkov%2C+A%2E%2C+Li%2C+R%2E%2C+Allal%2C+L%2E+B%2E%2C+Cassano%2C+F%2E%2C+Lamy%2DPoirier%2C+J%2E%2C+Tazi%2C+N%2E%2C+Tang%2C+A%2E%2C+Pykhtar%2C+D%2E%2C+Liu%2C+J%2E%2C+Wei%2C+Y%2E%2C+et+al%2E+Starcoder+2+and+the+stack+v2%3A+The+next+generation%2E+arXiv+preprint+arXiv%3A2402)
24. Mitra, A., Khanpour, H., Rosset, C., and Awadallah, A. [Orca-math: Unlocking the potential of slms in grade school math](https://md.research.elamur.ai/free/en/papers/mitra-2024-orca-math-unlocking-potential-slms/). arXiv preprint arXiv:2402.14830, 2024.
25. Wang, P., Li, L., Shao, Z., Xu, R., Dai, D., Li, Y., Chen, D., Wu, Y., and Sui, Z. [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 Papers), pp. 9426–9439, 2024.
26. Nguyen, M., Baker, A., Neo, C., Roush, A., Kirsch, A., and Shwartz-Ziv, R. Turning up the heat: Min-p sampling for creative and coherent llm outputs. arXiv preprint arXiv:2407.01082, 2024. — [arXiv:2407.01082](https://arxiv.org/abs/2407.01082) [find](https://scholar.google.com/scholar?q=Nguyen%2C+M%2E%2C+Baker%2C+A%2E%2C+Neo%2C+C%2E%2C+Roush%2C+A%2E%2C+Kirsch%2C+A%2E%2C+and+Shwartz%2DZiv%2C+R%2E+Turning+up+the+heat%3A+Min%2Dp+sampling+for+creative+and+coherent+llm+outputs%2E+arXiv+preprint+arXiv%3A2407%2E01082%2C+2024%2E+%E2%80%94+%5BarXiv%3A24)
27. Wei, J., Wang, X., Schuurmans, D., Bosma, M., Ichter, B., Xia, F., Chi, E. H., Le, Q. V., and Zhou, D. [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 Proceedings of the 36th International Conference on Neural Information Processing Systems, pp. 24824–24837, 2022.
28. OpenAI. Learning to reason with llms. [https://openai.com/index/](https://openai.com/index/) learning-to-reason-with-llms, 2024. [↗](https://openai.com/index/)
29. Ouyang, L., Wu, J., Jiang, X., Almeida, D., Wainwright, C. L., Mishkin, P., Zhang, C., Agarwal, S., Slama, K., Ray, A., et al. [Training language models to follow instructions with human feedback](https://md.research.elamur.ai/free/en/papers/ouyang-2022-training-language-models-follow-instructions/). In Proceedings of the 36th International Conference on Neural Information Processing Systems, pp. 27730–…
30. Yang, A., Yang, B., Zhang, B., Hui, B., Zheng, B., Yu, B., Li, C., Liu, D., Huang, F., Wei, H., et al. Qwen2. 5 technical report. arXiv preprint arXiv:2412.15115, 2024a. [find](https://scholar.google.com/scholar?q=Yang%2C+A%2E%2C+Yang%2C+B%2E%2C+Zhang%2C+B%2E%2C+Hui%2C+B%2E%2C+Zheng%2C+B%2E%2C+Yu%2C+B%2E%2C+Li%2C+C%2E%2C+Liu%2C+D%2E%2C+Huang%2C+F%2E%2C+Wei%2C+H%2E%2C+et+al%2E+Qwen2%2E+5+technical+report%2E+arXiv+preprint+arXiv%3A2412%2E15115%2C+2024a%2E)
31. Yang, A., Zhang, B., Hui, B., Gao, B., Yu, B., Li, C., Liu, D., Tu, J., Zhou, J., Lin, J., et al. Qwen2. 5-math technical report: Toward mathematical expert model via self-improvement. arXiv preprint arXiv:2409.[12122, 2024b](https://md.research.elamur.ai/free/en/papers/yang-2024-qwen2-5-math-technical-report/).
32. Paster, K., Santos, M. D., Azerbayev, Z., and Ba, J. [Openwebmath: An open dataset of high-quality mathematical web text](https://md.research.elamur.ai/free/en/papers/paster-2023-openwebmath-open-dataset-high-quality/). arXiv preprint arXiv:2310.06786, 2023.
33. Yu, L., Jiang, W., Shi, H., Jincheng, Y., Liu, Z., Zhang, Y., Kwok, J., Li, Z., Weller, A., and Liu, W. [Metamath: Bootstrap your own mathematical questions for large language models](https://md.research.elamur.ai/free/en/papers/yu-2023-metamath-bootstrap-your-own-mathematical/). In The Twelfth International Conference on Learning Representations, 2024.
34. Yuan, Z., Yuan, H., Li, C., Dong, G., Lu, K., Tan, C., Zhou, C., and Zhou, J. [Scaling relationship on learning mathematical reasoning with large language models](https://md.research.elamur.ai/free/en/papers/yuan-2023-scaling-relationship-learning-mathematical-reasoning/). arXiv preprint arXiv:2308.01825, 2023.
35. Yue, X., Qu, X., Zhang, G., Fu, Y., Huang, W., Sun, H., Su, Y., and Chen, W. [Mammoth: Building math generalist models through hybrid instruction tuning](https://md.research.elamur.ai/free/en/papers/yue-2023-mammoth-building-math-generalist-models/). In The Twelfth International Conference on Learning Representations. Yue, X., Qu, X., Zhang, G., Fu, Y., Huang, W., Sun, H., Su, Y., and Chen, W. M…
36. Zelikman, E., Wu, Y., and Goodman, N. D. Star: Self-taught reasoner. arXiv preprint arXiv:2203.[14465, 2022](https://md.research.elamur.ai/free/en/papers/zelikman-2022-star-bootstrapping-reasoning-reasoning/).
37. Zhang, D., Zhoubian, S., Hu, Z., Yue, Y., Dong, Y., and Tang, J. [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/). arXiv preprint arXiv:2406.03816, 2024.
38. Zheng, L., Yin, L., Xie, Z., Huang, J., Sun, C., Yu, C., Cao, S., Kozyrakis, C., Stoica, I., Gonzalez, J. E., et al. Efficiently programming large language models using sglang. [https://par.nsf.gov/servlets/purl/10524135](https://par.nsf.gov/servlets/purl/10524135), 2023. [↗](https://par.nsf.gov/servlets/purl/10524135)
39. Zhou, S., Xu, F. F., Zhu, H., Zhou, X., Lo, R., Sridhar, A., Cheng, X., Ou, T., Bisk, Y., Fried, D., et al. [Webarena: A realistic web environment for building autonomous agents](https://md.research.elamur.ai/free/en/papers/zhou-2023-webarena-realistic-web-environment-building/). In The Twelfth International Conference on Learning Representations, 2024.
40. Zhu, Q., Guo, D., Shao, Z., Yang, D., Wang, P., Xu, R., Wu, Y., Li, Y., Gao, H., Ma, S., et al. [Deepseek-coder-v2: Breaking the barrier of closed-source models in code intelligence](https://md.research.elamur.ai/free/en/papers/deepseek-ai-2024-deepseek-coder-v2-breaking-barrier/). arXiv preprint arXiv:2406.11931, 2024.

*Updated 3 November 2026*