---
title: "OptiVerse — paper by Zhang et al. (2026) — summary and ideas"
description: "To target these hidden mismatches, the authors propose the Dual-View Auditor Agent (DVA-Agent). 7.66 points on Hard. 46 references."
authors: ["Xinyu Zhang", "Boxuan Zhang", "Yuchen Wan", "Lingling Zhang", "YiXing Yao", "Bifan Wei", "Yaqiang Wu", "Jun Liu"]
year: 2026
venue: "Findings of the Association for Computational Linguistics: ACL 2026"
source: "https://aclanthology.org/2026.findings-acl.150/"
doi: "10.18653/v1/2026.findings-acl.150"
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/zhang-2026-optiverse-comprehensive-benchmark-optimization-problem/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/zhang-2026-optiverse-comprehensive-benchmark-optimization-problem/)

[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/) / OptiVerse: A Comprehensive Benchmark towards Optimization Problem Solving

# OptiVerse: A Comprehensive Benchmark towards Optimization Problem Solving

**Authors:** [Xinyu Zhang](https://md.research.elamur.ai/free/en/authors/xinyu-zhang/), [Boxuan Zhang](https://md.research.elamur.ai/free/en/authors/boxuan-zhang/), [Yuchen Wan](https://md.research.elamur.ai/free/en/authors/yuchen-wan/), [Lingling Zhang](https://md.research.elamur.ai/free/en/authors/lingling-zhang/), YiXing Yao, [Bifan Wei](https://md.research.elamur.ai/free/en/authors/bifan-wei/), Yaqiang Wu and [Jun Liu](https://md.research.elamur.ai/free/en/authors/jun-liu/) · **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.150/) · [PDF](https://aclanthology.org/2026.findings-acl.150.pdf) · [DOI 10.18653/v1/2026.findings-acl.150](https://doi.org/10.18653/v1/2026.findings-acl.150) · [OpenAlex](https://openalex.org/W7166864383)

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

## Summary
Existing benchmarks for LLM-based optimization modeling, such as OptiBench and OptMATH, cover mostly Mathematical Programming and Combinatorial Optimization. That narrow scope gives a limited picture of how well models handle optimization in general. OptiVerse addresses this with 1,000 curated problems drawn from public textbooks and academic publications. It spans six domains: MP, CO, Stochastic Optimization, Dynamic Optimization, Optimal Control and Game Optimization. Problems are split into Easy, Medium and Hard tiers, and answers are vector-valued rather than single scalars. The authors tested 22 LLMs, ranging from Qwen3-8B to GPT-5.2 and Gemini-3-Pro. Models do well on Easy items, but accuracy drops sharply on Hard ones, and the underrepresented domains (notably Optimal Control) lag behind MP and CO. Error analysis shows the main failure is flawed modeling and logic: generated code runs successfully but does not capture what the problem actually asks. To target these hidden mismatches, the authors propose the Dual-View Auditor Agent (DVA-Agent). It detects such defects and repairs them only when needed, raising accuracy at modest time cost. The benchmark therefore exposes clear gaps in LLM optimization reasoning.

## Key points
- **Dataset composition:** 300 Easy, 400 Medium and 300 Hard problems. By domain, the split is MP 36.7%, CO 23.8%, DO 14.6%, SO 12.0%, OC 7.8% and GO 5.1%. Problems whose solutions were easy to find online were excluded to limit contamination.
- **Hard-tier ceiling:** the best scores on Hard problems were 27% for Gemini-3-Pro and 25.33% for GPT-5.2.
- **DVA-Agent gains:** with Qwen3-235B-Instruct, accuracy improved by 10.5 points on Medium and 7.66 points on Hard. DVA-Agent beat the CoE and OptiMUS baselines for all three backbones tested.
- **Efficiency:** repair was triggered in only 23.6–32.3% of cases. Average time with Qwen3-235B was 58.8s, compared with 121.3s for CoE and 69.3s for OptiMUS.
- **Evaluation and release:** answers are checked by a two-stage LLM-as-a-judge process. The dataset and evaluation scripts are planned for open-source release.

*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

- [Xi'an Jiaotong University](https://md.research.elamur.ai/free/en/universities/xi-an-jiaotong-university/) — University, Xi'an, China · 42 works · 36,431 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): [🧮 Reasoning](https://md.research.elamur.ai/free/en/topics/reasoning/) · 1,685 works · [📏 Evaluation & benchmarks](https://md.research.elamur.ai/free/en/topics/evaluation-benchmarks/) · 1,341 works

## Cite

Cite as: Xinyu Zhang, Boxuan Zhang, Yuchen Wan, Lingling Zhang, YiXing Yao, Bifan Wei, Yaqiang Wu and Jun Liu. 2026. OptiVerse: A Comprehensive Benchmark towards Optimization Problem Solving. 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{zhang2026optiverse,
  title = {{OptiVerse: A Comprehensive Benchmark towards Optimization Problem Solving}},
  author = {Xinyu Zhang, Boxuan Zhang, Yuchen Wan, Lingling Zhang, YiXing Yao, Bifan Wei, Yaqiang Wu and Jun Liu},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.150},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.150}
}
```

- [← previous Optimizing What We Trust: Reliability-Guided QUBO Selection of Multi-Agent Weak Framing Signals for Arabic Sentiment Prediction](https://md.research.elamur.ai/free/en/papers/alkhalifa-2026-optimizing-what-we-trust-reliability/)
- [next → ORCA: Open-ended Response Correctness Assessment for Audio Question Answering](https://md.research.elamur.ai/free/en/papers/sedlacek-2026-orca-open-ended-response-correctness/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/44/)

## References

46 references, 7 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Sandhini Agarwal, Lama Ahmad, Jason Ai, Sam Altman, Andy Applebaum, Edwin Arbus, Rahul K Arora, Yu Bai, Bowen Baker, Haiming Bao, et al. 2025. [gpt-oss-120b & gpt-oss-20b model card](https://md.research.elamur.ai/free/en/papers/agarwal-2025-gpt-oss-120b-gpt-oss/). arXiv preprint arXiv:2508.10925.
2. Ali AhmadiTeshnizi, Wenzhi Gao, and Madeleine Udell. 2024. Optimus: Scalable optimization modeling with (mi) lp solvers and large language models. In Forty-first International Conference on Machine Learning. [find](https://scholar.google.com/scholar?q=Ali+AhmadiTeshnizi%2C+Wenzhi+Gao%2C+and+Madeleine+Udell%2E+2024%2E+Optimus%3A+Scalable+optimization+modeling+with+%28mi%29+lp+solvers+and+large+language+models%2E+In+Forty%2Dfirst+International+Conference+on+Machine+Le)
3. Anthropic. 2025. Introducing claude sonnet 4.5. [find](https://scholar.google.com/scholar?q=Anthropic%2E+2025%2E+Introducing+claude+sonnet+4%2E5%2E)
4. Nicolás Astorga, Tennison Liu, Yuanzhang Xiao, and Mihaela van der Schaar. 2025. Autoformulation of mathematical optimization models using llms. In Forty-second International Conference on Machine Learning. [find](https://scholar.google.com/scholar?q=Nicol%C3%A1s+Astorga%2C+Tennison+Liu%2C+Yuanzhang+Xiao%2C+and+Mihaela+van+der+Schaar%2E+2025%2E+Autoformulation+of+mathematical+optimization+models+using+llms%2E+In+Forty%2Dsecond+International+Conference+on+Machine+Lea)
5. Dimitri P Bertsekas. 2017. Dynamic Programming and Optimal Control, Vol. I & II, 4 edition. Athena Scientific. [find](https://scholar.google.com/scholar?q=Dimitri+P+Bertsekas%2E+2017%2E+Dynamic+Programming+and+Optimal+Control%2C+Vol%2E+I+%26+II%2C+4+edition%2E+Athena+Scientific%2E)
6. John R Birge and François Louveaux. 2011. Introduction to Stochastic Programming. Springer Science & Business Media. [find](https://scholar.google.com/scholar?q=John+R+Birge+and+Fran%C3%A7ois+Louveaux%2E+2011%2E+Introduction+to+Stochastic+Programming%2E+Springer+Science+%26+Business+Media%2E)
7. Stephen Boyd and Lieven Vandenberghe. 2004. Convex Optimization. Cambridge University Press. [find](https://scholar.google.com/scholar?q=Stephen+Boyd+and+Lieven+Vandenberghe%2E+2004%2E+Convex+Optimization%2E+Cambridge+University+Press%2E)
8. Yitian Chen, Jingfan Xia, Siyu Shao, Dongdong Ge, and Yinyu Ye. 2025. Solver-informed rl: Grounding large language models for authentic optimization modeling. The Thirty-ninth Annual Conference on Neural Information Processing Systems. [find](https://scholar.google.com/scholar?q=Yitian+Chen%2C+Jingfan+Xia%2C+Siyu+Shao%2C+Dongdong+Ge%2C+and+Yinyu+Ye%2E+2025%2E+Solver%2Dinformed+rl%3A+Grounding+large+language+models+for+authentic+optimization+modeling%2E+The+Thirty%2Dninth+Annual+Conference+on+Neu)
9. Google Deepmind. 2025a. Gemini 2.5 flash. [find](https://scholar.google.com/scholar?q=Google+Deepmind%2E+2025a%2E+Gemini+2%2E5+flash%2E)
10. Google Deepmind. 2025b. Gemini 2.5 pro. [find](https://scholar.google.com/scholar?q=Google+Deepmind%2E+2025b%2E+Gemini+2%2E5+pro%2E)
11. Google DeepMind. 2025a. Gemini 3 flash. [find](https://scholar.google.com/scholar?q=Google+DeepMind%2E+2025a%2E+Gemini+3+flash%2E)
12. Google DeepMind. 2025b. Gemini 3 pro. [find](https://scholar.google.com/scholar?q=Google+DeepMind%2E+2025b%2E+Gemini+3+pro%2E)
13. Igor Halperin. 2022. Reinforcement Learning and Stochastic Optimization: A Unified Framework for Sequential Decisions: by Warren B. Powell (ed.), Wiley (2022). Hardback. ISBN 9781119815051., volume 22. Taylor & Francis. [find](https://scholar.google.com/scholar?q=Igor+Halperin%2E+2022%2E+Reinforcement+Learning+and+Stochastic+Optimization%3A+A+Unified+Framework+for+Sequential+Decisions%3A+by+Warren+B%2E+Powell+%28ed%2E%29%2C+Wiley+%282022%29%2E+Hardback%2E+ISBN+9781119815051%2E%2C+volume+22)
14. Frederick S Hillier and Gerald J Lieberman. 2020. Introduction to Operations Research, 11 edition. McGraw-Hill Education. [find](https://scholar.google.com/scholar?q=Frederick+S+Hillier+and+Gerald+J+Lieberman%2E+2020%2E+Introduction+to+Operations+Research%2C+11+edition%2E+McGraw%2DHill+Education%2E)
15. Chenyu Huang, Zhengyang Tang, Shixi Hu, Ruoqing Jiang, Xin Zheng, Dongdong Ge, Benyou Wang, and Zizhuo Wang. 2025a. Orlm: A customizable framework in training large models for automated optimization modeling. Operations Research. [find](https://scholar.google.com/scholar?q=Chenyu+Huang%2C+Zhengyang+Tang%2C+Shixi+Hu%2C+Ruoqing+Jiang%2C+Xin+Zheng%2C+Dongdong+Ge%2C+Benyou+Wang%2C+and+Zizhuo+Wang%2E+2025a%2E+Orlm%3A+A+customizable+framework+in+training+large+models+for+automated+optimization+m)
16. Xuhan Huang, Qingning Shen, Yan Hu, Anningzhe Gao, and Benyou Wang. 2025b. LLMs for mathematical modeling: Towards bridging the gap between natural and mathematical languages. In Findings of the Association for Computational Linguistics: NAACL 2025, pages 2678–2710, Albuquerque, New Mexico. Associat… [find](https://scholar.google.com/scholar?q=Xuhan+Huang%2C+Qingning+Shen%2C+Yan+Hu%2C+Anningzhe+Gao%2C+and+Benyou+Wang%2E+2025b%2E+LLMs+for+mathematical+modeling%3A+Towards+bridging+the+gap+between+natural+and+mathematical+languages%2E+In+Findings+of+the+Assoc)
17. Peter Jansen, Oyvind Tafjord, Marissa Radensky, Pao Siangliulue, Tom Hope, Bhavana Dalvi, Bodhisattwa Prasad Majumder, Daniel S Weld, and Peter Clark. 2025. Codescientist: End-to-end semi-automated scientific discovery with code-based experimentation. In Findings of the Association for Computational… [find](https://scholar.google.com/scholar?q=Peter+Jansen%2C+Oyvind+Tafjord%2C+Marissa+Radensky%2C+Pao+Siangliulue%2C+Tom+Hope%2C+Bhavana+Dalvi%2C+Bodhisattwa+Prasad+Majumder%2C+Daniel+S+Weld%2C+and+Peter+Clark%2E+2025%2E+Codescientist%3A+End%2Dto%2Dend+semi%2Dautomated+sc)
18. Xia Jiang, Yaoxin Wu, Minshuo Li, Zhiguang Cao, and Yingqian Zhang. 2025. Large language models as end-to-end combinatorial optimization solvers. In The Thirty-ninth Annual Conference on Neural Information Processing Systems. [find](https://scholar.google.com/scholar?q=Xia+Jiang%2C+Yaoxin+Wu%2C+Minshuo+Li%2C+Zhiguang+Cao%2C+and+Yingqian+Zhang%2E+2025%2E+Large+language+models+as+end%2Dto%2Dend+combinatorial+optimization+solvers%2E+In+The+Thirty%2Dninth+Annual+Conference+on+Neural+Inform)
19. Kimi Team and Bai, Yifan and Bao, Yiping and Chen, Guanduo and Chen, Jiahao and Chen, Ningxin and Chen, Ruijue and Chen, Yanru and Chen, Yuankun and Chen, Yutian and others. 2025. [Kimi k2: Open agentic intelligence](https://md.research.elamur.ai/free/en/papers/kimi-team-2025-kimi-k2-open-agentic/). arXiv preprint arXiv:2507.20534.
20. Bernhard Korte and Jens Vygen. 2018. Combinatorial Optimization: Theory and Algorithms, 6 edition. Springer. [find](https://scholar.google.com/scholar?q=Bernhard+Korte+and+Jens+Vygen%2E+2018%2E+Combinatorial+Optimization%3A+Theory+and+Algorithms%2C+6+edition%2E+Springer%2E)
21. Gongnong Li. 2023. Fundamentals of Operations Research and MATLAB Applications, 2nd edition. Tsinghua University Press, Beijing. In Chinese. [find](https://scholar.google.com/scholar?q=Gongnong+Li%2E+2023%2E+Fundamentals+of+Operations+Research+and+MATLAB+Applications%2C+2nd+edition%2E+Tsinghua+University+Press%2C+Beijing%2E+In+Chinese%2E)
22. Aixin Liu, Aoxue Mei, Bangcai Lin, Bing Xue, Bingxuan Wang, Bingzheng Xu, Bochao Wu, Bowei Zhang, Chaofan Lin, Chen Dong, et al. 2025a. [Deepseekv3](https://md.research.elamur.ai/free/en/papers/deepseek-ai-2025-deepseek-v3-2-pushing/). 2: Pushing the frontier of open large language models. arXiv preprint arXiv:2512.02556.
23. Dongshuo Liu, Zhijing Wu, Dandan Song, and Heyan Huang. 2025b. A persona-aware LLM-enhanced framework for multi-session personalized dialogue generation. In Findings of the Association for Computational Linguistics: ACL 2025, pages 103–123, Vienna, Austria. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Dongshuo+Liu%2C+Zhijing+Wu%2C+Dandan+Song%2C+and+Heyan+Huang%2E+2025b%2E+A+persona%2Daware+LLM%2Denhanced+framework+for+multi%2Dsession+personalized+dialogue+generation%2E+In+Findings+of+the+Association+for+Computation)
24. Haoyang Liu, Jiang Hu, Yongfeng Li, and Zaiwen Wen. 2022. Optimization: Modeling, Algorithms, and Theory. Higher Education Press. Available at [http://faculty.bicmr.pku.edu.cn/](http://faculty.bicmr.pku.edu.cn/) wenzw/optbook.html. [↗](http://faculty.bicmr.pku.edu.cn/)
25. Haoyang Liu, Jie Wang, Yuyang Cai, Xiongwei Han, Yufei Kuang, and Jianye HAO. 2025c. Optitree: Hierarchical thoughts generation with tree search for llm optimization modeling. In The Thirty-ninth Annual Conference on Neural Information Processing Systems. [find](https://scholar.google.com/scholar?q=Haoyang+Liu%2C+Jie+Wang%2C+Yuyang+Cai%2C+Xiongwei+Han%2C+Yufei+Kuang%2C+and+Jianye+HAO%2E+2025c%2E+Optitree%3A+Hierarchical+thoughts+generation+with+tree+search+for+llm+optimization+modeling%2E+In+The+Thirty%2Dninth+Annu)
26. Hongliang Lu, Zhonglin Xie, Yaoyu Wu, Can Ren, Yuxuan Chen, and Zaiwen Wen. 2025. Optmath: A scalable bidirectional data synthesis framework for optimization modeling. In Forty-second International Conference on Machine Learning. [find](https://scholar.google.com/scholar?q=Hongliang+Lu%2C+Zhonglin+Xie%2C+Yaoyu+Wu%2C+Can+Ren%2C+Yuxuan+Chen%2C+and+Zaiwen+Wen%2E+2025%2E+Optmath%3A+A+scalable+bidirectional+data+synthesis+framework+for+optimization+modeling%2E+In+Forty%2Dsecond+International+Co)
27. Mistral AI Team. 2025. Introducing mistral 3. [find](https://scholar.google.com/scholar?q=Mistral+AI+Team%2E+2025%2E+Introducing+mistral+3%2E)
28. Junbo Niu, Zheng Liu, Zhuangcheng Gu, Bin Wang, Linke Ouyang, Zhiyuan Zhao, Tao Chu, Tianyao He, Fan Wu, Qintong Zhang, Zhenjiang Jin, Guang Liang, Rui Zhang, Wenzheng Zhang, Yuan Qu, Zhifei Ren, Yuefeng Sun, Yuanhong Zheng, Dongsheng Ma, Zirui Tang, Boyu Niu, Ziyang Miao, Hejun Dong, Siyi Qian, Jun… — [MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing](https://md.research.elamur.ai/free/en/papers/niu-2026-mineru2-5-decoupled-vision-language/)
29. OpenAI. 2025a. Introducing gpt-5.2. [find](https://scholar.google.com/scholar?q=OpenAI%2E+2025a%2E+Introducing+gpt%2D5%2E2%2E)
30. OpenAI. 2025b. Introducing openai o3 and o4-mini. [find](https://scholar.google.com/scholar?q=OpenAI%2E+2025b%2E+Introducing+openai+o3+and+o4%2Dmini%2E)
31. Martin J Osborne. 2004. An Introduction to Game Theory. Oxford University Press. [find](https://scholar.google.com/scholar?q=Martin+J+Osborne%2E+2004%2E+An+Introduction+to+Game+Theory%2E+Oxford+University+Press%2E)
32. Rindranirina Ramamonjison, Timothy Yu, Raymond Li, Haley Li, Giuseppe Carenini, Bissan Ghaddar, Shiqi He, Mahdi Mostajabdaveh, Amin Banitalebi-Dehkordi, Zirui Zhou, et al. 2023. Nl4opt competition: Formulating optimization problems based on their natural language descriptions. In NeurIPS 2022 compet… [find](https://scholar.google.com/scholar?q=Rindranirina+Ramamonjison%2C+Timothy+Yu%2C+Raymond+Li%2C+Haley+Li%2C+Giuseppe+Carenini%2C+Bissan+Ghaddar%2C+Shiqi+He%2C+Mahdi+Mostajabdaveh%2C+Amin+Banitalebi%2DDehkordi%2C+Zirui+Zhou%2C+et+al%2E+2023%2E+Nl4opt+competition%3A+Fo)
33. Lingling Zhang, and Jun Liu. 2025a. [PhysReason: A comprehensive benchmark towards physics-based reasoning](https://md.research.elamur.ai/free/en/papers/zhang-2025-physreason-comprehensive-benchmark-physics-based/). In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 16593–16615, Vienna, Austria. Association for Computational Linguistics…
34. 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.
35. Xinyu Zhang, Yuxuan Dong, Lingling Zhang, Chengyou Jia, Zhuohang Dang, Basura Fernando, Jun Liu, and Mike Zheng Shou. 2025b. Cofft: Chain of foresight-focus thought for visual language models. In The Thirty-ninth Annual Conference on Neural Information Processing Systems. [find](https://scholar.google.com/scholar?q=Xinyu+Zhang%2C+Yuxuan+Dong%2C+Lingling+Zhang%2C+Chengyou+Jia%2C+Zhuohang+Dang%2C+Basura+Fernando%2C+Jun+Liu%2C+and+Mike+Zheng+Shou%2E+2025b%2E+Cofft%3A+Chain+of+foresight%2Dfocus+thought+for+visual+language+models%2E+In+The+)
36. InternLM Team. 2025. Internlm3-8b-instruct. [find](https://scholar.google.com/scholar?q=InternLM+Team%2E+2025%2E+Internlm3%2D8b%2Dinstruct%2E)
37. Ziyang Xiao, Dongxiang Zhang, Yangjun Wu, Lilin Xu, Yuan Jessica Wang, Xiongwei Han, Xiaojin Fu, Tao Zhong, Jia Zeng, Mingli Song, et al. 2023. Chain-of-experts: When llms meet complex operations research problems. In The twelfth international conference on learning representations. [find](https://scholar.google.com/scholar?q=Ziyang+Xiao%2C+Dongxiang+Zhang%2C+Yangjun+Wu%2C+Lilin+Xu%2C+Yuan+Jessica+Wang%2C+Xiongwei+Han%2C+Xiaojin+Fu%2C+Tao+Zhong%2C+Jia+Zeng%2C+Mingli+Song%2C+et+al%2E+2023%2E+Chain%2Dof%2Dexperts%3A+When+llms+meet+complex+operations+rese)
38. Yibo Yan, Jiamin Su, Jianxiang He, Fangteng Fu, Xu Zheng, Yuanhuiyi Lyu, Kun Wang, Shen Wang, Qingsong Wen, and Xuming Hu. 2025. A survey of mathematical reasoning in the era of multimodal large language model: Benchmark, method & challenges. In Findings of the Association for Computational Linguist… [find](https://scholar.google.com/scholar?q=Yibo+Yan%2C+Jiamin+Su%2C+Jianxiang+He%2C+Fangteng+Fu%2C+Xu+Zheng%2C+Yuanhuiyi+Lyu%2C+Kun+Wang%2C+Shen+Wang%2C+Qingsong+Wen%2C+and+Xuming+Hu%2E+2025%2E+A+survey+of+mathematical+reasoning+in+the+era+of+multimodal+large+langu)
39. An Yang, Anfeng Li, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Gao, Chengen Huang, Chenxu Lv, et al. 2025a. [Qwen3 technical report](https://md.research.elamur.ai/free/en/papers/yang-2025-qwen3-technical-report/). arXiv preprint arXiv:2505.09388.
40. An Yang, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chengyuan Li, Dayiheng Liu, Fei Huang, Haoran Wei, et al. 2024. Qwen2. 5 technical report. arXiv e-prints, pages arXiv–2412. [find](https://scholar.google.com/scholar?q=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+Haoran+Wei%2C+et+al%2E+2024%2E+Qwen2%2E+5+technical+report%2E+arXiv+e%2Dprints%2C+pages+arXiv%E2%80%932412%2E)
41. Zhicheng Yang, Yiwei Wang, Yinya Huang, Zhijiang Guo, Wei Shi, Xiongwei Han, Liang Feng, Linqi Song, Xiaodan Liang, and Jing Tang. 2025b. Optibench meets resocratic: Measure and improve llms for optimization modeling. In The Thirteenth International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Zhicheng+Yang%2C+Yiwei+Wang%2C+Yinya+Huang%2C+Zhijiang+Guo%2C+Wei+Shi%2C+Xiongwei+Han%2C+Liang+Feng%2C+Linqi+Song%2C+Xiaodan+Liang%2C+and+Jing+Tang%2E+2025b%2E+Optibench+meets+resocratic%3A+Measure+and+improve+llms+for+optim)
42. Lingling Zhang, Xiaojun Chang, Jun Liu, Minnan Luo, Zhihui Li, Lina Yao, and Alex Hauptmann. 2022. Tn-zstad: Transferable network for zero-shot temporal activity detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(3):3848– 3861. [find](https://scholar.google.com/scholar?q=Lingling+Zhang%2C+Xiaojun+Chang%2C+Jun+Liu%2C+Minnan+Luo%2C+Zhihui+Li%2C+Lina+Yao%2C+and+Alex+Hauptmann%2E+2022%2E+Tn%2Dzstad%3A+Transferable+network+for+zero%2Dshot+temporal+activity+detection%2E+IEEE+Transactions+on+Patter)
43. Lingling Zhang, Xinyu Zhang, Qianying Wang, Wenjun Wu, Xiaojun Chang, and Jun Liu. 2023. Rpmg-fss: Robust prior mask guided few-shot semantic segmentation. IEEE Transactions on Circuits and Systems for Video Technology, 33(11):6609–6621. [find](https://scholar.google.com/scholar?q=Lingling+Zhang%2C+Xinyu+Zhang%2C+Qianying+Wang%2C+Wenjun+Wu%2C+Xiaojun+Chang%2C+and+Jun+Liu%2E+2023%2E+Rpmg%2Dfss%3A+Robust+prior+mask+guided+few%2Dshot+semantic+segmentation%2E+IEEE+Transactions+on+Circuits+and+Systems+fo)
44. Xinyu Zhang, Yuxuan Dong, Yanrui Wu, Jiaxing Huang, Chengyou Jia, Basura Fernando, Mike Zheng Shou, Xinyu Zhang, Lingling Zhang, Yanrui Wu, Muye Huang, and Jun Liu. 2025c. Cognitive predictive coding network: Rethinking the generalization in raven’s progressive matrices. In Proceedings of the 33rd A… [find](https://scholar.google.com/scholar?q=Xinyu+Zhang%2C+Yuxuan+Dong%2C+Yanrui+Wu%2C+Jiaxing+Huang%2C+Chengyou+Jia%2C+Basura+Fernando%2C+Mike+Zheng+Shou%2C+Xinyu+Zhang%2C+Lingling+Zhang%2C+Yanrui+Wu%2C+Muye+Huang%2C+and+Jun+Liu%2E+2025c%2E+Cognitive+predictive+coding+)
45. Xinyu Zhang, Lingling Zhang, Yanrui Wu, Muye Huang, Wenjun Wu, Bo Li, Shaowei Wang, Basura Fernando, and Jun Liu. 2025d. Diagram-driven course questions generation. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 5995–6010. [find](https://scholar.google.com/scholar?q=Xinyu+Zhang%2C+Lingling+Zhang%2C+Yanrui+Wu%2C+Muye+Huang%2C+Wenjun+Wu%2C+Bo+Li%2C+Shaowei+Wang%2C+Basura+Fernando%2C+and+Jun+Liu%2E+2025d%2E+Diagram%2Ddriven+course+questions+generation%2E+In+Proceedings+of+the+2025+Conferen)
46. Xinyu Zhang, Lingling Zhang, Yanrui Wu, Shaowei Wang, Wenjun Wu, Muye Huang, Qianying Wang, and Jun Liu. 2025e. Memory-enriched thought-by-thought framework for complex diagram question answering. Computer Vision and Image Understanding, page 104608. [find](https://scholar.google.com/scholar?q=Xinyu+Zhang%2C+Lingling+Zhang%2C+Yanrui+Wu%2C+Shaowei+Wang%2C+Wenjun+Wu%2C+Muye+Huang%2C+Qianying+Wang%2C+and+Jun+Liu%2E+2025e%2E+Memory%2Denriched+thought%2Dby%2Dthought+framework+for+complex+diagram+question+answering%2E+Com)

*Updated 2 November 2026*