---
title: "AdaTooler-V: Adaptive Tool-Use for Images and Videos (2026)"
description: "The authors propose AT-GRPO, a GRPO variant that scales the tool-related reward by a per-sample… 74 references, cited by 2 papers here."
authors: ["Chaoyang Wang", "Kaituo Feng", "Dongyang Chen", "Zhongyu Wang", "Zhixun Li", "Sicheng Gao", "Meng Meng", "Xu Zhou", "Manyuan Zhang", "Yuzhang Shang", "Xiangyu Yue"]
year: 2026
venue: "Findings of the Association for Computational Linguistics: ACL 2026"
source: "https://aclanthology.org/2026.findings-acl.898/"
doi: "10.18653/v1/2026.findings-acl.898"
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/wang-2026-adatooler-v-adaptive-tool-use/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/wang-2026-adatooler-v-adaptive-tool-use/)

[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/6/) / AdaTooler-V: Adaptive Tool-Use for Images and Videos

# AdaTooler-V: Adaptive Tool-Use for Images and Videos

**Authors:** Chaoyang Wang, Kaituo Feng, Dongyang Chen, [Zhongyu Wang](https://md.research.elamur.ai/free/en/authors/zhongyu-wang/), [Zhixun Li](https://md.research.elamur.ai/free/en/authors/zhixun-li/), Sicheng Gao, Meng Meng, Xu Zhou, Manyuan Zhang, Yuzhang Shang and [Xiangyu Yue](https://md.research.elamur.ai/free/en/authors/xiangyu-yue/) · **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.898/) · [PDF](https://aclanthology.org/2026.findings-acl.898.pdf) · [DOI 10.18653/v1/2026.findings-acl.898](https://doi.org/10.18653/v1/2026.findings-acl.898) · [OpenAlex](https://openalex.org/W4417531485)

**Citations:** 0 citations (OpenAlex, 2026-10-14) · 2 in our library, of the 149,439 papers whose bibliographies we read

## Summary
Open-source multimodal LLMs that reason by interleaving text with visual tool calls, such as zooming into image regions or extracting video segments, often call tools even when they are not needed. This raises inference cost and can lower accuracy, because the model overthinks and drifts away from the original visual input. AdaTooler-V tackles this by learning when a tool is actually worth calling. The authors propose AT-GRPO, a GRPO variant that scales the tool-related reward by a per-sample Tool Benefit Score ΔS. This score is the accuracy gap of Qwen2.5-VL-72B-Instruct on that sample with versus without tools. Tool calls are rewarded only where they help and penalized where they are redundant. Training has two stages: an SFT cold start on AdaTooler-V-CoT-100k, which contains multi-turn tool trajectories, followed by RL on AdaTooler-V-300k. Both datasets span single-image, multi-image and video tasks. Across twelve benchmarks, the 7B model outperforms prior methods and reaches 89.8% on V*, beating GPT-4o and Gemini 1.5 Pro. The work shows that selective tool use can be both cheaper and more accurate.

## Key points
- **Resources:** two released datasets, AdaTooler-V-CoT-100k (SFT) and AdaTooler-V-300k (RL with verifiable rewards). Tasks include math, counting, logic and spatial reasoning. Tools are vision-only, such as `crop_image` and `get_video_clip_frame`.
- **Headline result:** AdaTooler-V-7B scores 89.8% on V*, versus 78.5% for the base Qwen2.5-VL-7B.
- **Training-stage ablation:** average accuracy over V*, MathVista, VSI-Bench and MVBench is:
  - 65.9 with GRPO only,
  - 67.6 with SFT+GRPO,
  - 69.9 with SFT+AT-GRPO.
- **Tool-use ablation:** an RL variant without tools averages 65.5. It drops to 84.4 on V* and 39.9 on VSI-Bench, compared with 89.8 and 46.7 for AdaTooler-V.
- **Behavior and limitations:** during RL, average response length falls sharply as the model learns to answer easy samples with text-only CoT. The reward weight α works best at 0.6, and results are fairly robust to it. Audio inputs and knowledge-retrieval tools are not yet covered.

*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

- [Shanghai Jiao Tong University](https://md.research.elamur.ai/free/en/universities/shanghai-jiao-tong-university/) — University, Shanghai, China · 149 works · 16,161 citations
- [Chinese University of Hong Kong](https://md.research.elamur.ai/free/en/universities/chinese-university-of-hong-kong/) — University, Hong Kong, China · 126 works · 14,073 citations
- [University of Central Florida](https://md.research.elamur.ai/free/en/universities/university-of-central-florida/) — University, Orlando, United States · 13 works · 39,673 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

## Cite

Cite as: Chaoyang Wang, Kaituo Feng, Dongyang Chen, Zhongyu Wang, Zhixun Li, Sicheng Gao, Meng Meng, Xu Zhou, Manyuan Zhang, Yuzhang Shang and Xiangyu Yue. 2026. AdaTooler-V: Adaptive Tool-Use for Images and Videos. 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{wang2026adatooler,
  title = {{AdaTooler-V: Adaptive Tool-Use for Images and Videos}},
  author = {Chaoyang Wang, Kaituo Feng, Dongyang Chen, Zhongyu Wang, Zhixun Li, Sicheng Gao, Meng Meng, Xu Zhou, Manyuan Zhang, Yuzhang Shang and Xiangyu Yue},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.898},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.898}
}
```

- [← previous Adaptive Text Anonymization: Learning Privacy-Utility Trade-offs via Prompt Optimization](https://md.research.elamur.ai/free/en/papers/loiseau-2026-adaptive-text-anonymization-learning-privacy/)
- [next → AfriCaption: Establishing a New Paradigm for Image Captioning in African Languages](https://md.research.elamur.ai/free/en/papers/oduwole-2026-africaption-establishing-new-paradigm-image/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/6/)

## References

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

1. Sule Bai, Mingxing Li, Yong Liu, Jing Tang, Haoji Zhang, Lei Sun, Xiangxiang Chu, and Yansong Tang. 2025c. Univg-r1: Reasoning guided universal visual grounding with reinforcement learning. arXiv preprint arXiv:2505.14231. — [arXiv:2505.14231](https://arxiv.org/abs/2505.14231) [find](https://scholar.google.com/scholar?q=Sule+Bai%2C+Mingxing+Li%2C+Yong+Liu%2C+Jing+Tang%2C+Haoji+Zhang%2C+Lei+Sun%2C+Xiangxiang+Chu%2C+and+Yansong+Tang%2E+2025c%2E+Univg%2Dr1%3A+Reasoning+guided+universal+visual+grounding+with+reinforcement+learning%2E+arXiv+prep)
2. Xingyu Chen, Jiahao Xu, Tian Liang, Zhiwei He, Jianhui Pang, Dian Yu, Linfeng Song, Qiuzhi Liu, Mengfei Zhou, Zhuosheng Zhang, and 1 others. 2024. [Do not think that much for 2+ 3=?](https://md.research.elamur.ai/free/en/papers/chen-2024-think-that-much-2-3/) on the overthinking of o1-like llms. arXiv preprint arXiv:2412.21187.
3. Junhao Cheng, Yuying Ge, Teng Wang, Yixiao Ge, Jing Liao, and Ying Shan. 2025a. Video-holmes: Can mllm think like holmes for complex video reasoning? arXiv preprint arXiv:2505.21374. — [arXiv:2505.21374](https://arxiv.org/abs/2505.21374) [find](https://scholar.google.com/scholar?q=Junhao+Cheng%2C+Yuying+Ge%2C+Teng+Wang%2C+Yixiao+Ge%2C+Jing+Liao%2C+and+Ying+Shan%2E+2025a%2E+Video%2Dholmes%3A+Can+mllm+think+like+holmes+for+complex+video+reasoning%3F+arXiv+preprint+arXiv%3A2505%2E21374%2E+%E2%80%94+%5BarXiv%3A2505%2E213)
4. Junhao Cheng, Yuying Ge, Teng Wang, Yixiao Ge, Jing Liao, and Ying Shan. 2025b. Video-holmes: Can mllm think like holmes for complex video reasoning? arXiv preprint arXiv:2505.21374. — [arXiv:2505.21374](https://arxiv.org/abs/2505.21374) [find](https://scholar.google.com/scholar?q=Junhao+Cheng%2C+Yuying+Ge%2C+Teng+Wang%2C+Yixiao+Ge%2C+Jing+Liao%2C+and+Ying+Shan%2E+2025b%2E+Video%2Dholmes%3A+Can+mllm+think+like+holmes+for+complex+video+reasoning%3F+arXiv+preprint+arXiv%3A2505%2E21374%2E+%E2%80%94+%5BarXiv%3A2505%2E213)
5. Chenrui Fan, Ming Li, Lichao Sun, and Tianyi Zhou. 2025a. Missing premise exacerbates overthinking: Are reasoning models losing critical thinking skill? arXiv preprint arXiv:2504.06514. — [arXiv:2504.06514](https://arxiv.org/abs/2504.06514) [find](https://scholar.google.com/scholar?q=Chenrui+Fan%2C+Ming+Li%2C+Lichao+Sun%2C+and+Tianyi+Zhou%2E+2025a%2E+Missing+premise+exacerbates+overthinking%3A+Are+reasoning+models+losing+critical+thinking+skill%3F+arXiv+preprint+arXiv%3A2504%2E06514%2E+%E2%80%94+%5BarXiv%3A2504%2E)
6. Kaixuan Fan, Kaituo Feng, Haoming Lyu, Dongzhan Zhou, and Xiangyu Yue. 2025b. Sophiavl-r1: Reinforcing mllms reasoning with thinking reward. arXiv preprint arXiv:2505.17018. — [arXiv:2505.17018](https://arxiv.org/abs/2505.17018) [find](https://scholar.google.com/scholar?q=Kaixuan+Fan%2C+Kaituo+Feng%2C+Haoming+Lyu%2C+Dongzhan+Zhou%2C+and+Xiangyu+Yue%2E+2025b%2E+Sophiavl%2Dr1%3A+Reinforcing+mllms+reasoning+with+thinking+reward%2E+arXiv+preprint+arXiv%3A2505%2E17018%2E+%E2%80%94+%5BarXiv%3A2505%2E17018%5D%28https)
7. Kaituo Feng, Kaixiong Gong, Bohao Li, Zonghao Guo, Yibing Wang, Tianshuo Peng, Junfei Wu, Xiaoying Zhang, Benyou Wang, and Xiangyu Yue. 2025a. Video-r1: Reinforcing video reasoning in mllms. arXiv preprint arXiv:2503.21776. — [arXiv:2503.21776](https://arxiv.org/abs/2503.21776) [find](https://scholar.google.com/scholar?q=Kaituo+Feng%2C+Kaixiong+Gong%2C+Bohao+Li%2C+Zonghao+Guo%2C+Yibing+Wang%2C+Tianshuo+Peng%2C+Junfei+Wu%2C+Xiaoying+Zhang%2C+Benyou+Wang%2C+and+Xiangyu+Yue%2E+2025a%2E+Video%2Dr1%3A+Reinforcing+video+reasoning+in+mllms%2E+arXiv+pre)
8. Kaituo Feng, Manyuan Zhang, Hongyu Li, Kaixuan Fan, Shuang Chen, Yilei Jiang, Dian Zheng, Peiwen Sun, Yiyuan Zhang, Haoze Sun, and 1 others. 2025b. Onethinker: All-in-one reasoning model for image and video. arXiv preprint arXiv:2512.03043. — [arXiv:2512.03043](https://arxiv.org/abs/2512.03043) [find](https://scholar.google.com/scholar?q=Kaituo+Feng%2C+Manyuan+Zhang%2C+Hongyu+Li%2C+Kaixuan+Fan%2C+Shuang+Chen%2C+Yilei+Jiang%2C+Dian+Zheng%2C+Peiwen+Sun%2C+Yiyuan+Zhang%2C+Haoze+Sun%2C+and+1+others%2E+2025b%2E+Onethinker%3A+All%2Din%2Done+reasoning+model+for+image+and)
9. Chaoyou Fu, Peixian Chen, Yunhang Shen, Yulei Qin, Mengdan Zhang, Xu Lin, Jinrui Yang, Xiawu Zheng, Ke Li, Xing Sun, and 1 others. 2025a. [Mme: A comprehensive evaluation benchmark for multimodal large language models](https://md.research.elamur.ai/free/en/papers/fu-2023-mme-comprehensive-evaluation-benchmark-multimodal/). In The Thirty-ninth Annual Conference on Neural Information Processing Systems Dat…
10. Shuai Bai, Keqin Chen, Xuejing Liu, Jialin Wang, Wenbin Ge, Sibo Song, Kai Dang, Peng Wang, Shijie Wang, Jun Tang, Humen Zhong, Yuanzhi Zhu, Mingkun Yang, Zhaohai Li, Jianqiang Wan, Pengfei Wang, Wei Ding, Zheren Fu, Yiheng Xu, and 8 others. 2025a. [Qwen2.5-vl technical report](https://md.research.elamur.ai/free/en/papers/bai-2025-qwen2-5-vl-technical/). arXiv preprint arXiv:2…
11. Chaoyou Fu, Yuhan Dai, Yongdong Luo, Lei Li, Shuhuai Ren, Renrui Zhang, Zihan Wang, Chenyu Zhou, Yunhang Shen, Mengdan Zhang, and 1 others. 2025b. [Video-mme: The first-ever comprehensive evaluation benchmark of multi-modal llms in video analysis](https://md.research.elamur.ai/free/en/papers/fu-2024-video-mme-first-ever-comprehensive/). In Proceedings of the Computer Vision and Pattern Rec…
12. Shuai Bai, Keqin Chen, Xuejing Liu, Jialin Wang, Wenbin Ge, Sibo Song, Kai Dang, Peng Wang, Shijie Wang, Jun Tang, and 1 others. 2025b. Qwen2. 5-vl technical report. arXiv preprint arXiv:2502.13923. — [Qwen2.5-VL Technical Report](https://md.research.elamur.ai/free/en/papers/bai-2025-qwen2-5-vl-technical/)
13. Haonan Ge, Yiwei Wang, Kai-Wei Chang, Hang Wu, and Yujun Cai. 2025. Framemind: Frame-interleaved chain-of-thought for video reasoning via reinforcement learning. arXiv preprint arXiv:2509.24008. — [arXiv:2509.24008](https://arxiv.org/abs/2509.24008) [find](https://scholar.google.com/scholar?q=Haonan+Ge%2C+Yiwei+Wang%2C+Kai%2DWei+Chang%2C+Hang+Wu%2C+and+Yujun+Cai%2E+2025%2E+Framemind%3A+Frame%2Dinterleaved+chain%2Dof%2Dthought+for+video+reasoning+via+reinforcement+learning%2E+arXiv+preprint+arXiv%3A2509%2E24008%2E+%E2%80%94+%5Bar)
14. Gemini Team. 2024. [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://md.research.elamur.ai/free/en/papers/gemini-team-2024-gemini-1-5-unlocking-multimodal/). Preprint, arXiv:2403.05530.
15. Daya Guo, Dejian Yang, Haowei Zhang, Junxiao Song, Ruoyu Zhang, Runxin Xu, Qihao Zhu, Shirong Ma, Peiyi Wang, Xiao Bi, and 1 others. 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/). arXiv preprint arXiv:2501.12948.
16. Daya Guo, Dejian Yang, Haowei Zhang, Junxiao Song, Ruoyu Zhang, Runxin Xu, Qihao Zhu, Shirong Ma, Peiyi Wang, Xiao Bi, and 1 others. 2025b. [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/). arXiv preprint arXiv:2501.12948.
17. Kairui Hu, Penghao Wu, Fanyi Pu, Wang Xiao, Yuanhan Zhang, Xiang Yue, Bo Li, and Ziwei Liu. 2025. Video-mmmu: Evaluating knowledge acquisition from multi-discipline professional videos. arXiv preprint arXiv:2501.13826. — [arXiv:2501.13826](https://arxiv.org/abs/2501.13826) [find](https://scholar.google.com/scholar?q=Kairui+Hu%2C+Penghao+Wu%2C+Fanyi+Pu%2C+Wang+Xiao%2C+Yuanhan+Zhang%2C+Xiang+Yue%2C+Bo+Li%2C+and+Ziwei+Liu%2E+2025%2E+Video%2Dmmmu%3A+Evaluating+knowledge+acquisition+from+multi%2Ddiscipline+professional+videos%2E+arXiv+preprint)
18. Wenxuan Huang, Bohan Jia, Zijie Zhai, Shaosheng Cao, Zheyu Ye, Fei Zhao, Zhe Xu, Yao Hu, and Shaohui Lin. 2025a. Vision-r1: Incentivizing reasoning capability in multimodal large language models. arXiv preprint arXiv:2503.06749. [find](https://scholar.google.com/scholar?q=Wenxuan+Huang%2C+Bohan+Jia%2C+Zijie+Zhai%2C+Shaosheng+Cao%2C+Zheyu+Ye%2C+Fei+Zhao%2C+Zhe+Xu%2C+Yao+Hu%2C+and+Shaohui+Lin%2E+2025a%2E+Vision%2Dr1%3A+Incentivizing+reasoning+capability+in+multimodal+large+language+models%2E+arXi)
19. Wenxuan Huang, Bohan Jia, Zijie Zhai, Shaosheng Cao, Zheyu Ye, Fei Zhao, Zhe Xu, Yao Hu, and Shaohui Lin. 2025b. Vision-r1: Incentivizing reasoning capability in multimodal large language models. arXiv preprint arXiv:2503.06749. [find](https://scholar.google.com/scholar?q=Wenxuan+Huang%2C+Bohan+Jia%2C+Zijie+Zhai%2C+Shaosheng+Cao%2C+Zheyu+Ye%2C+Fei+Zhao%2C+Zhe+Xu%2C+Yao+Hu%2C+and+Shaohui+Lin%2E+2025b%2E+Vision%2Dr1%3A+Incentivizing+reasoning+capability+in+multimodal+large+language+models%2E+arXi)
20. Dongfu Jiang, Yi Lu, Zhuofeng Li, Zhiheng Lyu, Ping Nie, Haozhe Wang, Alex Su, Hui Chen, Kai Zou, Chao Du, and 1 others. 2025. Verltool: Towards holistic agentic reinforcement learning with tool use. arXiv preprint arXiv:2509.01055. — [arXiv:2509.01055](https://arxiv.org/abs/2509.01055) [find](https://scholar.google.com/scholar?q=Dongfu+Jiang%2C+Yi+Lu%2C+Zhuofeng+Li%2C+Zhiheng+Lyu%2C+Ping+Nie%2C+Haozhe+Wang%2C+Alex+Su%2C+Hui+Chen%2C+Kai+Zou%2C+Chao+Du%2C+and+1+others%2E+2025%2E+Verltool%3A+Towards+holistic+agentic+reinforcement+learning+with+tool+use%2E+)
21. Woosuk Kwon, Zhuohan Li, Siyuan Zhuang, Ying Sheng, Lianmin Zheng, Cody Hao Yu, Joseph E. Gonzalez, Hao Zhang, and Ion Stoica. 2023. [Efficient memory management for large language model serving with pagedattention](https://md.research.elamur.ai/free/en/papers/kwon-2023-efficient-memory-management-large-language/). In Proceedings of the ACM SIGOPS 29th Symposium on Operating Systems Principles.
22. Xin Lai, Junyi Li, Wei Li, Tao Liu, Tianjian Li, and Hengshuang Zhao. 2025a. Mini-o3: Scaling up reasoning patterns and interaction turns for visual search. arXiv:2509.07969. — [arXiv:2509.07969](https://arxiv.org/abs/2509.07969) [find](https://scholar.google.com/scholar?q=Xin+Lai%2C+Junyi+Li%2C+Wei+Li%2C+Tao+Liu%2C+Tianjian+Li%2C+and+Hengshuang+Zhao%2E+2025a%2E+Mini%2Do3%3A+Scaling+up+reasoning+patterns+and+interaction+turns+for+visual+search%2E+arXiv%3A2509%2E07969%2E+%E2%80%94+%5BarXiv%3A2509%2E07969%5D%28http)
23. Xin Lai, Junyi Li, Wei Li, Tao Liu, Tianjian Li, and Hengshuang Zhao. 2025b. Mini-o3: Scaling up reasoning patterns and interaction turns for visual search. arXiv preprint arXiv:2509.07969. — [arXiv:2509.07969](https://arxiv.org/abs/2509.07969) [find](https://scholar.google.com/scholar?q=Xin+Lai%2C+Junyi+Li%2C+Wei+Li%2C+Tao+Liu%2C+Tianjian+Li%2C+and+Hengshuang+Zhao%2E+2025b%2E+Mini%2Do3%3A+Scaling+up+reasoning+patterns+and+interaction+turns+for+visual+search%2E+arXiv+preprint+arXiv%3A2509%2E07969%2E+%E2%80%94+%5BarXiv%3A2)
24. Bo Li, Yuanhan Zhang, Dong Guo, Renrui Zhang, Feng Li, Hao Zhang, Kaichen Zhang, Peiyuan Zhang, Yanwei Li, Ziwei Liu, and 1 others. 2024a. [Llava-onevision: Easy visual task transfer](https://md.research.elamur.ai/free/en/papers/li-2024-llava-onevision-easy-visual-task/). arXiv preprint arXiv:2408.03326.
25. Chengzu Li, Wenshan Wu, Huanyu Zhang, Yan Xia, Shaoguang Mao, Li Dong, Ivan Vulić, and Furu Wei. 2025a. Imagine while reasoning in space: Multimodal visualization-of-thought. arXiv preprint arXiv:2501.07542. — [arXiv:2501.07542](https://arxiv.org/abs/2501.07542) [find](https://scholar.google.com/scholar?q=Chengzu+Li%2C+Wenshan+Wu%2C+Huanyu+Zhang%2C+Yan+Xia%2C+Shaoguang+Mao%2C+Li+Dong%2C+Ivan+Vulic%CC%81%2C+and+Furu+Wei%2E+2025a%2E+Imagine+while+reasoning+in+space%3A+Multimodal+visualization%2Dof%2Dthought%2E+arXiv+preprint+arXiv%3A250)
26. Hongyu Li, Songhao Han, Yue Liao, Junfeng Luo, Jialin Gao, Shuicheng Yan, and Si Liu. 2025b. Reinforcement learning tuning for videollms: Reward design and data efficiency. arXiv preprint arXiv:2506.01908. — [arXiv:2506.01908](https://arxiv.org/abs/2506.01908) [find](https://scholar.google.com/scholar?q=Hongyu+Li%2C+Songhao+Han%2C+Yue+Liao%2C+Junfeng+Luo%2C+Jialin+Gao%2C+Shuicheng+Yan%2C+and+Si+Liu%2E+2025b%2E+Reinforcement+learning+tuning+for+videollms%3A+Reward+design+and+data+efficiency%2E+arXiv+preprint+arXiv%3A2506%2E0)
27. Hongyu Li, Manyuan Zhang, Dian Zheng, Ziyu Guo, Yimeng Jia, Kaituo Feng, Hao Yu, Yexin Liu, Yan Feng, Peng Pei, and 1 others. 2025c. Editthinker: Unlocking iterative reasoning for any image editor. arXiv preprint arXiv:2512.05965. — [arXiv:2512.05965](https://arxiv.org/abs/2512.05965) [find](https://scholar.google.com/scholar?q=Hongyu+Li%2C+Manyuan+Zhang%2C+Dian+Zheng%2C+Ziyu+Guo%2C+Yimeng+Jia%2C+Kaituo+Feng%2C+Hao+Yu%2C+Yexin+Liu%2C+Yan+Feng%2C+Peng+Pei%2C+and+1+others%2E+2025c%2E+Editthinker%3A+Unlocking+iterative+reasoning+for+any+image+editor%2E+ar)
28. Kunchang Li, Yali Wang, Yinan He, Yizhuo Li, Yi Wang, Yi Liu, Zun Wang, Jilan Xu, Guo Chen, Ping Luo, and 1 others. 2024b. [Mvbench: A comprehensive multi-modal video understanding benchmark](https://md.research.elamur.ai/free/en/papers/li-2023-mvbench-comprehensive-multi-modal-video/). In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 22195–22206.
29. Wenjun Li, Dexun Li, Kuicai Dong, Cong Zhang, Hao Zhang, Weiwen Liu, Yasheng Wang, Ruiming Tang, and Yong Liu. 2025d. [Adaptive tool use in large language models with meta-cognition trigger](https://md.research.elamur.ai/free/en/papers/li-2025-adaptive-tool-use-large-language/). arXiv preprint arXiv:2502.12961.
30. Xinhao Li, Ziang Yan, Desen Meng, Lu Dong, Xiangyu Zeng, Yinan He, Yali Wang, Yu Qiao, Yi Wang, and Limin Wang. 2025e. Videochat-r1: Enhancing spatio-temporal perception via reinforcement fine-tuning. arXiv preprint arXiv:2504.06958. — [arXiv:2504.06958](https://arxiv.org/abs/2504.06958) [find](https://scholar.google.com/scholar?q=Xinhao+Li%2C+Ziang+Yan%2C+Desen+Meng%2C+Lu+Dong%2C+Xiangyu+Zeng%2C+Yinan+He%2C+Yali+Wang%2C+Yu+Qiao%2C+Yi+Wang%2C+and+Limin+Wang%2E+2025e%2E+Videochat%2Dr1%3A+Enhancing+spatio%2Dtemporal+perception+via+reinforcement+fine%2Dtuning%2E)
31. Haotian Liu, Chunyuan Li, Yuheng Li, and Yong Jae Lee. 2024a. [Improved baselines with visual instruction tuning](https://md.research.elamur.ai/free/en/papers/liu-2023-improved-baselines-visual-instruction-tuning/). In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 26296–26306.
32. Yuan Liu, Haodong Duan, Yuanhan Zhang, Bo Li, Songyang Zhang, Wangbo Zhao, Yike Yuan, Jiaqi Wang, Conghui He, Ziwei Liu, and 1 others. 2024b. [Mmbench: Is your multi-modal model an all-around player?](https://md.research.elamur.ai/free/en/papers/liu-2023-mmbench-multi-modal-model-all/) In European conference on computer vision, pages 216–233. Springer.
33. Yuqi Liu, Bohao Peng, Zhisheng Zhong, Zihao Yue, Fanbin Lu, Bei Yu, and Jiaya Jia. 2025a. Seg-zero: Reasoning-chain guided segmentation via cognitive reinforcement. arXiv preprint arXiv:2503.06520. — [arXiv:2503.06520](https://arxiv.org/abs/2503.06520) [find](https://scholar.google.com/scholar?q=Yuqi+Liu%2C+Bohao+Peng%2C+Zhisheng+Zhong%2C+Zihao+Yue%2C+Fanbin+Lu%2C+Bei+Yu%2C+and+Jiaya+Jia%2E+2025a%2E+Seg%2Dzero%3A+Reasoning%2Dchain+guided+segmentation+via+cognitive+reinforcement%2E+arXiv+preprint+arXiv%3A2503%2E06520%2E+%E2%80%94+)
34. Ziyu Liu, Zeyi Sun, Yuhang Zang, Xiaoyi Dong, Yuhang Cao, Haodong Duan, Dahua Lin, and Jiaqi Wang. 2025b. Visual-rft: Visual reinforcement fine-tuning. arXiv preprint arXiv:2503.01785. — [arXiv:2503.01785](https://arxiv.org/abs/2503.01785) [find](https://scholar.google.com/scholar?q=Ziyu+Liu%2C+Zeyi+Sun%2C+Yuhang+Zang%2C+Xiaoyi+Dong%2C+Yuhang+Cao%2C+Haodong+Duan%2C+Dahua+Lin%2C+and+Jiaqi+Wang%2E+2025b%2E+Visual%2Drft%3A+Visual+reinforcement+fine%2Dtuning%2E+arXiv+preprint+arXiv%3A2503%2E01785%2E+%E2%80%94+%5BarXiv%3A2503%2E0)
35. Ilya Loshchilov and Frank Hutter. 2017. Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101. [find](https://scholar.google.com/scholar?q=Ilya+Loshchilov+and+Frank+Hutter%2E+2017%2E+Decoupled+weight+decay+regularization%2E+arXiv+preprint+arXiv%3A1711%2E05101%2E)
36. Pan Lu, Hritik Bansal, Tony Xia, Jiacheng Liu, Chunyuan Li, Hannaneh Hajishirzi, Hao Cheng, Kai-Wei Chang, Michel Galley, and Jianfeng Gao. 2024. [Mathvista: Evaluating mathematical reasoning of foundation models in visual contexts](https://md.research.elamur.ai/free/en/papers/lu-2023-mathvista-evaluating-mathematical-reasoning-foundation/). In International Conference on Learning Representations (ICLR).
37. Minesh Mathew, Viraj Bagal, Rubèn Tito, Dimosthenis Karatzas, Ernest Valveny, and CV Jawahar. 2022. Infographicvqa. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pages 1697–1706. [find](https://scholar.google.com/scholar?q=Minesh+Mathew%2C+Viraj+Bagal%2C+Rub%C3%A8n+Tito%2C+Dimosthenis+Karatzas%2C+Ernest+Valveny%2C+and+CV+Jawahar%2E+2022%2E+Infographicvqa%2E+In+Proceedings+of+the+IEEE%2FCVF+Winter+Conference+on+Applications+of+Computer+Vision%2C)
38. Jiahao Meng, Xiangtai Li, Haochen Wang, Yue Tan, Tao Zhang, Lingdong Kong, Yunhai Tong, Anran Wang, Zhiyang Teng, Yujing Wang, and 1 others. 2025. Open-o3 video: Grounded video reasoning with explicit spatio-temporal evidence. arXiv preprint arXiv:2510.20579. — [arXiv:2510.20579](https://arxiv.org/abs/2510.20579) [find](https://scholar.google.com/scholar?q=Jiahao+Meng%2C+Xiangtai+Li%2C+Haochen+Wang%2C+Yue+Tan%2C+Tao+Zhang%2C+Lingdong+Kong%2C+Yunhai+Tong%2C+Anran+Wang%2C+Zhiyang+Teng%2C+Yujing+Wang%2C+and+1+others%2E+2025%2E+Open%2Do3+video%3A+Grounded+video+reasoning+with+explicit)
39. OpenAI. 2024. Hello gpt-4o. [https://openai.com/](https://openai.com/) index/hello-gpt-4o/. Accessed 2025-09-19. [↗](https://openai.com/)
40. OpenAI. 2025. Thinking with images. [find](https://scholar.google.com/scholar?q=OpenAI%2E+2025%2E+Thinking+with+images%2E)
41. Yingzhe Peng, Gongrui Zhang, Miaosen Zhang, Zhiyuan You, Jie Liu, Qipeng Zhu, Kai Yang, Xingzhong Xu, Xin Geng, and Xu Yang. 2025. Lmm-r1: Empowering 3b lmms with strong reasoning abilities through two-stage rule-based rl. arXiv preprint arXiv:2503.07536. — [arXiv:2503.07536](https://arxiv.org/abs/2503.07536) [find](https://scholar.google.com/scholar?q=Yingzhe+Peng%2C+Gongrui+Zhang%2C+Miaosen+Zhang%2C+Zhiyuan+You%2C+Jie+Liu%2C+Qipeng+Zhu%2C+Kai+Yang%2C+Xingzhong+Xu%2C+Xin+Geng%2C+and+Xu+Yang%2E+2025%2E+Lmm%2Dr1%3A+Empowering+3b+lmms+with+strong+reasoning+abilities+through+tw)
42. Zhihong Shao, Peiyi Wang, Qihao Zhu, Runxin Xu, Junxiao Song, Xiao Bi, Haowei Zhang, Mingchuan Zhang, YK Li, Yang Wu, and 1 others. 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/). arXiv preprint arXiv:2402.03300.
43. Haozhan Shen, Peng Liu, Jingcheng Li, Chunxin Fang, Yibo Ma, Jiajia Liao, Qiaoli Shen, Zilun Zhang, Kangjia Zhao, Qianqian Zhang, and 1 others. 2025. Vlm-r1: A stable and generalizable r1-style large vision-language model. arXiv preprint arXiv:2504.07615. [find](https://scholar.google.com/scholar?q=Haozhan+Shen%2C+Peng+Liu%2C+Jingcheng+Li%2C+Chunxin+Fang%2C+Yibo+Ma%2C+Jiajia+Liao%2C+Qiaoli+Shen%2C+Zilun+Zhang%2C+Kangjia+Zhao%2C+Qianqian+Zhang%2C+and+1+others%2E+2025%2E+Vlm%2Dr1%3A+A+stable+and+generalizable+r1%2Dstyle+large+)
44. Guangming Sheng, Chi Zhang, Zilingfeng Ye, Xibin Wu, Wang Zhang, Ru Zhang, Yanghua Peng, Haibin Lin, and Chuan Wu. 2024. [Hybridflow: A flexible and efficient rlhf framework](https://md.research.elamur.ai/free/en/papers/sheng-2024-hybridflow-flexible-efficient-rlhf-framework/). arXiv preprint arXiv: 2409.19256.
45. Fangxun Shu, Lei Zhang, Hao Jiang, and Cihang Xie. 2023. Audio-visual llm for video understanding. arXiv preprint arXiv:2312.06720. — [arXiv:2312.06720](https://arxiv.org/abs/2312.06720) [find](https://scholar.google.com/scholar?q=Fangxun+Shu%2C+Lei+Zhang%2C+Hao+Jiang%2C+and+Cihang+Xie%2E+2023%2E+Audio%2Dvisual+llm+for+video+understanding%2E+arXiv+preprint+arXiv%3A2312%2E06720%2E+%E2%80%94+%5BarXiv%3A2312%2E06720%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2312%2E06720%29)
46. Yan Shu, Zheng Liu, Peitian Zhang, Minghao Qin, Junjie Zhou, Zhengyang Liang, Tiejun Huang, and Bo Zhao. 2025. Video-xl: Extra-long vision language model for hour-scale video understanding. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). [find](https://scholar.google.com/scholar?q=Yan+Shu%2C+Zheng+Liu%2C+Peitian+Zhang%2C+Minghao+Qin%2C+Junjie+Zhou%2C+Zhengyang+Liang%2C+Tiejun+Huang%2C+and+Bo+Zhao%2E+2025%2E+Video%2Dxl%3A+Extra%2Dlong+vision+language+model+for+hour%2Dscale+video+understanding%2E+In+Proceed)
47. Alex Su, Haozhe Wang, Weiming Ren, Fangzhen Lin, and Wenhu Chen. 2025a. Pixel reasoner: Incentivizing pixel-space reasoning with curiosity-driven reinforcement learning. arXiv preprint arXiv:2505.15966. — [arXiv:2505.15966](https://arxiv.org/abs/2505.15966) [find](https://scholar.google.com/scholar?q=Alex+Su%2C+Haozhe+Wang%2C+Weiming+Ren%2C+Fangzhen+Lin%2C+and+Wenhu+Chen%2E+2025a%2E+Pixel+reasoner%3A+Incentivizing+pixel%2Dspace+reasoning+with+curiosity%2Ddriven+reinforcement+learning%2E+arXiv+preprint+arXiv%3A2505%2E1596)
48. Jinyan Su, Jennifer Healey, Preslav Nakov, and Claire Cardie. 2025b. Between underthinking and overthinking: An empirical study of reasoning length and correctness in llms. arXiv preprint arXiv:2505.00127. — [arXiv:2505.00127](https://arxiv.org/abs/2505.00127) [find](https://scholar.google.com/scholar?q=Jinyan+Su%2C+Jennifer+Healey%2C+Preslav+Nakov%2C+and+Claire+Cardie%2E+2025b%2E+Between+underthinking+and+overthinking%3A+An+empirical+study+of+reasoning+length+and+correctness+in+llms%2E+arXiv+preprint+arXiv%3A2505%2E0)
49. Zhaochen Su, Linjie Li, Mingyang Song, Yunzhuo Hao, Zhengyuan Yang, Jun Zhang, Guanjie Chen, Jiawei Gu, Juntao Li, Xiaoye Qu, and 1 others. 2025c. Openthinkimg: Learning to think with images via visual tool reinforcement learning. arXiv preprint arXiv:2505.08617. — [arXiv:2505.08617](https://arxiv.org/abs/2505.08617) [find](https://scholar.google.com/scholar?q=Zhaochen+Su%2C+Linjie+Li%2C+Mingyang+Song%2C+Yunzhuo+Hao%2C+Zhengyuan+Yang%2C+Jun+Zhang%2C+Guanjie+Chen%2C+Jiawei+Gu%2C+Juntao+Li%2C+Xiaoye+Qu%2C+and+1+others%2E+2025c%2E+Openthinkimg%3A+Learning+to+think+with+images+via+visua)
50. Zhaochen Su, Peng Xia, Hangyu Guo, Zhenhua Liu, Yan Ma, Xiaoye Qu, Jiaqi Liu, Yanshu Li, Kaide Zeng, Zhengyuan Yang, and 1 others. 2025d. Thinking with images for multimodal reasoning: Foundations, methods, and future frontiers. arXiv preprint arXiv:2506.23918. — [arXiv:2506.23918](https://arxiv.org/abs/2506.23918) [find](https://scholar.google.com/scholar?q=Zhaochen+Su%2C+Peng+Xia%2C+Hangyu+Guo%2C+Zhenhua+Liu%2C+Yan+Ma%2C+Xiaoye+Qu%2C+Jiaqi+Liu%2C+Yanshu+Li%2C+Kaide+Zeng%2C+Zhengyuan+Yang%2C+and+1+others%2E+2025d%2E+Thinking+with+images+for+multimodal+reasoning%3A+Foundations%2C+me)
51. Huajie Tan, Yuheng Ji, Xiaoshuai Hao, Minglan Lin, Pengwei Wang, Zhongyuan Wang, and Shanghang Zhang. 2025. Reason-rft: Reinforcement fine-tuning for visual reasoning. arXiv preprint arXiv:2503.20752. — [arXiv:2503.20752](https://arxiv.org/abs/2503.20752) [find](https://scholar.google.com/scholar?q=Huajie+Tan%2C+Yuheng+Ji%2C+Xiaoshuai+Hao%2C+Minglan+Lin%2C+Pengwei+Wang%2C+Zhongyuan+Wang%2C+and+Shanghang+Zhang%2E+2025%2E+Reason%2Drft%3A+Reinforcement+fine%2Dtuning+for+visual+reasoning%2E+arXiv+preprint+arXiv%3A2503%2E20752%2E)
52. Xinyu Tian, Shu Zou, Zhaoyuan Yang, Mengqi He, Fabian Waschkowski, Lukas Wesemann, Peter Tu, and Jing Zhang. 2025. More thought, less accuracy? on the dual nature of reasoning in vision-language models. arXiv preprint arXiv:2509.25848. — [arXiv:2509.25848](https://arxiv.org/abs/2509.25848) [find](https://scholar.google.com/scholar?q=Xinyu+Tian%2C+Shu+Zou%2C+Zhaoyuan+Yang%2C+Mengqi+He%2C+Fabian+Waschkowski%2C+Lukas+Wesemann%2C+Peter+Tu%2C+and+Jing+Zhang%2E+2025%2E+More+thought%2C+less+accuracy%3F+on+the+dual+nature+of+reasoning+in+vision%2Dlanguage+model)
53. Chaoyang Wang, Yangfan He, Yiyang Zhou, Yixuan Wang, Jiaqi Liu, Peng Xia, Zhengzhong Tu, Mohit Bansal, and Huaxiu Yao. 2025a. Knowing the answer isn’t enough: Fixing reasoning path failures in lvlms. arXiv preprint arXiv:2512.06258. — [arXiv:2512.06258](https://arxiv.org/abs/2512.06258) [find](https://scholar.google.com/scholar?q=Chaoyang+Wang%2C+Yangfan+He%2C+Yiyang+Zhou%2C+Yixuan+Wang%2C+Jiaqi+Liu%2C+Peng+Xia%2C+Zhengzhong+Tu%2C+Mohit+Bansal%2C+and+Huaxiu+Yao%2E+2025a%2E+Knowing+the+answer+isn%E2%80%99t+enough%3A+Fixing+reasoning+path+failures+in+lvlms%2E+)
54. Chaoyang Wang, Zeyu Zhang, Meng Meng, Xu Zhou, and Haiyun Jiang. 2025b. Vision-ekipl: External knowledge-infused policy learning for visual reasoning. arXiv preprint arXiv:2506.06856. — [arXiv:2506.06856](https://arxiv.org/abs/2506.06856) [find](https://scholar.google.com/scholar?q=Chaoyang+Wang%2C+Zeyu+Zhang%2C+Meng+Meng%2C+Xu+Zhou%2C+and+Haiyun+Jiang%2E+2025b%2E+Vision%2Dekipl%3A+External+knowledge%2Dinfused+policy+learning+for+visual+reasoning%2E+arXiv+preprint+arXiv%3A2506%2E06856%2E+%E2%80%94+%5BarXiv%3A2506%2E06)
55. Haochen Wang, Xiangtai Li, Zilong Huang, Anran Wang, Jiacong Wang, Tao Zhang, Jiani Zheng, Sule Bai, Zijian Kang, Jiashi Feng, and 1 others. 2025c. Traceable evidence enhanced visual grounded reasoning: Evaluation and methodology. arXiv preprint arXiv:2507.07999. — [arXiv:2507.07999](https://arxiv.org/abs/2507.07999) [find](https://scholar.google.com/scholar?q=Haochen+Wang%2C+Xiangtai+Li%2C+Zilong+Huang%2C+Anran+Wang%2C+Jiacong+Wang%2C+Tao+Zhang%2C+Jiani+Zheng%2C+Sule+Bai%2C+Zijian+Kang%2C+Jiashi+Feng%2C+and+1+others%2E+2025c%2E+Traceable+evidence+enhanced+visual+grounded+reasonin)
56. Haozhe Wang, Chao Qu, Zuming Huang, Wei Chu, Fangzhen Lin, and Wenhu Chen. 2025d. Vl-rethinker: Incentivizing self-reflection of vision-language models with reinforcement learning. arXiv preprint arXiv:2504.08837. [find](https://scholar.google.com/scholar?q=Haozhe+Wang%2C+Chao+Qu%2C+Zuming+Huang%2C+Wei+Chu%2C+Fangzhen+Lin%2C+and+Wenhu+Chen%2E+2025d%2E+Vl%2Drethinker%3A+Incentivizing+self%2Dreflection+of+vision%2Dlanguage+models+with+reinforcement+learning%2E+arXiv+preprint+arXi)
57. Jiacong Wang, Zijian Kang, Haochen Wang, Haiyong Jiang, Jiawen Li, Bohong Wu, Ya Wang, Jiao Ran, Xiao Liang, Chao Feng, and 1 others. 2025e. Vgr: Visual grounded reasoning. arXiv preprint arXiv:2506.11991. — [arXiv:2506.11991](https://arxiv.org/abs/2506.11991) [find](https://scholar.google.com/scholar?q=Jiacong+Wang%2C+Zijian+Kang%2C+Haochen+Wang%2C+Haiyong+Jiang%2C+Jiawen+Li%2C+Bohong+Wu%2C+Ya+Wang%2C+Jiao+Ran%2C+Xiao+Liang%2C+Chao+Feng%2C+and+1+others%2E+2025e%2E+Vgr%3A+Visual+grounded+reasoning%2E+arXiv+preprint+arXiv%3A2506%2E1)
58. Qi Wang, Yanrui Yu, Ye Yuan, Rui Mao, and Tianfei Zhou. 2025f. Videorft: Incentivizing video reasoning capability in mllms via reinforced fine-tuning. arXiv preprint arXiv:2505.12434. — [arXiv:2505.12434](https://arxiv.org/abs/2505.12434) [find](https://scholar.google.com/scholar?q=Qi+Wang%2C+Yanrui+Yu%2C+Ye+Yuan%2C+Rui+Mao%2C+and+Tianfei+Zhou%2E+2025f%2E+Videorft%3A+Incentivizing+video+reasoning+capability+in+mllms+via+reinforced+fine%2Dtuning%2E+arXiv+preprint+arXiv%3A2505%2E12434%2E+%E2%80%94+%5BarXiv%3A2505%2E12)
59. Shijian Wang, Jiarui Jin, Xingjian Wang, Linxin Song, Runhao Fu, Hecheng Wang, Zongyuan Ge, Yuan Lu, and Xuelian Cheng. 2025g. Video-thinker: Sparking" thinking with videos" via reinforcement learning. arXiv preprint arXiv:2510.23473. — [arXiv:2510.23473](https://arxiv.org/abs/2510.23473) [find](https://scholar.google.com/scholar?q=Shijian+Wang%2C+Jiarui+Jin%2C+Xingjian+Wang%2C+Linxin+Song%2C+Runhao+Fu%2C+Hecheng+Wang%2C+Zongyuan+Ge%2C+Yuan+Lu%2C+and+Xuelian+Cheng%2E+2025g%2E+Video%2Dthinker%3A+Sparking%22+thinking+with+videos%22+via+reinforcement+learning)
60. Yuxuan Wang, Zilong Zheng, Xueliang Zhao, Jinpeng Li, Yueqian Wang, and Dongyan Zhao. 2023. Vstar: A video-grounded dialogue dataset for situated semantic understanding with scene and topic transitions. arXiv preprint arXiv:2305.18756. [find](https://scholar.google.com/scholar?q=Yuxuan+Wang%2C+Zilong+Zheng%2C+Xueliang+Zhao%2C+Jinpeng+Li%2C+Yueqian+Wang%2C+and+Dongyan+Zhao%2E+2023%2E+Vstar%3A+A+video%2Dgrounded+dialogue+dataset+for+situated+semantic+understanding+with+scene+and+topic+transition)
61. Junfei Wu, Jian Guan, Kaituo Feng, Qiang Liu, Shu Wu, Liang Wang, Wei Wu, and Tieniu Tan. 2025. Reinforcing spatial reasoning in vision-language models with interwoven thinking and visual drawing. arXiv preprint arXiv:2506.09965. — [arXiv:2506.09965](https://arxiv.org/abs/2506.09965) [find](https://scholar.google.com/scholar?q=Junfei+Wu%2C+Jian+Guan%2C+Kaituo+Feng%2C+Qiang+Liu%2C+Shu+Wu%2C+Liang+Wang%2C+Wei+Wu%2C+and+Tieniu+Tan%2E+2025%2E+Reinforcing+spatial+reasoning+in+vision%2Dlanguage+models+with+interwoven+thinking+and+visual+drawing%2E+arX)
62. Zilin Xiao, Jaywon Koo, Siru Ouyang, Jefferson Hernandez, Yu Meng, and Vicente Ordonez. 2025. Prox-ythinker: Test-time guidance through small visual reasoners. arXiv preprint arXiv:2505.24872. — [arXiv:2505.24872](https://arxiv.org/abs/2505.24872) [find](https://scholar.google.com/scholar?q=Zilin+Xiao%2C+Jaywon+Koo%2C+Siru+Ouyang%2C+Jefferson+Hernandez%2C+Yu+Meng%2C+and+Vicente+Ordonez%2E+2025%2E+Prox%2Dythinker%3A+Test%2Dtime+guidance+through+small+visual+reasoners%2E+arXiv+preprint+arXiv%3A2505%2E24872%2E+%E2%80%94+%5BarXi)
63. Jihan Yang, Shusheng Yang, Anjali W Gupta, Rilyn Han, Li Fei-Fei, and Saining Xie. 2025a. Thinking in space: How multimodal large language models see, remember, and recall spaces. In Proceedings of the Computer Vision and Pattern Recognition Conference, pages 10632–10643. [find](https://scholar.google.com/scholar?q=Jihan+Yang%2C+Shusheng+Yang%2C+Anjali+W+Gupta%2C+Rilyn+Han%2C+Li+Fei%2DFei%2C+and+Saining+Xie%2E+2025a%2E+Thinking+in+space%3A+How+multimodal+large+language+models+see%2C+remember%2C+and+recall+spaces%2E+In+Proceedings+of+th)
64. Sihan Yang, Runsen Xu, Yiman Xie, Sizhe Yang, Mo Li, Jingli Lin, Chenming Zhu, Xiaochen Chen, Haodong Duan, Xiangyu Yue, and 1 others. 2025b. Mmsi-bench: A benchmark for multi-image spatial intelligence. arXiv preprint arXiv:2505.23764. — [arXiv:2505.23764](https://arxiv.org/abs/2505.23764) [find](https://scholar.google.com/scholar?q=Sihan+Yang%2C+Runsen+Xu%2C+Yiman+Xie%2C+Sizhe+Yang%2C+Mo+Li%2C+Jingli+Lin%2C+Chenming+Zhu%2C+Xiaochen+Chen%2C+Haodong+Duan%2C+Xiangyu+Yue%2C+and+1+others%2E+2025b%2E+Mmsi%2Dbench%3A+A+benchmark+for+multi%2Dimage+spatial+intelligen)
65. Jiahui Zhang, Yurui Chen, Yanpeng Zhou, Yueming Xu, Ze Huang, Jilin Mei, Junhui Chen, Yu-Jie Yuan, Xinyue Cai, Guowei Huang, and 1 others. 2025b. From flatland to space: Teaching vision-language models to perceive and reason in 3d. arXiv preprint arXiv:2503.22976. — [arXiv:2503.22976](https://arxiv.org/abs/2503.22976) [find](https://scholar.google.com/scholar?q=Jiahui+Zhang%2C+Yurui+Chen%2C+Yanpeng+Zhou%2C+Yueming+Xu%2C+Ze+Huang%2C+Jilin+Mei%2C+Junhui+Chen%2C+Yu%2DJie+Yuan%2C+Xinyue+Cai%2C+Guowei+Huang%2C+and+1+others%2E+2025b%2E+From+flatland+to+space%3A+Teaching+vision%2Dlanguage+model)
66. Xiaoying Zhang, Hao Sun, Yipeng Zhang, Kaituo Feng, Chaochao Lu, Chao Yang, and Helen Meng. 2025c. Critique-grpo: Advancing llm reasoning with natural language and numerical feedback. arXiv preprint arXiv:2506.03106. — [arXiv:2506.03106](https://arxiv.org/abs/2506.03106) [find](https://scholar.google.com/scholar?q=Xiaoying+Zhang%2C+Hao+Sun%2C+Yipeng+Zhang%2C+Kaituo+Feng%2C+Chaochao+Lu%2C+Chao+Yang%2C+and+Helen+Meng%2E+2025c%2E+Critique%2Dgrpo%3A+Advancing+llm+reasoning+with+natural+language+and+numerical+feedback%2E+arXiv+preprint+a)
67. Yi-Fan Zhang, Xingyu Lu, Shukang Yin, Chaoyou Fu, Wei Chen, Xiao Hu, Bin Wen, Kaiyu Jiang, Changyi Liu, Tianke Zhang, and 1 others. 2025d. Thyme: Think beyond images. arXiv preprint arXiv:2508.11630. — [arXiv:2508.11630](https://arxiv.org/abs/2508.11630) [find](https://scholar.google.com/scholar?q=Yi%2DFan+Zhang%2C+Xingyu+Lu%2C+Shukang+Yin%2C+Chaoyou+Fu%2C+Wei+Chen%2C+Xiao+Hu%2C+Bin+Wen%2C+Kaiyu+Jiang%2C+Changyi+Liu%2C+Tianke+Zhang%2C+and+1+others%2E+2025d%2E+Thyme%3A+Think+beyond+images%2E+arXiv+preprint+arXiv%3A2508%2E11630%2E+)
68. Ziwei Zheng, Michael Yang, Jack Hong, Chenxiao Zhao, Guohai Xu, Le Yang, Chao Shen, and Xing Yu. 2025a. Deepeyes: Incentivizing" thinking with images" via reinforcement learning. arXiv preprint arXiv:2505.14362. — [arXiv:2505.14362](https://arxiv.org/abs/2505.14362) [find](https://scholar.google.com/scholar?q=Ziwei+Zheng%2C+Michael+Yang%2C+Jack+Hong%2C+Chenxiao+Zhao%2C+Guohai+Xu%2C+Le+Yang%2C+Chao+Shen%2C+and+Xing+Yu%2E+2025a%2E+Deepeyes%3A+Incentivizing%22+thinking+with+images%22+via+reinforcement+learning%2E+arXiv+preprint+arXiv%3A)
69. Ziwei Zheng, Michael Yang, Jack Hong, Chenxiao Zhao, Guohai Xu, Le Yang, Chao Shen, and Xing Yu. 2025b. Deepeyes: Incentivizing “thinking with images" via reinforcement learning. arXiv preprint arXiv:2505.14362. — [arXiv:2505.14362](https://arxiv.org/abs/2505.14362) [find](https://scholar.google.com/scholar?q=Ziwei+Zheng%2C+Michael+Yang%2C+Jack+Hong%2C+Chenxiao+Zhao%2C+Guohai+Xu%2C+Le+Yang%2C+Chao+Shen%2C+and+Xing+Yu%2E+2025b%2E+Deepeyes%3A+Incentivizing+%E2%80%9Cthinking+with+images%22+via+reinforcement+learning%2E+arXiv+preprint+arXiv%3A)
70. Jinguo Zhu, Weiyun Wang, Zhe Chen, Zhaoyang Liu, Shenglong Ye, Lixin Gu, Hao Tian, Yuchen Duan, Weijie Su, Jie Shao, and 1 others. 2025. [Internvl3: Exploring advanced training and test-time recipes for open-source multimodal models](https://md.research.elamur.ai/free/en/papers/zhu-2025-internvl3-exploring-advanced-training/). arXiv preprint arXiv:2504.10479.
71. Zhao Yang, Jiaqi Wang, Xubing Ye, Yansong Tang, Kai Chen, Hengshuang Zhao, and Philip HS Torr. 2024. Language-aware vision transformer for referring segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence. [find](https://scholar.google.com/scholar?q=Zhao+Yang%2C+Jiaqi+Wang%2C+Xubing+Ye%2C+Yansong+Tang%2C+Kai+Chen%2C+Hengshuang+Zhao%2C+and+Philip+HS+Torr%2E+2024%2E+Language%2Daware+vision+transformer+for+referring+segmentation%2E+IEEE+Transactions+on+Pattern+Analysis)
72. Qiying Yu, Zheng Zhang, Ruofei Zhu, Yufeng Yuan, Xiaochen Zuo, Yu Yue, Weinan Dai, Tiantian Fan, Gaohong Liu, Lingjun Liu, and 1 others. 2025. [Dapo: An open-source llm reinforcement learning system at scale](https://md.research.elamur.ai/free/en/papers/yu-2025-dapo-open-source-llm-reinforcement/). arXiv preprint arXiv:2503.14476.
73. Jiakang Yuan, Tianshuo Peng, Yilei Jiang, Yiting Lu, Renrui Zhang, Kaituo Feng, Chaoyou Fu, Tao Chen, Lei Bai, Bo Zhang, and 1 others. 2025. Mme-reasoning: A comprehensive benchmark for logical reasoning in mllms. arXiv preprint arXiv:2505.21327. — [arXiv:2505.21327](https://arxiv.org/abs/2505.21327) [find](https://scholar.google.com/scholar?q=Jiakang+Yuan%2C+Tianshuo+Peng%2C+Yilei+Jiang%2C+Yiting+Lu%2C+Renrui+Zhang%2C+Kaituo+Feng%2C+Chaoyou+Fu%2C+Tao+Chen%2C+Lei+Bai%2C+Bo+Zhang%2C+and+1+others%2E+2025%2E+Mme%2Dreasoning%3A+A+comprehensive+benchmark+for+logical+reason)
74. Haoji Zhang, Xin Gu, Jiawen Li, Chixiang Ma, Sule Bai, Chubin Zhang, Bowen Zhang, Zhichao Zhou, Dongliang He, and Yansong Tang. 2025a. Thinking with videos: Multimodal tool-augmented reinforcement learning for long video reasoning. arXiv preprint arXiv:2508.04416. — [arXiv:2508.04416](https://arxiv.org/abs/2508.04416) [find](https://scholar.google.com/scholar?q=Haoji+Zhang%2C+Xin+Gu%2C+Jiawen+Li%2C+Chixiang+Ma%2C+Sule+Bai%2C+Chubin+Zhang%2C+Bowen+Zhang%2C+Zhichao+Zhou%2C+Dongliang+He%2C+and+Yansong+Tang%2E+2025a%2E+Thinking+with+videos%3A+Multimodal+tool%2Daugmented+reinforcement+lea)

*Updated 1 November 2026*