Elamur Research⌕
☰
home / papers / 2026 / Kimi K2.5: Visual Agentic Intelligence

Kimi K2.5: Visual Agentic Intelligence

Paper · 2026 · Kimi Team, Tongtong Bai, Yifan Bai et al.

Summary

Kimi K2.5 addresses two weaknesses of current agentic LLMs. Vision is often added to a text model late in training, and agents usually run tool calls one after another, so latency grows with task size. Built on Kimi K2, the model is jointly pre-trained on roughly 15 trillion mixed text and visual tokens. Vision is introduced early at a modest, constant share. Ablations showed this beats late, vision-heavy mixing under an equal token budget. Images and video pass through MoonViT-3D, a native-resolution encoder. Post-training begins with zero-vision SFT, which uses only text data and performs image manipulation through IPython code. Joint RL follows, with domains grouped by ability rather than by modality. Visual RL even improved text-only scores. The second contribution, Agent Swarm, uses Parallel-Agent RL (PARL) to train an orchestrator that spawns and schedules frozen sub-agents running in parallel. The result is an open-weight model with strong agentic-search results and much lower latency, a practical base for multimodal agents.

Key points

  • Pre-training mixes about 15T vision and text tokens from early on. In ablations, early fusion with a 10%:90% vision-text ratio outperformed mid (20%:80%) and late (50%:50%) injection on most measured categories.
  • MoonViT-3D uses NaViT-style packing for variable resolution. It groups video frames in fours and averages them over time at the patch level, which fits about 4× longer videos into the same context. Image and video encoders share all weights.
  • Vision RL raised text benchmarks:
    • MMLU-Pro: 84.7 → 86.4
    • GPQA-Diamond: 84.3 → 86.4
    • LongBench v2: 56.7 → 58.9
  • Agent Swarm results compared with single-agent K2.5:
    • BrowseComp: 60.6% → 78.4%, ahead of GPT-5.2 Pro at 77.9%
    • WideSearch Item-F1: 72.7% → 79.0%, ahead of Claude Opus 4.5 at 76.2%
    • Time to reach target performance on WideSearch: 3×–4.5× shorter
  • Sub-agents also act as proactive context management (context sharding), outperforming Discard-all truncation on BrowseComp. The post-trained checkpoint is released as moonshotai/Kimi-K2.5 on Hugging Face.

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 3The field of science this work belongs to (OpenAlex fields).Computer Science · 9,086 worksArtificial Intelligence · 8,889 worksComputer Vision and Pattern Recognition · 1,282 works

Cite

Cite as Kimi Team, Tongtong Bai, Yifan Bai, Yiping Bao, S.H. Cai, Yuan Cao, Ziwei Chai, Y. Charles, H.S. Che, Cheng Chen, Guanduo Chen, Huarong Chen, Jia Chen, Jianlong Chen, Jun Chen, Kefan Chen, Liang Chen, Ruijue Chen, Xinhao Chen, Yanru Chen, Yanxu Chen, Yicun Chen, Yimin Chen, Yingjiang Chen, Yuankun Chen, Yujie Chen, Yutian Chen, Zhirong Chen, Ziwei Chen, Dazhi Cheng, Yean Cheng, Minghan Chu, Jialei Cui, Jiaqi Deng, Muxi Diao, Hao Ding, Mengfan Dong, Mengnan Dong, Yuxin Dong, Yuhao Dong, Angang Du, Chenzhuang Du, Dikang Du, Lingxiao Du, Yulun Du, Yu Fan, Shengjun Fang, Qiulin Feng, Yichen Feng, Garimugai Fu, Kelin Fu, Hongcheng Gao, Tong Gao, Yuyao Ge, Shangyi Geng, Chengyang Gong, Xiaochen Gong, Zhuoma Gongque, Qizheng Gu, Xinran Gu, Yicheng Gu, Longyu Guan, Shuhao Guan, Yuanying Guo, Xiaoru Hao, Dailan He, Tianhong He, Weiran He, Wenyang He, Yibo He, Yunjia He, Chao Hong, Hao Hu, Jiaxi Hu, Yangyang Hu, Zhenxing Hu, Ke Huang, Ruiyuan Huang, Weixiao Huang, Zhiqi Huang, Chaobo Jia, Tao Jiang, Zhejun Jiang, Xinyi Jin, Yu Jing, Guokun Lai, Aidi Li, C. Li, Cheng Li, Fang Li, Guanghe Li, Guanyu Li, Haitao Li, Haoyang Li, Jia Li, Jingwei Li, Junxiong Li, Lincan Li, Mo Li, Weihong Li, Wentao Li, Xinhang Li, Xinhao Li, Yang Li, Yanhao Li, Yiwei Li, Yuxiao Li, Zhaowei Li, Zhaoxi Li, Zheming Li, Weilong Liao, Jiawei Lin, Xiaohan Lin, Yibo Lin, Zhishan Lin, Zichao Lin, Cheng Liu, Chenyu Liu, Hongzhang Liu, Liang Liu, Shaowei Liu, Shudong Liu, Shuran Liu, Tianwei Liu, Tianyu Liu, Weizhou Liu, Xiangyan Liu, Yangyang Liu, Yanming Liu, Yibo Liu, Yuanxin Liu, Zhengying Liu, Zhongnuo Liu, Enzhe Lu, Haoyu Lu, Zhiyuan Lu, G. Luo, Junyu Luo, Tongxu Luo, Yashuo Luo, Long Ma, Shaoguang Mao, Yuan Mei, Xin Men, Fanqing Meng, Zhiyong Meng, Yibo Miao, Minqing Ni, Kun Ouyang, Siyuan Pan, Bo Pang, Yuchao Qian, Ruoyu Qin, Zeyu Qin, Jiezhong Qiu, Bowen Qu, Zeyu Shang, Youbo Shao, Tianxiao Shen, Zhennan Shen, Juanfeng Shi, Lidong Shi, Shengyuan Shi, Feifan Song, Pengwei Song, Tianhui Song, Xiaoxi Song, Hongjin Su, Jianlin Su, Zhaochen Su, Lin Sui, Jinsong Sun, Junyao Sun, Tongyu Sun, Flood Sung, Yunpeng Tai, Chuning Tang, Heyi Tang, Xiaojuan Tang, Zhengyang Tang, Jiawen Tao, Shiyuan Teng, Chaoran Tian, Pengfei Tian, Bowen Wang, Chensi Wang, Chuang Wang, Congcong Wang, Dingkun Wang, Dinglu Wang, Dongliang Wang, Feng Wang, Hailong Wang, Haiming Wang, Hao Wang, Hengzhi Wang, Huaqing Wang, Hui Wang, Jiahao Wang, Jinhong Wang, Jiuzheng Wang, Kaixin Wang, Linian Wang, Qibin Wang, Shengjie Wang, Shuyi Wang, Si Wang, Wei Wang, Xiaochen Wang, Xinyuan Wang, Yao Wang, Yejie Wang, Yipu Wang, Yiqin Wang, Yucheng Wang, Yuzhi Wang, Zhaoji Wang, Zhaowei Wang, Zhengtao Wang, Zhexu Wang, Zifan Wang, Zihan Wang, Zizhe Wang, Chu Wei, Ming Wei, Chuan Wen, Zichen Wen, Chengjie Wu, Haoning Wu, Junyan Wu, Rucong Wu, Wenhao Wu, Yuefeng Wu, Yuhao Wu, Yuxin Wu, Zijian Wu, Chenjun Xiao, Jin Xie, Xiaotong Xie, Yuchong Xie, Bowei Xing, Boyu Xu, Jianfan Xu, Jing Xu, Jinjing Xu, L.H. Xu, Lin Xu, Suting Xu, Weixin Xu, Xinbo Xu, Xinran Xu, Yangchuan Xu, Yichang Xu, Yuemeng Xu, Zelai Xu, Ziyao Xu, Junjie Yan, Yuzi Yan, Guangyao Yang, Hao Yang, Junwei Yang, Kai Yang, Ningyuan Yang, Xiaofei Yang, Xinlong Yang, Xinyu Yang, Ying Yang, Yi Yang, Yi Yang, Zhen Yang, Zhilin Yang, Zonghan Yang, Haotian Yao, Dan Ye, Haoran Ye, Wenjie Ye, Zhuorui Ye, Peng Yebo, Bohong Yin, Chengzhen Yu, Longhui Yu, Tao Yu, Tianxiang Yu, Enming Yuan, Mengjie Yuan, Xiaokun Yuan, Yang Yue, Weihao Zeng, Dunyuan Zha, Haobing Zhan, Dehao Zhang, Hao Zhang, Jin Zhang, Puqi Zhang, Qiao Zhang, Rui Zhang, Xiaobin Zhang, Xiaoyun Zhang, Y. Zhang, Yadong Zhang, Yangkun Zhang, Yichi Zhang, Yizhi Zhang, Yongting Zhang, Yu Zhang, Yushun Zhang, Yutao Zhang, Yutong Zhang, Zheng Zhang, Chenguang Zhao, Feifan Zhao, Jinxiang Zhao, Shuai Zhao, Xiangyu Zhao, Xuanle Zhao, Yikai Zhao, Zijia Zhao, Huabin Zheng, Ruihan Zheng, Shaojie Zheng, Tengyang Zheng, Junfeng Zhong, Longguang Zhong, Weiming Zhong, M. Zhou, Runjie Zhou, Xinyu Zhou, Zaida Zhou, Jinguo Zhu, Liya Zhu, Xinhao Zhu, Yuxuan Zhu, Zhen Zhu, Jingze Zhuang, Weiyu Zhuang, Ying Zou and Xinxing Zu. 2026. Kimi K2.5: Visual Agentic Intelligence. arXiv:2602.02276.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.48550/arxiv.2602.02276 · arXiv 2602.02276

@misc{team2026kimi,
  title = {{Kimi K2.5: Visual Agentic Intelligence}},
  author = {Kimi Team, Tongtong Bai, Yifan Bai, Yiping Bao, S.H. Cai, Yuan Cao, Ziwei Chai, Y. Charles, H.S. Che, Cheng Chen, Guanduo Chen, Huarong Chen, Jia Chen, Jianlong Chen, Jun Chen, Kefan Chen, Liang Chen, Ruijue Chen, Xinhao Chen, Yanru Chen, Yanxu Chen, Yicun Chen, Yimin Chen, Yingjiang Chen, Yuankun Chen, Yujie Chen, Yutian Chen, Zhirong Chen, Ziwei Chen, Dazhi Cheng, Yean Cheng, Minghan Chu, Jialei Cui, Jiaqi Deng, Muxi Diao, Hao Ding, Mengfan Dong, Mengnan Dong, Yuxin Dong, Yuhao Dong, Angang Du, Chenzhuang Du, Dikang Du, Lingxiao Du, Yulun Du, Yu Fan, Shengjun Fang, Qiulin Feng, Yichen Feng, Garimugai Fu, Kelin Fu, Hongcheng Gao, Tong Gao, Yuyao Ge, Shangyi Geng, Chengyang Gong, Xiaochen Gong, Zhuoma Gongque, Qizheng Gu, Xinran Gu, Yicheng Gu, Longyu Guan, Shuhao Guan, Yuanying Guo, Xiaoru Hao, Dailan He, Tianhong He, Weiran He, Wenyang He, Yibo He, Yunjia He, Chao Hong, Hao Hu, Jiaxi Hu, Yangyang Hu, Zhenxing Hu, Ke Huang, Ruiyuan Huang, Weixiao Huang, Zhiqi Huang, Chaobo Jia, Tao Jiang, Zhejun Jiang, Xinyi Jin, Yu Jing, Guokun Lai, Aidi Li, C. Li, Cheng Li, Fang Li, Guanghe Li, Guanyu Li, Haitao Li, Haoyang Li, Jia Li, Jingwei Li, Junxiong Li, Lincan Li, Mo Li, Weihong Li, Wentao Li, Xinhang Li, Xinhao Li, Yang Li, Yanhao Li, Yiwei Li, Yuxiao Li, Zhaowei Li, Zhaoxi Li, Zheming Li, Weilong Liao, Jiawei Lin, Xiaohan Lin, Yibo Lin, Zhishan Lin, Zichao Lin, Cheng Liu, Chenyu Liu, Hongzhang Liu, Liang Liu, Shaowei Liu, Shudong Liu, Shuran Liu, Tianwei Liu, Tianyu Liu, Weizhou Liu, Xiangyan Liu, Yangyang Liu, Yanming Liu, Yibo Liu, Yuanxin Liu, Zhengying Liu, Zhongnuo Liu, Enzhe Lu, Haoyu Lu, Zhiyuan Lu, G. Luo, Junyu Luo, Tongxu Luo, Yashuo Luo, Long Ma, Shaoguang Mao, Yuan Mei, Xin Men, Fanqing Meng, Zhiyong Meng, Yibo Miao, Minqing Ni, Kun Ouyang, Siyuan Pan, Bo Pang, Yuchao Qian, Ruoyu Qin, Zeyu Qin, Jiezhong Qiu, Bowen Qu, Zeyu Shang, Youbo Shao, Tianxiao Shen, Zhennan Shen, Juanfeng Shi, Lidong Shi, Shengyuan Shi, Feifan Song, Pengwei Song, Tianhui Song, Xiaoxi Song, Hongjin Su, Jianlin Su, Zhaochen Su, Lin Sui, Jinsong Sun, Junyao Sun, Tongyu Sun, Flood Sung, Yunpeng Tai, Chuning Tang, Heyi Tang, Xiaojuan Tang, Zhengyang Tang, Jiawen Tao, Shiyuan Teng, Chaoran Tian, Pengfei Tian, Bowen Wang, Chensi Wang, Chuang Wang, Congcong Wang, Dingkun Wang, Dinglu Wang, Dongliang Wang, Feng Wang, Hailong Wang, Haiming Wang, Hao Wang, Hengzhi Wang, Huaqing Wang, Hui Wang, Jiahao Wang, Jinhong Wang, Jiuzheng Wang, Kaixin Wang, Linian Wang, Qibin Wang, Shengjie Wang, Shuyi Wang, Si Wang, Wei Wang, Xiaochen Wang, Xinyuan Wang, Yao Wang, Yejie Wang, Yipu Wang, Yiqin Wang, Yucheng Wang, Yuzhi Wang, Zhaoji Wang, Zhaowei Wang, Zhengtao Wang, Zhexu Wang, Zifan Wang, Zihan Wang, Zizhe Wang, Chu Wei, Ming Wei, Chuan Wen, Zichen Wen, Chengjie Wu, Haoning Wu, Junyan Wu, Rucong Wu, Wenhao Wu, Yuefeng Wu, Yuhao Wu, Yuxin Wu, Zijian Wu, Chenjun Xiao, Jin Xie, Xiaotong Xie, Yuchong Xie, Bowei Xing, Boyu Xu, Jianfan Xu, Jing Xu, Jinjing Xu, L.H. Xu, Lin Xu, Suting Xu, Weixin Xu, Xinbo Xu, Xinran Xu, Yangchuan Xu, Yichang Xu, Yuemeng Xu, Zelai Xu, Ziyao Xu, Junjie Yan, Yuzi Yan, Guangyao Yang, Hao Yang, Junwei Yang, Kai Yang, Ningyuan Yang, Xiaofei Yang, Xinlong Yang, Xinyu Yang, Ying Yang, Yi Yang, Yi Yang, Zhen Yang, Zhilin Yang, Zonghan Yang, Haotian Yao, Dan Ye, Haoran Ye, Wenjie Ye, Zhuorui Ye, Peng Yebo, Bohong Yin, Chengzhen Yu, Longhui Yu, Tao Yu, Tianxiang Yu, Enming Yuan, Mengjie Yuan, Xiaokun Yuan, Yang Yue, Weihao Zeng, Dunyuan Zha, Haobing Zhan, Dehao Zhang, Hao Zhang, Jin Zhang, Puqi Zhang, Qiao Zhang, Rui Zhang, Xiaobin Zhang, Xiaoyun Zhang, Y. Zhang, Yadong Zhang, Yangkun Zhang, Yichi Zhang, Yizhi Zhang, Yongting Zhang, Yu Zhang, Yushun Zhang, Yutao Zhang, Yutong Zhang, Zheng Zhang, Chenguang Zhao, Feifan Zhao, Jinxiang Zhao, Shuai Zhao, Xiangyu Zhao, Xuanle Zhao, Yikai Zhao, Zijia Zhao, Huabin Zheng, Ruihan Zheng, Shaojie Zheng, Tengyang Zheng, Junfeng Zhong, Longguang Zhong, Weiming Zhong, M. Zhou, Runjie Zhou, Xinyu Zhou, Zaida Zhou, Jinguo Zhu, Liya Zhu, Xinhao Zhu, Yuxuan Zhu, Zhen Zhu, Jingze Zhuang, Weiyu Zhuang, Ying Zou and Xinxing Zu},
  year = {2026},
  doi = {10.48550/arxiv.2602.02276},
  eprint = {2602.02276},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2602.02276}
}

References

81 references, 25 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Moonshot AI. Introducing Kimi K2 Thinking. 2025. URL : https://moonshotai.github.io/Kimi-K2/thinking.html. ↗
  2. Moonshot AI. Kimi-Researcher End-to-End RL Training for Emerging Agentic Capabilities. 2025. URL : https://moonshotai.github.io/Kimi-Researcher/. ↗
  3. Amazon Web Services. Amazon Simple Storage Service (Amazon S3). Web. Available at: https://aws.amazon.com/s3/. 2023. URL : https://aws.amazon.com/s3/ (visited on 12/15/2023). ↗
  4. Mathematical Association of America. 2025 American Invitational Mathematics Examination I. Held on February 6, 2025. 2025. URL : https://artofproblemsolving.com/wiki/index.php/2025_AIME_I. ↗
  5. Anthropic. Building multi-agent systems: when and how to use them. 2026. URL : https://claude.com/blog/building-multi-agent-systems-when-and-how-to-use-them. ↗
  6. Anthropic. Claude Opus 4.5 System Card. 2025. URL : https://www - cdn . anthropic . com / bf10f64990cfda0ba858290be7b8cc6317685f47.pdf. find
  7. Anthropic. How we built our multi-agent research system. 2025. URL : https://www.anthropic.com/engineering/multi-agent-research-system. ↗
  8. Shuai Bai et al. Qwen3-VL Technical Report. 2025. arXiv: 2511 . 21631 [cs.CV]. URL : https://arxiv.org/abs/2511.21631. ↗
  9. Yushi Bai et al. LongBench v2: Towards Deeper Understanding and Reasoning on Realistic Long-context Multitasks. 2025. arXiv: 2412.15204 [cs.CL]. URL : https://arxiv.org/abs/2412.15204. ↗
  10. Greg Brockman et al. OpenAI Gym. 2016. arXiv: 1606.01540 [cs.LG]. URL : https://arxiv.org/abs/1606.01540. ↗
  11. Tom B. Brown et al. Language Models are Few-Shot Learners. 2020. arXiv: 2005.14165 [cs.CL]. URL : https://arxiv.org/abs/2005.14165. ↗
  12. Liang Chen et al. BabyVision: Visual Reasoning Beyond Language. 2026. arXiv: 2601.06521 [cs.CV]. URL : https://arxiv.org/abs/2601.06521. — [arXiv:2601.06521](https://arxiv.org/abs/2601.06521) ↗
  13. Xianfu Cheng et al. SimpleVQA: Multimodal Factuality Evaluation for Multimodal Large Language Models. 2025. arXiv: 2502.13059 [cs.CL]. URL : https://arxiv.org/abs/2502.13059. — [arXiv:2502.13059](https://arxiv.org/abs/2502.13059) ↗
  14. DeepSeek-AI et al. DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models. 2025. arXiv: 2512. 02556 [cs.CL]. URL : https://arxiv.org/abs/2512.02556. ↗
  15. Mostafa Dehghani et al. Patch n’ Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolution. 2023. arXiv: 2307.06304 [cs.CV]. URL : https://arxiv.org/abs/2307.06304. — [arXiv:2307.06304](https://arxiv.org/abs/2307.06304) ↗
  16. Xiang Deng et al. “SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?” In: arXiv preprint arXiv:2509.16941 (2025). — [arXiv:2509.16941](https://arxiv.org/abs/2509.16941) find
  17. Chaoyou Fu et al. Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis. 2025. arXiv: 2405.21075 [cs.CV]. URL : https://arxiv.org/abs/2405.21075. ↗
  18. Xingyu Fu et al. BLINK: Multimodal Large Language Models Can See but Not Perceive. 2024. arXiv: 2404. 12390 [cs.CV]. URL : https://arxiv.org/abs/2404.12390. ↗
  19. Samir Yitzhak Gadre et al. “Datacomp: In search of the next generation of multimodal datasets”. In: Advances in Neural Information Processing Systems 36 (2024). find
  20. Google. Gemini 3 Pro. 2025. URL : https://deepmind.google/models/gemini/pro/. ↗
  21. Dong Guo et al. Seed1.5-VL Technical Report. 2025. arXiv: 2505 . 07062 [cs.CV]. URL : https://arxiv.org/abs/2505.07062. ↗
  22. Lukas Haas et al. SimpleQA Verified: A Reliable Factuality Benchmark to Measure Parametric Knowledge. 2025. arXiv: 2509.07968 [cs.CL]. URL : https://arxiv.org/abs/2509.07968. ↗
  23. Yun He et al. AdvancedIF: Rubric-Based Benchmarking and Reinforcement Learning for Advancing LLM Instruction Following. 2025. arXiv: 2511.10507 [cs.CL]. URL : https://arxiv.org/abs/2511.10507. ↗
  24. Wenyi Hong et al. MotionBench: Benchmarking and Improving Fine-grained Video Motion Understanding for Vision Language Models. 2025. arXiv: 2501 . 02955 [cs.CV]. URL : https://arxiv.org/abs/2501.02955. ↗
  25. Kairui Hu et al. Video-MMMU: Evaluating Knowledge Acquisition from Multi-Discipline Professional Videos. 2025. arXiv: 2501.13826 [cs.CV]. URL : https://arxiv.org/abs/2501.13826. — [arXiv:2501.13826](https://arxiv.org/abs/2501.13826) ↗
  26. Liang Hu et al. FinSearchComp: Towards a Realistic, Expert-Level Evaluation of Financial Search and Reasoning. 2025. arXiv: 2509.13160 [cs.CL]. URL : https://arxiv.org/abs/2509.13160. — [arXiv:2509.13160](https://arxiv.org/abs/2509.13160) ↗
  27. Yanping Huang et al. GPipe: Efficient Training of Giant Neural Networks using Pipeline Parallelism. 2019. arXiv: 1811.06965 [cs.CV]. URL : https://arxiv.org/abs/1811.06965. ↗
  28. Naman Jain et al. “Livecodebench: Holistic and contamination free evaluation of large language models for code”. In: arXiv preprint arXiv:2403.07974 (2024).
  29. Carlos E Jimenez et al. “Swe-bench: Can language models resolve real-world github issues?” In: arXiv preprint arXiv:2310.06770 (2023).
  30. Keller Jordan et al. Muon: An optimizer for hidden layers in neural networks. 2024. URL : https://kellerjordan.github.io/posts/muon/. ↗
  31. Kimi Team. “Kimi k1. 5: Scaling reinforcement learning with llms”. In: arXiv preprint arXiv:2501.12599 (2025).
  32. Hugo Laurençon et al. “Obelics: An open web-scale filtered dataset of interleaved image-text documents”. In: Advances in Neural Information Processing Systems 36 (2024).
  33. Dmitry Lepikhin et al. “Gshard: Scaling giant models with conditional computation and automatic sharding”. In: arXiv preprint arXiv:2006.16668 (2020). find
  34. Jingyuan Liu et al. “Muon is Scalable for LLM Training”. In: arXiv preprint arXiv:2502.16982 (2025). find
  35. Yuliang Liu et al. “OCRBench: on the hidden mystery of OCR in large multimodal models”. In: Science China Information Sciences 67.12 (Dec. 2024). ISSN : 1869-1919. DOI : 10.1007/s11432-024-4235-6. URL : http://dx.doi.org/10.1007/s11432-024-4235-6. ↗
  36. Pan Lu et al. MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts. 2024. arXiv: 2310.02255 [cs.CV]. URL : https://arxiv.org/abs/2310.02255. ↗
  37. Thang Luong et al. “Towards Robust Mathematical Reasoning”. In: Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. Ed. by Christos Christodoulopoulos et al. Suzhou, China: Association for Computational Linguistics, Nov. 2025, pp. 35418–35442. ISBN : 979-8-89176-3… find
  38. Minesh Mathew et al. InfographicVQA. 2021. arXiv: 2104.12756 [cs.CV]. URL : https://arxiv.org/abs/2104.12756. — [arXiv:2104.12756](https://arxiv.org/abs/2104.12756) ↗
  39. Mike A Merrill et al. “Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces”. In: arXiv preprint arXiv:2601.11868 (2026). — [arXiv:2601.11868](https://arxiv.org/abs/2601.11868) find
  40. Deepak Narayanan et al. Efficient Large-Scale Language Model Training on GPU Clusters Using Megatron-LM. 2021. arXiv: 2104.04473 [cs.CL]. URL : https://arxiv.org/abs/2104.04473. ↗
  41. OpenAI. Introducing GPT 5.2. 2025. URL : https://openai.com/index/introducing-gpt- 5-2/. ↗
  42. Linke Ouyang et al. OmniDocBench: Benchmarking Diverse PDF Document Parsing with Comprehensive Annotations. 2025. arXiv: 2412.07626 [cs.CV]. URL : https://arxiv.org/abs/2412.07626. — [arXiv:2412.07626](https://arxiv.org/abs/2412.07626) ↗
  43. Tejal Patwardhan et al. GDPval: Evaluating AI Model Performance on Real-World Economically Valuable Tasks. 2025. arXiv: 2510.04374 [cs.LG]. URL : https://arxiv.org/abs/2510.04374. ↗
  44. Bowen Peng et al. “Yarn: Efficient context window extension of large language models”. In: arXiv preprint arXiv:2309.00071 (2023). find
  45. Thinh Pham et al. SealQA: Raising the Bar for Reasoning in Search-Augmented Language Models. Seal-0 is the main subset of this benchmark. 2025. arXiv: 2506.01062 [cs.CL]. URL : https://arxiv.org/abs/2506.01062. — [arXiv:2506.01062](https://arxiv.org/abs/2506.01062) ↗
  46. Long Phan et al. Humanity’s Last Exam. 2025. arXiv: 2501.14249 [cs.LG]. URL : https://arxiv.org/abs/2501.14249. ↗
  47. David Rein et al. “Gpqa: A graduate-level google-proof q&a benchmark”. In: First Conference on Language Modeling. 2024.
  48. Jonathan Roberts et al. ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models. 2025. arXiv: 2502.09696 [cs.CV]. URL : https://arxiv.org/abs/2502.09696. — [arXiv:2502.09696](https://arxiv.org/abs/2502.09696) ↗
  49. Christoph Schuhmann et al. “Laion-5b: An open large-scale dataset for training next generation image-text models”. In: Advances in Neural Information Processing Systems 35 (2022), pp. 25278–25294.
  50. John Schulman et al. “Proximal Policy Optimization Algorithms”. In: arXiv preprint arXiv:1707.06347 (2017). URL : https://arxiv.org/abs/1707.06347. ↗
  51. Tianhui Song et al. Towards Pixel-Level VLM Perception via Simple Points Prediction. 2026. arXiv: 2601. 19228 [cs.CV]. URL : https://arxiv.org/abs/2601.19228. — [arXiv:2601.19228](https://arxiv.org/abs/2601.19228) ↗
  52. Giulio Starace et al. “PaperBench: Evaluating AI’s Ability to Replicate AI Research”. In: arXiv preprint arXiv:2504.01848 (2025). find
  53. Kimi Team et al. “Kimi k2: Open agentic intelligence”. In: arXiv preprint arXiv:2507.20534 (2025).
  54. Kimi Team et al. “Kimi-vl technical report”. In: arXiv preprint arXiv:2504.07491 (2025).
  55. Meituan LongCat Team et al. “Longcat-flash-omni technical report”. In: arXiv preprint arXiv:2511.00279 (2025). — [arXiv:2511.00279](https://arxiv.org/abs/2511.00279) find
  56. Minyang Tian et al. “Scicode: A research coding benchmark curated by scientists”. In: Advances in Neural Information Processing Systems 37 (2024), pp. 30624–30650. find
  57. Shengbang Tong et al. Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs. 2024. arXiv: 2401.06209 [cs.CV]. URL : https://arxiv.org/abs/2401.06209. ↗
  58. Harvard-MIT Mathematics Tournament. Harvard-MIT Mathematics Tournament, February 2025. Held on February 15, 2025. 2025. URL : https://www.hmmt.org/www/archive/282. ↗
  59. Ashish Vaswani et al. “Attention is All you Need”. In: Advances in Neural Information Processing Systems. Ed. by I. Guyon et al. Vol. 30. Curran Associates, Inc., 2017. URL : https://proceedings.neurips.cc/paper_files/paper/2017/file/3f5ee243547dee91fbd053c1c4a845aa-Paper.pdf. ↗
  60. Nikhita Vedula et al. DeepSearchQA: Bridging the Comprehensiveness Gap for Deep Research Agents. 2025. URL : https://storage.googleapis . com / deepmind - media / DeepSearchQA / DeepSearchQA_benchmark_paper.pdf. ↗
  61. Ke Wang et al. Measuring Multimodal Mathematical Reasoning with MATH-Vision Dataset. 2024. arXiv: 2402.14804 [cs.CV]. URL : https://arxiv.org/abs/2402.14804. ↗
  62. Weihan Wang et al. LVBench: An Extreme Long Video Understanding Benchmark. 2025. arXiv: 2406.08035 [cs.CV]. URL : https://arxiv.org/abs/2406.08035. ↗
  63. Xinyuan Wang et al. OpenCUA: Open Foundations for Computer-Use Agents. 2025. arXiv: 2508 . 09123 [cs.AI]. URL : https://arxiv.org/abs/2508.09123. — [arXiv:2508.09123](https://arxiv.org/abs/2508.09123) ↗
  64. Yubo Wang et al. MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark. 2024. arXiv: 2406.01574 [cs.CL]. URL : https://arxiv.org/abs/2406.01574. ↗
  65. Zhexu Wang et al. “OJBench: A Competition Level Code Benchmark For Large Language Models”. In: arXiv preprint arXiv:2506.16395 (2025). — [arXiv:2506.16395](https://arxiv.org/abs/2506.16395) find
  66. Zhun Wang et al. “CyberGym: Evaluating AI Agents’ Cybersecurity Capabilities with Real-World Vulnerabilities at Scale”. In: arXiv preprint arXiv:2506.02548 (2025). — [arXiv:2506.02548](https://arxiv.org/abs/2506.02548) find
  67. Zirui Wang et al. CharXiv: Charting Gaps in Realistic Chart Understanding in Multimodal LLMs. 2024. arXiv: 2406.18521 [cs.CL]. URL : https://arxiv.org/abs/2406.18521. ↗
  68. Jason Wei et al. BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agents. 2025. arXiv: 2504. 12516 [cs.CL]. URL : https://arxiv.org/abs/2504.12516. ↗
  69. Ryan Wong et al. WideSearch: Benchmarking Agentic Broad Info-Seeking. 2025. arXiv: 2508 . 07999 [cs.CL]. URL : https://arxiv.org/abs/2508.07999. ↗
  70. Haoning Wu et al. LongVideoBench: A Benchmark for Long-context Interleaved Video-Language Understanding. 2024. arXiv: 2407.15754 [cs.CV]. URL : https://arxiv.org/abs/2407.15754. ↗
  71. Xixi Wu et al. ReSum: Unlocking Long-Horizon Search Intelligence via Context Summarization. 2025. arXiv: 2509.13313 [cs.CL]. URL : https://arxiv.org/abs/2509.13313. ↗
  72. Tianbao Xie et al. “Introducing OSWorld-Verified”. In: xlang.ai (July 2025). URL : https://xlang.ai/blog/osworld-verified. ↗
  73. Tianbao Xie et al. OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments. 2024. arXiv: 2404.07972 [cs.AI].
  74. Feng Yao et al. Your Efficient RL Framework Secretly Brings You Off-Policy RL Training. Aug. 2025. URL : https://fengyao.notion.site/off-policy-rl. ↗
  75. Xiang Yue et al. MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark. 2025. arXiv: 2409.02813 [cs.CL]. URL : https://arxiv.org/abs/2409.02813. ↗
  76. Xiang Yue et al. “MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI”. In: Proceedings of CVPR. 2024.
  77. Xiaohua Zhai et al. Sigmoid Loss for Language Image Pre-Training. 2023. arXiv: 2303.15343 [cs.CV]. URL : https://arxiv.org/abs/2303.15343. ↗
  78. Xin Zhao et al. Small Leak Can Sink a Great Ship–Boost RL Training on MoE with IcePop! Sept. 2025. URL : https://ringtech.notion.site/icepop. ↗
  79. Yilun Zhao et al. MMVU: Measuring Expert-Level Multi-Discipline Video Understanding. 2025. arXiv: 2501. 12380 [cs.CV]. URL : https://arxiv.org/abs/2501.12380. — [arXiv:2501.12380](https://arxiv.org/abs/2501.12380) ↗
  80. Shuyan Zhou et al. “WebArena: A Realistic Web Environment for Building Autonomous Agents”. In: arXiv preprint arXiv:2307.13854 (2023). URL : https://webarena.dev. ↗
  81. Wanrong Zhu et al. “Multimodal c4: An open, billion-scale corpus of images interleaved with text”. In: Advances in Neural Information Processing Systems 36 (2024). find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/kimi-team-2026-kimi-k2-5-visual/