---
title: "Qwen3.8-Omni: Towards Native Omni-Modal Agents (2026)"
description: "Earlier omni models were built mainly for perception and conversation. 77 references. Among them: 0."
authors: ["Qwen Team"]
year: 2026
venue: "arXiv:2609.25611"
source: "https://arxiv.org/abs/2609.25611"
doi: "10.48550/arxiv.2609.25611"
arxiv: "2609.25611"
licence: "CC BY 4.0 (arXiv)"
licence_url: "http://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/qwen-team-2026-qwen3-8-omni-native/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/qwen-team-2026-qwen3-8-omni-native/)

[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/46/) / Qwen3.8-Omni: Towards Native Omni-Modal Agents

# Qwen3.8-Omni: Towards Native Omni-Modal Agents

**Authors:** [Qwen Team](https://md.research.elamur.ai/free/en/authors/qwen-team/) · **Year:** 2026 · **Venue:** arXiv:2609.25611 · **Licence:** [CC BY 4.0 (arXiv)](http://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://arxiv.org/abs/2609.25611) · [PDF](https://arxiv.org/pdf/2609.25611) · [DOI 10.48550/arxiv.2609.25611](https://doi.org/10.48550/arxiv.2609.25611) · [arXiv 2609.25611](https://arxiv.org/abs/2609.25611) · [OpenAlex](https://openalex.org/W7214110418)

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

## Summary
Earlier omni models were built mainly for perception and conversation. They handled long, video-centric productivity work poorly, such as editing clips, making music videos, or translating long recordings. The Qwen Team addresses this with Qwen3.8-Omni-Flash, a native omni-modal agent built on the Thinker-Talker design. Its Thinker is a hybrid sparse MoE backbone from Qwen3.8-Next that combines Gated DeltaNet with Qwen Sparse Attention. Three encoders feed it: a vision encoder, AuT, and a new Spatial AuT for directional audio. The model is co-trained on text, image, audio and video data from the start. Post-training adds long-horizon reasoning, interactive sandboxes and multi-teacher distillation, and the context window is extended to 1M tokens. Two open-source frameworks accompany the model. Qwen-MM-Plugins gives existing agent harnesses access to audiovisual content through captions, notes and lazy loading. Qwen-Live-Harness supports real-time agents. The model reportedly keeps text skills on par with similarly sized text-only models and clearly beats its predecessor on omni-modal tasks. This makes it a candidate base for production multimodal agents.

## Key points
- Compared with Qwen3.5-Omni-Plus, the average score across 29 audio, audiovisual reasoning and agent benchmarks rises by more than 25%. Estimated API input cost per hour drops by over 98% for audio and over 93% for audiovisual input.
- Pretraining uses a native 256K-token context, which is extended to 1M tokens after post-training.
- AuT produces about 6.25 tokens per second, roughly one every 160 ms. It was pretrained on over 20 languages, with Chinese, English and all others in a 3.5:3.5:3 ratio. Spatial AuT reads first-order ambisonics (FOA) audio through its complex STFT, keeping both phase and amplitude cues.
- Qwen-MM-Plugins bundles several modules:
  - Omni-Caption and Omni-Video2Note turn video into captions and structured notes.
  - Omni-Memory loads audiovisual content only when needed.
  - Omni-Skill-Creator converts tutorials into executable skills.
  - Omni-Chatcut supports long-form translation, narration and music videos.
- Qwen3.8-Omni-Flash-Realtime speech results:
  - 93.3% on PhonePronunciation
  - 95.0% style-control success (Gemini 3.1 TTS Flash: 97.5%)
  - 72.7% ABX naturalness win rate

*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 (5): [🖥️ 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 · [👁️ Computer Vision and Pattern Recognition](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · 3,486 works

## Cite

Cite as: Qwen Team. 2026. Qwen3.8-Omni: Towards Native Omni-Modal Agents. arXiv:2609.25611.

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

```bibtex
@misc{team2026qwen3,
  title = {{Qwen3.8-Omni: Towards Native Omni-Modal Agents}},
  author = {Qwen Team},
  year = {2026},
  doi = {10.48550/arxiv.2609.25611},
  eprint = {2609.25611},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2609.25611}
}
```

- [← previous Qwen-AgentWorld: Language World Models for General Agents](https://md.research.elamur.ai/free/en/papers/zuo-2026-qwen-agentworld-language-world/)
- [next → R ESEARCH QA: Evaluating Scholarly Question Answering at Scale Across 75 Fields with Survey-Mined Questions and Rubrics](https://md.research.elamur.ai/free/en/papers/yifei-2026-r-esearch-qa-evaluating-scholarly/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/46/)

## References

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

1. Alibaba Token Hub, Alibaba Group. Omnilingua-Bench: Multilingual omni-modal evaluation of long audio recognition, multi-speaker understanding, and instruction following. [https://github.com/Qwe](https://github.com/Qwe) nLM/Omnilingua-Bench, 2026. [↗](https://github.com/Qwe)
2. Anthropic. Claude 3.7 sonnet and claude code. [https://www.anthropic.com/news/claude-3-7-sonnet](https://www.anthropic.com/news/claude-3-7-sonnet), 2025. Accessed: 2026-09-03. [↗](https://www.anthropic.com/news/claude-3-7-sonnet)
3. Zongheng Cao, Yi Zheng, Rui Song, and Xinyu Hu. Agenticvbench: Can ai agents complete real-world post-production tasks? arXiv preprint arXiv:2605.27705, 2026. — [arXiv:2605.27705](https://arxiv.org/abs/2605.27705) [find](https://scholar.google.com/scholar?q=Zongheng+Cao%2C+Yi+Zheng%2C+Rui+Song%2C+and+Xinyu+Hu%2E+Agenticvbench%3A+Can+ai+agents+complete+real%2Dworld+post%2Dproduction+tasks%3F+arXiv+preprint+arXiv%3A2605%2E27705%2C+2026%2E+%E2%80%94+%5BarXiv%3A2605%2E27705%5D%28https%3A%2F%2Farxiv%2Eorg%2Fab)
4. Jianghan Chao, Jianzhang Gao, Wenhui Tan, Yuchong Sun, Ruihua Song, and Liyun Ru. Jointavbench: A benchmark for joint audio-visual reasoning evaluation. CoRR, abs/2512.12772, 2025. doi: 10.48550/A RXIV.2512.12772. — [doi:10.48550/a](https://doi.org/10.48550/a) [find](https://scholar.google.com/scholar?q=Jianghan+Chao%2C+Jianzhang+Gao%2C+Wenhui+Tan%2C+Yuchong+Sun%2C+Ruihua+Song%2C+and+Liyun+Ru%2E+Jointavbench%3A+A+benchmark+for+joint+audio%2Dvisual+reasoning+evaluation%2E+CoRR%2C+abs%2F2512%2E12772%2C+2025%2E+doi%3A+10%2E48550%2FA+RXI)
5. Qi Chen, Yunfei Chu, Haolin He, Yifan Yang, Zihan Liu, Yuxuan Wang, Ziyang Ma, Ruiyang Xu, Meng Gao, Yinsong Yan, Ling Wang, Hui Wang, Wen Huang, Yiheng Chen, Guanrou Yang, Qiuqiang Kong, Jin Xu, and Xie Chen. Omni demand understanding: A benchmark for contextual user-intent inference in multimodal… — [arXiv:2609.21392](https://arxiv.org/abs/2609.21392) [find](https://scholar.google.com/scholar?q=Qi+Chen%2C+Yunfei+Chu%2C+Haolin+He%2C+Yifan+Yang%2C+Zihan+Liu%2C+Yuxuan+Wang%2C+Ziyang+Ma%2C+Ruiyang+Xu%2C+Meng+Gao%2C+Yinsong+Yan%2C+Ling+Wang%2C+Hui+Wang%2C+Wen+Huang%2C+Yiheng+Chen%2C+Guanrou+Yang%2C+Qiuqiang+Kong%2C+Jin+Xu%2C+and+)
6. Yiming Chen, Xianghu Yue, Chen Zhang, Xiaoxue Gao, Robby T Tan, and Haizhou Li. [Voicebench: Benchmarking llm-based voice assistants](https://md.research.elamur.ai/free/en/papers/chen-2026-voicebench-benchmarking-llm-based-voice/). arXiv preprint arXiv:2410.17196, 2024.
7. Zhekai Chen, Chengqi Duan, Kaiyue Sun, Bohao Li, Yuqing Wang, Manyuan Zhang, and Xihui Liu. Uniclawbench: A universal benchmark for proactive agents on real-world tasks. arXiv preprint arXiv:2607.08768, 2026b. — [arXiv:2607.08768](https://arxiv.org/abs/2607.08768) [find](https://scholar.google.com/scholar?q=Zhekai+Chen%2C+Chengqi+Duan%2C+Kaiyue+Sun%2C+Bohao+Li%2C+Yuqing+Wang%2C+Manyuan+Zhang%2C+and+Xihui+Liu%2E+Uniclawbench%3A+A+universal+benchmark+for+proactive+agents+on+real%2Dworld+tasks%2E+arXiv+preprint+arXiv%3A2607%2E0876)
8. Xize Cheng, Wenxu Jia, Chenyuhao Wen, Dongjie Fu, Zehan Wang, Xinyu Zhang, and Tao Jin. Vox-infinity: Benchmarking the limits of long- context spoken language models, September 2026. URL https://doi.org/10.5281/zenodo.22868361. — [doi:10.5281/zenodo.22868361](https://doi.org/10.5281/zenodo.22868361) [↗](https://doi.org/10.5281/zenodo.22868361)
9. Alexis Conneau, Min Ma, Simran Khanuja, Yu Zhang, Vera Axelrod, Siddharth Dalmia, Jason Riesa, Clara Rivera, and Ankur Bapna. [Fleurs: Few-shot learning evaluation of universal representations of speech](https://md.research.elamur.ai/free/en/papers/conneau-2022-fleurs-few-shot-learning-evaluation/). 2022 IEEE Spoken Language Technology Workshop (SLT), pp. 798–805, 2022. URL [https://api.semantic…](https://api.semantic…) [↗](https://api.semantic…)
10. Datacurve. DeepSWE, 2026. URL [https://deepswe.datacurve.ai/](https://deepswe.datacurve.ai/). Benchmark version 1.1. Accessed: 2026-09-18. [↗](https://deepswe.datacurve.ai/)
11. DeepSeek-AI. [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, 2025.
12. Xiang Deng, Jeff Da, Edwin Pan, Yannis Yiming He, Charles Ide, Kanak Garg, Niklas Lauffer, Andrew Park, Nitin Pasari, Chetan Rane, et al. Swe-bench pro: Can ai agents solve long-horizon software engineering tasks? arXiv preprint arXiv:2509.16941, 2025. — [arXiv:2509.16941](https://arxiv.org/abs/2509.16941) [find](https://scholar.google.com/scholar?q=Xiang+Deng%2C+Jeff+Da%2C+Edwin+Pan%2C+Yannis+Yiming+He%2C+Charles+Ide%2C+Kanak+Garg%2C+Niklas+Lauffer%2C+Andrew+Park%2C+Nitin+Pasari%2C+Chetan+Rane%2C+et+al%2E+Swe%2Dbench+pro%3A+Can+ai+agents+solve+long%2Dhorizon+software+engin)
13. Jingzhe Ding, Shengda Long, Changxin Pu, Huan Zhou, Hongwan Gao, Xiang Gao, Chao He, Yue Hou, Fei Hu, Zhaojian Li, et al. Nl2repo-bench: Towards long-horizon repository generation evaluation of coding agents. arXiv preprint arXiv:2512.12730, 2025. — [arXiv:2512.12730](https://arxiv.org/abs/2512.12730) [find](https://scholar.google.com/scholar?q=Jingzhe+Ding%2C+Shengda+Long%2C+Changxin+Pu%2C+Huan+Zhou%2C+Hongwan+Gao%2C+Xiang+Gao%2C+Chao+He%2C+Yue+Hou%2C+Fei+Hu%2C+Zhaojian+Li%2C+et+al%2E+Nl2repo%2Dbench%3A+Towards+long%2Dhorizon+repository+generation+evaluation+of+coding)
14. Shuangrui Ding, Xuanlang Dai, Long Xing, Shengyuan Ding, Ziyu Liu, Yang JingYi, Penghui Yang, Zhixiong Zhang, Xilin Wei, Xinyu Fang, et al. Wildclawbench: A benchmark for real-world, long-horizon agent evaluation. arXiv preprint arXiv:2605.10912, 2026. — [arXiv:2605.10912](https://arxiv.org/abs/2605.10912) [find](https://scholar.google.com/scholar?q=Shuangrui+Ding%2C+Xuanlang+Dai%2C+Long+Xing%2C+Shengyuan+Ding%2C+Ziyu+Liu%2C+Yang+JingYi%2C+Penghui+Yang%2C+Zhixiong+Zhang%2C+Xilin+Wei%2C+Xinyu+Fang%2C+et+al%2E+Wildclawbench%3A+A+benchmark+for+real%2Dworld%2C+long%2Dhorizon+agen)
15. Chaoyou Fu, Haozhi Yuan, Yuhao Dong, Yifan Zhang, Yunhang Shen, Xiaoxing Hu, Xueying Li, Jinsen Su, Chengwu Long, Xiaoyao Xie, Yongkang Xie, Xiawu Zheng, Xue Yang, Haoyu Cao, Yunsheng Wu, Ziwei Liu, Xing Sun, Caifeng Shan, and Ran He. Video-mme-v2: Towards the next stage in benchmarks for comprehens… — [doi:10.48550/arxiv.2604.05015](https://doi.org/10.48550/arxiv.2604.05015) [find](https://scholar.google.com/scholar?q=Chaoyou+Fu%2C+Haozhi+Yuan%2C+Yuhao+Dong%2C+Yifan+Zhang%2C+Yunhang+Shen%2C+Xiaoxing+Hu%2C+Xueying+Li%2C+Jinsen+Su%2C+Chengwu+Long%2C+Xiaoyao+Xie%2C+Yongkang+Xie%2C+Xiawu+Zheng%2C+Xue+Yang%2C+Haoyu+Cao%2C+Yunsheng+Wu%2C+Ziwei+Liu%2C+X)
16. Yihui Fu, Luyao Cheng, Shubo Lv, Yukai Jv, Yuxiang Kong, Zhuo Chen, Yanxin Hu, Lei Xie, Jian Wu, Hui Bu, Xin Xu, Jun Du, and Jingdong Chen. Aishell-4: An open source dataset for speech enhancement, separation, recognition and speaker diarization in conference scenario. In Interspeech, 2021. URL http… [find](https://scholar.google.com/scholar?q=Yihui+Fu%2C+Luyao+Cheng%2C+Shubo+Lv%2C+Yukai+Jv%2C+Yuxiang+Kong%2C+Zhuo+Chen%2C+Yanxin+Hu%2C+Lei+Xie%2C+Jian+Wu%2C+Hui+Bu%2C+Xin+Xu%2C+Jun+Du%2C+and+Jingdong+Chen%2E+Aishell%2D4%3A+An+open+source+dataset+for+speech+enhancement%2C+se)
17. Arushi Goel, Sreyan Ghosh, Vatsal Agarwal, Nishit Anand, Kaousheik Jayakumar, Lasha Koroshinadze, Yao Xu, Katie Lyons, James Case, Karan Sapra, Kevin J. Shih, Siddharth Gururani, Abhinav Shrivastava, Ramani Duraiswami, Dinesh Manocha, Andrew Tao, Bryan Catanzaro, Mohammad Shoeybi, and Wei Ping. MMOU… [find](https://scholar.google.com/scholar?q=Arushi+Goel%2C+Sreyan+Ghosh%2C+Vatsal+Agarwal%2C+Nishit+Anand%2C+Kaousheik+Jayakumar%2C+Lasha+Koroshinadze%2C+Yao+Xu%2C+Katie+Lyons%2C+James+Case%2C+Karan+Sapra%2C+Kevin+J%2E+Shih%2C+Siddharth+Gururani%2C+Abhinav+Shrivastava%2C+)
18. Google. Gemini 3.8 Flash, 2026. URL [https://ai.google.dev/gemini-api/docs/models/gemini-3.8-f](https://ai.google.dev/gemini-api/docs/models/gemini-3.8-f) lash. Gemini API documentation. Accessed: 2026-09-18. [↗](https://ai.google.dev/gemini-api/docs/models/gemini-3.8-f)
19. Advait Gosai, Tyler Vuong, Utkarsh Tyagi, Steven Li, Wenjia You, Miheer Bavare, Arda Uçar, Zhongwang Fang, Brian Jang, Bing Liu, and Yunzhong He. Audio multichallenge: A multi-turn evaluation of spoken dialogue systems on natural human interaction. In Maria Liakata, Viviane P. Moreira, Jiajun Zhang,… [find](https://scholar.google.com/scholar?q=Advait+Gosai%2C+Tyler+Vuong%2C+Utkarsh+Tyagi%2C+Steven+Li%2C+Wenjia+You%2C+Miheer+Bavare%2C+Arda+U%C3%A7ar%2C+Zhongwang+Fang%2C+Brian+Jang%2C+Bing+Liu%2C+and+Yunzhong+He%2E+Audio+multichallenge%3A+A+multi%2Dturn+evaluation+of+spoke)
20. Minghao Han, Zhenghao Xing, Xize Cheng, Yuxuan Wang, Junming Lin, Ling Wang, Yinsong Yan, Yunfei Chu, Qize Yang, and Jin Xu. Omni2web: Benchmarking audiovisual website development, September 2026. URL https://doi.org/10.5281/zenodo.22855767. — [doi:10.5281/zenodo.22855767](https://doi.org/10.5281/zenodo.22855767) [↗](https://doi.org/10.5281/zenodo.22855767)
21. Haolin He, Yunfei Chu, Qi Chen, Wen Huang, Yuan Feng, Muzhi Zhu, Zheqi Dai, Haoning Xu, Dongchao Yang, Chunyat Wu, Zining Liang, Zhengxi Liu, Xiquan Li, Xie Chen, Xize Cheng, Qize Yang, Jin Xu, and Qiuqiang Kong. Omnivchat: Synthesizing, benchmarking, and training for native audio-visual dialogue, 2… — [arXiv:2609.21465](https://arxiv.org/abs/2609.21465) [find](https://scholar.google.com/scholar?q=Haolin+He%2C+Yunfei+Chu%2C+Qi+Chen%2C+Wen+Huang%2C+Yuan+Feng%2C+Muzhi+Zhu%2C+Zheqi+Dai%2C+Haoning+Xu%2C+Dongchao+Yang%2C+Chunyat+Wu%2C+Zining+Liang%2C+Zhengxi+Liu%2C+Xiquan+Li%2C+Xie+Chen%2C+Xize+Cheng%2C+Qize+Yang%2C+Jin+Xu%2C+and+Qi)
22. Zehai He, Wenyi Hong, Zhen Yang, Ziyang Pan, Mingdao Liu, Xiaotao Gu, and Jie Tang. Vision2web: A hierarchical benchmark for visual website development with agent verification. arXiv preprint arXiv:2603.26648, 2026b. — [arXiv:2603.26648](https://arxiv.org/abs/2603.26648) [find](https://scholar.google.com/scholar?q=Zehai+He%2C+Wenyi+Hong%2C+Zhen+Yang%2C+Ziyang+Pan%2C+Mingdao+Liu%2C+Xiaotao+Gu%2C+and+Jie+Tang%2E+Vision2web%3A+A+hierarchical+benchmark+for+visual+website+development+with+agent+verification%2E+arXiv+preprint+arXiv%3A26)
23. Jack Hong, Shilin Yan, Jiayin Cai, Xiaolong Jiang, Yao Hu, and Weidi Xie. Worldsense: Evaluating real-world omnimodal understanding for multimodal llms. CoRR, abs/2502.04326, 2025. — [arXiv:2502.04326](https://arxiv.org/abs/2502.04326) [find](https://scholar.google.com/scholar?q=Jack+Hong%2C+Shilin+Yan%2C+Jiayin+Cai%2C+Xiaolong+Jiang%2C+Yao+Hu%2C+and+Weidi+Xie%2E+Worldsense%3A+Evaluating+real%2Dworld+omnimodal+understanding+for+multimodal+llms%2E+CoRR%2C+abs%2F2502%2E04326%2C+2025%2E+%E2%80%94+%5BarXiv%3A2502%2E04326)
24. Wen Huang, Yunfei Chu, Meng Gao, Haolin He, and Jin Xu. Audiospan: Spanning the duration and depth of audio comprehension. CoRR, abs/2608.26431, 2026. doi: 10.48550/ARXIV.2608.26431. — [doi:10.48550/arxiv.2608.26431](https://doi.org/10.48550/arxiv.2608.26431) [find](https://scholar.google.com/scholar?q=Wen+Huang%2C+Yunfei+Chu%2C+Meng+Gao%2C+Haolin+He%2C+and+Jin+Xu%2E+Audiospan%3A+Spanning+the+duration+and+depth+of+audio+comprehension%2E+CoRR%2C+abs%2F2608%2E26431%2C+2026%2E+doi%3A+10%2E48550%2FARXIV%2E2608%2E26431%2E+%E2%80%94+%5Bdoi%3A10%2E48550%2Fa)
25. Naman Jain, King Han, Alex Gu, Wen-Ding Li, Fanjia Yan, Tianjun Zhang, Sida Wang, Armando Solar-Lezama, Koushik Sen, and Ion Stoica. [LiveCodeBench: Holistic and contamination free evaluation of large language models for code](https://md.research.elamur.ai/free/en/papers/jain-2024-livecodebench-holistic-contamination-free-evaluation/). CoRR, abs/2403.07974, 2024.
26. Kabir Khandpur, Kilian Lieret, Carlos E. Jimenez, Ofir Press, and John Yang. SWE-bench Multilingual, 2025. URL [https://www.swebench.com/multilingual.html](https://www.swebench.com/multilingual.html). Accessed: 2026-09-18. [↗](https://www.swebench.com/multilingual.html)
27. Daeyong Kwon, Qiyu Wu, Shinobu Kuriya, Junghyun Koo, Shuyang Cui, Zhi Zhong, Wei-Hsiang Liao, Hiromi Wakaki, and Yuki Mitsufuji. Mustbench: Benchmarking and advancing temporal grounding in music llms. CoRR, abs/2605.29300, 2026. doi: 10.48550/ARXIV.2605.29300. — [doi:10.48550/arxiv.2605.29300](https://doi.org/10.48550/arxiv.2605.29300) [find](https://scholar.google.com/scholar?q=Daeyong+Kwon%2C+Qiyu+Wu%2C+Shinobu+Kuriya%2C+Junghyun+Koo%2C+Shuyang+Cui%2C+Zhi+Zhong%2C+Wei%2DHsiang+Liao%2C+Hiromi+Wakaki%2C+and+Yuki+Mitsufuji%2E+Mustbench%3A+Benchmarking+and+advancing+temporal+grounding+in+music+llms%2E)
28. Caorui Li, Yu Chen, Yiyan Ji, Jin Xu, Zhenyu Cui, Shihao Li, Yuanxing Zhang, Jiafu Tang, Zhenghao Song, Dingling Zhang, Ying He, Haoxiang Liu, Yuxuan Wang, Qiufeng Wang, Zhenhe Wu, Jiehui Luo, Zhiyu Pan, Weihao Xie, Chenchen Zhang, Zhaohui Wang, Jiayi Tian, Yanghai Wang, Zhe Cao, Minxin Dai, Ke Wang… — [doi:10.48550/a](https://doi.org/10.48550/a) [find](https://scholar.google.com/scholar?q=Caorui+Li%2C+Yu+Chen%2C+Yiyan+Ji%2C+Jin+Xu%2C+Zhenyu+Cui%2C+Shihao+Li%2C+Yuanxing+Zhang%2C+Jiafu+Tang%2C+Zhenghao+Song%2C+Dingling+Zhang%2C+Ying+He%2C+Haoxiang+Liu%2C+Yuxuan+Wang%2C+Qiufeng+Wang%2C+Zhenhe+Wu%2C+Jiehui+Luo%2C+Zhiyu+P)
29. Xiaoxi Li, Wenxiang Jiao, Jiarui Jin, Shijian Wang, Guanting Dong, Jiajie Jin, Hao Wang, Yinuo Wang, Ji-Rong Wen, Yuan Lu, et al. Omnigaia: Towards native omni-modal ai agents. arXiv preprint arXiv:2602.22897, 2026. — [arXiv:2602.22897](https://arxiv.org/abs/2602.22897) [find](https://scholar.google.com/scholar?q=Xiaoxi+Li%2C+Wenxiang+Jiao%2C+Jiarui+Jin%2C+Shijian+Wang%2C+Guanting+Dong%2C+Jiajie+Jin%2C+Hao+Wang%2C+Yinuo+Wang%2C+Ji%2DRong+Wen%2C+Yuan+Lu%2C+et+al%2E+Omnigaia%3A+Towards+native+omni%2Dmodal+ai+agents%2E+arXiv+preprint+arXiv%3A26)
30. Junming Lin, Zheng Fang, Chi Chen, Zihao Wan, Fuwen Luo, Peng Li, Yang Liu, and Maosong Sun. Streamingbench: Assessing the gap for mllms to achieve streaming video understanding. CoRR, abs/2411.03628, 2024. doi: 10.48550/ARXIV.2411.03628. URL https://doi.org/10.48550/arXiv.2411. 03628. — [doi:10.48550/arxiv.2411.03628](https://doi.org/10.48550/arxiv.2411.03628) [↗](https://doi.org/10.48550/arXiv.2411)
31. Ruixun Liu, Yuxuan Wang, Jiacheng Xie, Yuhuan You, Donghua Cai, Junming Lin, Xiong-Hui Chen, Zhifang Guo, Yunfei Chu, Qize Yang, Xize Cheng, Jin Xv, and Yiwu Zhong. Omniecho: Spatial audio understanding for embodied agents, September 2026. URL https://doi.org/10.5281/zenodo.22855 748. — [doi:10.5281/zenodo.22855](https://doi.org/10.5281/zenodo.22855) [↗](https://doi.org/10.5281/zenodo.22855)
32. Wenhan Ma, Jianyu Wei, Liang Zhao, Hailin Zhang, Bangjun Xiao, Lei Li, Qibin Yang, Bofei Gao, Yudong Wang, Rang Li, Jin-Hao Dong, Zhifang Sui, and Fuli Luo. Mopd: Multi-teacher on-policy distillation for capability integration in llm post-training. ArXiv, abs/2606.30406, 2026. URL [https://api.seman…](https://api.seman…) — [arXiv:2606.30406](https://arxiv.org/abs/2606.30406) [↗](https://api.seman…)
33. Ziyang Ma, Yinghao Ma, Yanqiao Zhu, Chen Yang, Yi-Wen Chao, Ruiyang Xu, Wenxi Chen, Yuanzhe Chen, Zhuo Chen, Jian Cong, Kai Li, Keliang Li, Siyou Li, Xinfeng Li, Xiquan Li, Zheng Lian, Yuzhe Liang, Minghao Liu, Zhikang Niu, Tianrui Wang, Yuping Wang, Yuxuan Wang, Yihao Wu, Guanrou Yang, Jianwei Yu,… — [doi:10.48550/arxiv.2505.13032](https://doi.org/10.48550/arxiv.2505.13032) [find](https://scholar.google.com/scholar?q=Ziyang+Ma%2C+Yinghao+Ma%2C+Yanqiao+Zhu%2C+Chen+Yang%2C+Yi%2DWen+Chao%2C+Ruiyang+Xu%2C+Wenxi+Chen%2C+Yuanzhe+Chen%2C+Zhuo+Chen%2C+Jian+Cong%2C+Kai+Li%2C+Keliang+Li%2C+Siyou+Li%2C+Xinfeng+Li%2C+Xiquan+Li%2C+Zheng+Lian%2C+Yuzhe+Liang%2C+Mi)
34. Ziyang Ma, Ruiyang Xu, Zhenghao Xing, Yunfei Chu, Yuxuan Wang, Jinzheng He, Jin Xu, Pheng-Ann Heng, Kai Yu, Junyang Lin, et al. Omni-captioner: Data pipeline, models, and benchmark for omni detailed perception. arXiv preprint arXiv:2510.12720, 2025b. — [arXiv:2510.12720](https://arxiv.org/abs/2510.12720) [find](https://scholar.google.com/scholar?q=Ziyang+Ma%2C+Ruiyang+Xu%2C+Zhenghao+Xing%2C+Yunfei+Chu%2C+Yuxuan+Wang%2C+Jinzheng+He%2C+Jin+Xu%2C+Pheng%2DAnn+Heng%2C+Kai+Yu%2C+Junyang+Lin%2C+et+al%2E+Omni%2Dcaptioner%3A+Data+pipeline%2C+models%2C+and+benchmark+for+omni+detailed+p)
35. Meta. Introducing Muse Code and Muse Spark 1.2, August 2026. URL [https://research.meta.ai/blo](https://research.meta.ai/blo) g/introducing-muse-code-and-muse-spark-1-2. Published August 5, 2026. Accessed: 2026-09-18. [↗](https://research.meta.ai/blo)
36. Bingshen Mu, Pengcheng Guo, Zhaokai Sun, Shuai Wang, Hexin Liu, Mingchen Shao, Lei Xie, Eng Siong Chng, Longshuai Xiao, Qiangze Feng, and Daliang Wang. Summary on the multilingual conversational speech language model challenge: Datasets, tasks, baselines, and methods. CoRR, abs/2509.13785, 2025. doi… — [doi:10.48550/arxiv.2509.13785](https://doi.org/10.48550/arxiv.2509.13785) [find](https://scholar.google.com/scholar?q=Bingshen+Mu%2C+Pengcheng+Guo%2C+Zhaokai+Sun%2C+Shuai+Wang%2C+Hexin+Liu%2C+Mingchen+Shao%2C+Lei+Xie%2C+Eng+Siong+Chng%2C+Longshuai+Xiao%2C+Qiangze+Feng%2C+and+Daliang+Wang%2E+Summary+on+the+multilingual+conversational+speec)
37. Le Thien Phuc Nguyen, Zhuoran Yu, Samuel Low Yu Hang, Subin An, Jeongik Lee, Yohan Ban, Se-ungEun Chung, Thanh-Huy Nguyen, JuWan Maeng, Soochahn Lee, et al. See, hear, and understand: Benchmarking audiovisual human speech understanding in multimodal large language models. arXiv preprint arXiv:2512.0… — [arXiv:2512.02231](https://arxiv.org/abs/2512.02231) [find](https://scholar.google.com/scholar?q=Le+Thien+Phuc+Nguyen%2C+Zhuoran+Yu%2C+Samuel+Low+Yu+Hang%2C+Subin+An%2C+Jeongik+Lee%2C+Yohan+Ban%2C+Se%2DungEun+Chung%2C+Thanh%2DHuy+Nguyen%2C+JuWan+Maeng%2C+Soochahn+Lee%2C+et+al%2E+See%2C+hear%2C+and+understand%3A+Benchmarking+aud)
38. OpenAI. ChatML, 2022. URL [https://github.com/openai/openai-python/blob/e389823ba013a24b4c3](https://github.com/openai/openai-python/blob/e389823ba013a24b4c3) 2ce38fa0bd87e6bccae94/chatml.md. [↗](https://github.com/openai/openai-python/blob/e389823ba013a24b4c3)
39. OpenAI. Introducing openai o1-preview. [https://openai.com/index/introducing-openai-o1-preview/](https://openai.com/index/introducing-openai-o1-preview/), 2024. Accessed: 2026-09-03. [↗](https://openai.com/index/introducing-openai-o1-preview/)
40. Long Phan, Alice Gatti, Ziwen Han, Nathaniel Li, Josephina Hu, Hugh Zhang, Chen Bo Calvin Zhang, Mohamed Shaaban, John Ling, Sean Shi, et al. Humanity’s last exam. arXiv preprint arXiv:2501.[14249, 2025](https://md.research.elamur.ai/free/en/papers/phan-2025-humanity-s-last-exam/).
41. Reza Pourreza, Rishit Dagli, Apratim Bhattacharyya, Sunny Panchal, Guillaume Berger, and Roland Memisevic. Can vision-language models answer face to face questions in the real-world? arXiv preprint arXiv:2503.19356, 2025. — [arXiv:2503.19356](https://arxiv.org/abs/2503.19356) [find](https://scholar.google.com/scholar?q=Reza+Pourreza%2C+Rishit+Dagli%2C+Apratim+Bhattacharyya%2C+Sunny+Panchal%2C+Guillaume+Berger%2C+and+Roland+Memisevic%2E+Can+vision%2Dlanguage+models+answer+face+to+face+questions+in+the+real%2Dworld%3F+arXiv+preprint+ar)
42. Valentina Pyatkin, Saumya Malik, Victoria Graf, Hamish Ivison, Shengyi Huang, Pradeep Dasigi, Nathan Lambert, and Hannaneh Hajishirzi. [Generalizing verifiable instruction following](https://md.research.elamur.ai/free/en/papers/pyatkin-2025-generalizing-verifiable-instruction-following/). CoRR, abs/2507.02833, 2025. doi: 10.48550/ARXIV.2507.02833. URL https://doi.org/10.48550/arXiv.2507. 02833. [↗](https://doi.org/10.48550/arXiv.2507)
43. Zihan Qiu, Zekun Wang, Xiao Li, Yanpeng Li, Yang Xu, Yixuan Wang, Huaqing Zhang, Rui Men, Bochao Mao, Chengruidong Zhang, et al. On the design of qwen3. 8-next architecture: Evaluation, efficiency, and training stability. arXiv preprint arXiv:2608.30320, 2026. — [arXiv:2608.30320](https://arxiv.org/abs/2608.30320) [find](https://scholar.google.com/scholar?q=Zihan+Qiu%2C+Zekun+Wang%2C+Xiao+Li%2C+Yanpeng+Li%2C+Yang+Xu%2C+Yixuan+Wang%2C+Huaqing+Zhang%2C+Rui+Men%2C+Bochao+Mao%2C+Chengruidong+Zhang%2C+et+al%2E+On+the+design+of+qwen3%2E+8%2Dnext+architecture%3A+Evaluation%2C+efficiency%2C+an)
44. Qwen Team. On the design of Qwen3.8-Next architecture: Evaluation, efficiency, and training stability. Technical report, Alibaba Group, August 2026a. [find](https://scholar.google.com/scholar?q=Qwen+Team%2E+On+the+design+of+Qwen3%2E8%2DNext+architecture%3A+Evaluation%2C+efficiency%2C+and+training+stability%2E+Technical+report%2C+Alibaba+Group%2C+August+2026a%2E)
45. Qwen Team. Qwen3.7-plus: Multimodal agent intelligence, June 2026b. URL [https://qwen.ai/blog?id=](https://qwen.ai/blog?id=) qwen3.7-plus. [↗](https://qwen.ai/blog?id=)
46. Qwen Team. Qwen3.5-omni: Technical report. arXiv preprint arXiv:2604.[15804, 2026c](https://md.research.elamur.ai/free/en/papers/qwen-team-2026-qwen3-5-omni-technical/). URL https://arxiv.org/abs/2604.15804. [↗](https://arxiv.org/abs/2604.15804)
47. Qwen Team. Qwen3.8-max: A new bar for coding and cowork, August 2026d. URL [https://qwen.ai/bl](https://qwen.ai/bl) og?id=qwen3.8. [↗](https://qwen.ai/bl)
48. Chris Rawles, Sarah Clinckemaillie, Yifan Chang, Jonathan Waltz, Gabrielle Lau, Marybeth Fair, Alice Li, William Bishop, Wei Li, Folawiyo Campbell-Ajala, et al. [Androidworld: A dynamic benchmarking environment for autonomous agents](https://md.research.elamur.ai/free/en/papers/rawles-2024-androidworld-dynamic-benchmarking-environment-autonomous/). In International Conference on Learning Representations, volume 202…
49. David Rein, Betty Li Hou, Asa Cooper Stickland, Jackson Petty, Richard Yuanzhe Pang, Julien Dirani, Julian Michael, and Samuel R. Bowman. [GPQA: A graduate-level Google-proof Q&A benchmark](https://md.research.elamur.ai/free/en/papers/rein-2023-gpqa-graduate-level-google-proof/). CoRR, abs/2311.12022, 2023.
50. S Sakshi, Utkarsh Tyagi, Sonal Kumar, Ashish Seth, Ramaneswaran Selvakumar, Oriol Nieto, Ramani Duraiswami, Sreyan Ghosh, and Dinesh Manocha. [Mmau: A massive multi-task audio understanding and reasoning benchmark](https://md.research.elamur.ai/free/en/papers/sakshi-2024-mmau-massive-multi-task-audio/), 2024. URL https://arxiv.org/abs/2410.19168. [↗](https://arxiv.org/abs/2410.19168)
51. Bytedance Seed. Seed2. 0 model card: Towards intelligence frontier for real-world complexity. arXiv preprint arXiv:2607.00248, 2026. — [arXiv:2607.00248](https://arxiv.org/abs/2607.00248) [find](https://scholar.google.com/scholar?q=Bytedance+Seed%2E+Seed2%2E+0+model+card%3A+Towards+intelligence+frontier+for+real%2Dworld+complexity%2E+arXiv+preprint+arXiv%3A2607%2E00248%2C+2026%2E+%E2%80%94+%5BarXiv%3A2607%2E00248%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2607%2E00248%29)
52. Luoyi Sun, Xiao Zhou, Zeqian Li, Ya Zhang, Yanking Wang, and Weidi Xie. Spotsound: Enhancing large audio-language models with fine-grained temporal grounding. arXiv preprint arXiv:2604.13023, 2026. — [arXiv:2604.13023](https://arxiv.org/abs/2604.13023) [find](https://scholar.google.com/scholar?q=Luoyi+Sun%2C+Xiao+Zhou%2C+Zeqian+Li%2C+Ya+Zhang%2C+Yanking+Wang%2C+and+Weidi+Xie%2E+Spotsound%3A+Enhancing+large+audio%2Dlanguage+models+with+fine%2Dgrained+temporal+grounding%2E+arXiv+preprint+arXiv%3A2604%2E13023%2C+2026%2E+%E2%80%94+)
53. Keda Tao, Yuhua Zheng, Xu Jia, Wenjie Du, Kele Shao, Hesong Wang, Xueyi Chen, Xin Jin, Junhan Zhu, Bohan Yu, Weiqiang Wang, Jian Liu, Can Qin, Yulun Zhang, Ming-Hsuan Yang, and Huan Wang. Lvomnibench: Pioneering long audio-video understanding evaluation for omnimodal llms. CoRR, abs/2603.19217, 2026… — [doi:10.48550/arxiv.2603.19217](https://doi.org/10.48550/arxiv.2603.19217) [find](https://scholar.google.com/scholar?q=Keda+Tao%2C+Yuhua+Zheng%2C+Xu+Jia%2C+Wenjie+Du%2C+Kele+Shao%2C+Hesong+Wang%2C+Xueyi+Chen%2C+Xin+Jin%2C+Junhan+Zhu%2C+Bohan+Yu%2C+Weiqiang+Wang%2C+Jian+Liu%2C+Can+Qin%2C+Yulun+Zhang%2C+Ming%2DHsuan+Yang%2C+and+Huan+Wang%2E+Lvomnibench%3A)
54. Gemini Robotics Team. Gemini robotics: Bringing AI into the physical world. CoRR, abs/2503.20020, 2025. [find](https://scholar.google.com/scholar?q=Gemini+Robotics+Team%2E+Gemini+robotics%3A+Bringing+AI+into+the+physical+world%2E+CoRR%2C+abs%2F2503%2E20020%2C+2025%2E)
55. Qwen Team. [Qwen3-asr technical report](https://md.research.elamur.ai/free/en/papers/shi-2026-qwen3-asr-technical-report/), 2026. URL https://arxiv.org/abs/2601.21337. [↗](https://arxiv.org/abs/2601.21337)
56. Dingdong Wang, Jincenzi Wu, Junan Li, Dongchao Yang, Xueyuan Chen, Tianhua Zhang, and Helen Meng. MMSU: A massive multi-task spoken language understanding and reasoning benchmark. CoRR, abs/2506.04779, 2025a. doi: 10.48550/ARXIV.2506.04779. URL https://doi.org/10.48550/arXiv.250 6.04779. — [doi:10.48550/arxiv.2506.04779](https://doi.org/10.48550/arxiv.2506.04779) [↗](https://doi.org/10.48550/arXiv.250)
57. Hui Wang, Yunfei Chu, Xize Cheng, Yu Xi, Meng Gao, Qi Chen, Yifan Yang, Wenxiang Guo, Yong Qin, and Jin Xu. Lamar-bench: Evaluating long-form and multi-audio understanding and reasoning, September 2026a. URL https://doi.org/10.5281/zenodo.22857938. — [doi:10.5281/zenodo.22857938](https://doi.org/10.5281/zenodo.22857938) [↗](https://doi.org/10.5281/zenodo.22857938)
58. Jiahao Wang, An Ping, Yanghai Wang, Yuanxing Zhang, Shihao Li, Hanyan Bian, Yichi Ren, Yize Zhang, Han Wang, Haowen Chen, Junze Li, Jiaqi Wang, Yiyang Hu, Zhuze Xu, Zijie Zhang, and Jiaheng Liu. Omnicap-if: Benchmarking and improving instruction following abilities for omni-video captioning. CoRR, a… — [doi:10.48550/arxiv.2606.08572](https://doi.org/10.48550/arxiv.2606.08572) [find](https://scholar.google.com/scholar?q=Jiahao+Wang%2C+An+Ping%2C+Yanghai+Wang%2C+Yuanxing+Zhang%2C+Shihao+Li%2C+Hanyan+Bian%2C+Yichi+Ren%2C+Yize+Zhang%2C+Han+Wang%2C+Haowen+Chen%2C+Junze+Li%2C+Jiaqi+Wang%2C+Yiyang+Hu%2C+Zhuze+Xu%2C+Zijie+Zhang%2C+and+Jiaheng+Liu%2E+Omnic)
59. Ke Wang, Junting Pan, Weikang Shi, Zimu Lu, Mingjie Zhan, and Hongsheng Li. [Measuring multimodal mathematical reasoning with math-vision dataset](https://md.research.elamur.ai/free/en/papers/wang-2024-measuring-multimodal-mathematical-reasoning-math/). arXiv:2402.14804, 2024a.
60. Weihan Wang, Zehai He, Wenyi Hong, Yean Cheng, Xiaohan Zhang, Ji Qi, Shiyu Huang, Bin Xu, Yuxiao Dong, Ming Ding, and Jie Tang. [Lvbench: An extreme long video understanding benchmark](https://md.research.elamur.ai/free/en/papers/wang-2024-lvbench-extreme-long-video-understanding/). CoRR, abs/2406.08035, 2024b.
61. Yueqian Wang, Xiaojun Meng, Yifan Wang, Huishuai Zhang, and Dongyan Zhao. Proactivevideoqa: A comprehensive benchmark evaluating proactive interactions in video large language models. CoRR, abs/2507.09313, 2025b. doi: 10.48550/ARXIV.2507.09313. URL https://doi.org/10.48550/arXiv.250 7.09313. — [doi:10.48550/arxiv.2507.09313](https://doi.org/10.48550/arxiv.2507.09313) [↗](https://doi.org/10.48550/arXiv.250)
62. Zirui Wang, Mengzhou Xia, Luxi He, Howard Chen, Yitao Liu, Richard Zhu, Kaiqu Liang, Xindi Wu, Haotian Liu, Sadhika Malladi, Alexis Chevalier, Sanjeev Arora, and Danqi Chen. [Charxiv: Charting gaps in realistic chart understanding in multimodal llms](https://md.research.elamur.ai/free/en/papers/wang-2024-charxiv-charting-gaps-realistic-chart/). arXiv preprint arXiv:2406.18521, 2024c.
63. Benno Weck, Pablo Puentes, Andrea Poltronieri, Satyajeet Prabhu, and Dmitry Bogdanov. [Hummusqa: A human-written music understanding QA benchmark dataset](https://md.research.elamur.ai/free/en/papers/weck-2026-hummusqa-human-written-music-understanding/). CoRR, abs/2603.27877, 2026. doi: 10.48550/ARXIV.2603.27877. xAI. Grok-1.5 Vision Preview, April 2024. URL [https://x.ai/news/grok-1.5v](https://x.ai/news/grok-1.5v). Introduces… [↗](https://x.ai/news/grok-1.5v)
64. Jin Xu, Zhifang Guo, Jinzheng He, Hangrui Hu, Ting He, Shuai Bai, Keqin Chen, Jialin Wang, Yang Fan, Kai Dang, et al. Qwen2. 5-omni technical report. arXiv preprint arXiv:2503.[20215, 2025a](https://md.research.elamur.ai/free/en/papers/xu-2025-qwen2-5-omni-technical/).
65. Jin Xu, Zhifang Guo, Hangrui Hu, Yunfei Chu, Xiong Wang, Jinzheng He, Yuxuan Wang, Xianzhong Shi, Ting He, Xinfa Zhu, Yuanjun Lv, Yongqi Wang, Dake Guo, He Wang, Linhan Ma, Pei Zhang, Xinyu Zhang, Hongkun Hao, Zishan Guo, Baosong Yang, Bin Zhang, Ziyang Ma, Xipin Wei, Shuai Bai, Ke Chen, Xue Lian Li… — [Qwen3-Omni Technical Report](https://md.research.elamur.ai/free/en/papers/xu-2025-qwen3-omni-technical-report/)
66. Yudong Yang, Jimin Zhuang, Guangzhi Sun, Changli Tang, Yixuan Li, Peihan Li, Yifan Jiang, Wei Li, Zejun Ma, and Chao Zhang. [Audio-centric video understanding benchmark without text shortcut](https://md.research.elamur.ai/free/en/papers/yang-2025-audio-centric-video-understanding-benchmark/). In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pp. 6580–6598, 202…
67. Zehui Yang, Yifan Chen, Lei Luo, Runyan Yang, Lingxuan Ye, Gaofeng Cheng, Ji Xu, Yaohui Jin, Qingqing Zhang, Pengyuan Zhang, Lei Xie, and Yonghong Yan. Open source magicdata-ramc: A rich annotated mandarin conversational(ramc) speech dataset. CoRR, abs/2203.16844, 2022. doi: 10.48550/ARXIV.220 3.168… — [doi:10.48550/arxiv.220](https://doi.org/10.48550/arxiv.220) [find](https://scholar.google.com/scholar?q=Zehui+Yang%2C+Yifan+Chen%2C+Lei+Luo%2C+Runyan+Yang%2C+Lingxuan+Ye%2C+Gaofeng+Cheng%2C+Ji+Xu%2C+Yaohui+Jin%2C+Qingqing+Zhang%2C+Pengyuan+Zhang%2C+Lei+Xie%2C+and+Yonghong+Yan%2E+Open+source+magicdata%2Dramc%3A+A+rich+annotated+man)
68. Zeyu Yang, Xinyu Zhang, Zibo Bi, Pei Zhang, Xize Cheng, Jin Xu, Baosong Yang, and Satoshi Nakamura. Mula-bench: A multilingual long-form audio understanding benchmark via multi-tier auditing, 2026. URL https://arxiv.org/abs/2609.23416. — [arXiv:2609.23416](https://arxiv.org/abs/2609.23416) [↗](https://arxiv.org/abs/2609.23416)
69. Bowen Ye, Rang Li, Qibin Yang, Yuanxin Liu, Linli Yao, Hanglong Lv, Zhihui Xie, Chenxin An, Lei Li, Lingpeng Kong, Qi Liu, Zhifang Sui, and Tong Yang. Claw-eval: Towards trustworthy evaluation of autonomous agents, 2026. URL https://arxiv.org/abs/2604.06132. — [arXiv:2604.06132](https://arxiv.org/abs/2604.06132) [↗](https://arxiv.org/abs/2604.06132)
70. Fan Yu, Shiliang Zhang, Yihui Fu, Lei Xie, Siqi Zheng, Zhihao Du, Weilong Huang, Pengcheng Guo, Zhijie Yan, Bin Ma, Xin Xu, and Hui Bu. M2met: The icassp 2022 multi-channel multi-party meeting transcription challenge. In ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signa… — [doi:10.1109/icassp43922.2022.9746465](https://doi.org/10.1109/icassp43922.2022.9746465) [find](https://scholar.google.com/scholar?q=Fan+Yu%2C+Shiliang+Zhang%2C+Yihui+Fu%2C+Lei+Xie%2C+Siqi+Zheng%2C+Zhihao+Du%2C+Weilong+Huang%2C+Pengcheng+Guo%2C+Zhijie+Yan%2C+Bin+Ma%2C+Xin+Xu%2C+and+Hui+Bu%2E+M2met%3A+The+icassp+2022+multi%2Dchannel+multi%2Dparty+meeting+transcr)
71. Yongyi Zang, Sean O’Brien, Taylor Berg-Kirkpatrick, Julian McAuley, and Zachary Novack. Are you really listening? boosting perceptual awareness in music-qa benchmarks. arXiv preprint arXiv:2504.00369, 2025. — [arXiv:2504.00369](https://arxiv.org/abs/2504.00369) [find](https://scholar.google.com/scholar?q=Yongyi+Zang%2C+Sean+O%E2%80%99Brien%2C+Taylor+Berg%2DKirkpatrick%2C+Julian+McAuley%2C+and+Zachary+Novack%2E+Are+you+really+listening%3F+boosting+perceptual+awareness+in+music%2Dqa+benchmarks%2E+arXiv+preprint+arXiv%3A2504%2E00369%2C)
72. Binbin Zhang, Hang Lv, Pengcheng Guo, Qijie Shao, Chao Yang, Lei Xie, Xin Xu, Hui Bu, Xiaoyu Chen, Chenchen Zeng, Di Wu, and Zhendong Peng. WENETSPEECH: A 10000+ hours multi-domain mandarin corpus for speech recognition. In IEEE International Conference on Acoustics, Speech and Signal Processing, IC… [find](https://scholar.google.com/scholar?q=Binbin+Zhang%2C+Hang+Lv%2C+Pengcheng+Guo%2C+Qijie+Shao%2C+Chao+Yang%2C+Lei+Xie%2C+Xin+Xu%2C+Hui+Bu%2C+Xiaoyu+Chen%2C+Chenchen+Zeng%2C+Di+Wu%2C+and+Zhendong+Peng%2E+WENETSPEECH%3A+A+10000%2B+hours+multi%2Ddomain+mandarin+corpus+for)
73. IEEE, 2022. doi: 10.1109/ICASSP43922.2022.9746682. URL https://doi.org/10.1109/ICASSP43922.2022.9746682. — [doi:10.1109/icassp43922.2022.9746682](https://doi.org/10.1109/icassp43922.2022.9746682) [↗](https://doi.org/10.1109/ICASSP43922.2022.9746682)
74. Linhao Zhang, Jian Zhang, Bokai Lei, Chuhan Wu, Aiwei Liu, Wei Jia, and Xiao Zhou. Wildspeech-bench: Benchmarking end-to-end speechllms in the wild, 2025. [find](https://scholar.google.com/scholar?q=Linhao+Zhang%2C+Jian+Zhang%2C+Bokai+Lei%2C+Chuhan+Wu%2C+Aiwei+Liu%2C+Wei+Jia%2C+and+Xiao+Zhou%2E+Wildspeech%2Dbench%3A+Benchmarking+end%2Dto%2Dend+speechllms+in+the+wild%2C+2025%2E)
75. Chujie Zheng, Shixuan Liu, Mingze Li, Xiong-Hui Chen, Bowen Yu, Chang Gao, Kai Dang, Yuqiong Liu, Rui Men, An Yang, et al. [Group sequence policy optimization](https://md.research.elamur.ai/free/en/papers/zheng-2025-group-sequence-policy-optimization/). arXiv preprint arXiv:2507.18071, 2025.
76. Ziwei Zhou, Rui Wang, and Zuxuan Wu. Daily-omni: Towards audio-visual reasoning with temporal alignment across modalities. CoRR, abs/2505.17862, 2025. — [arXiv:2505.17862](https://arxiv.org/abs/2505.17862) [find](https://scholar.google.com/scholar?q=Ziwei+Zhou%2C+Rui+Wang%2C+and+Zuxuan+Wu%2E+Daily%2Domni%3A+Towards+audio%2Dvisual+reasoning+with+temporal+alignment+across+modalities%2E+CoRR%2C+abs%2F2505%2E17862%2C+2025%2E+%E2%80%94+%5BarXiv%3A2505%2E17862%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2505%2E1)
77. Authors Core Contributors 4 Bing Han Baosong Yang Dake Guo Dayiheng Liu ∗ Fei Huang Hangrui Hu Hongkun Hao Hao Wang Hui Wang Junming Lin Jin Xu ∗ Keda Tao Linhan Ma Pei Zhang Qize Yang Ruiyang Xu Shun Lei Ting He Xize Cheng Xun Gong Xian Shi Xiong Wang Xinfa Zhu Xinyu Zhang Xueyao Zhang Yunfei Chu Y… [find](https://scholar.google.com/scholar?q=Authors+Core+Contributors+4+Bing+Han+Baosong+Yang+Dake+Guo+Dayiheng+Liu+%E2%88%97+Fei+Huang+Hangrui+Hu+Hongkun+Hao+Hao+Wang+Hui+Wang+Junming+Lin+Jin+Xu+%E2%88%97+Keda+Tao+Linhan+Ma+Pei+Zhang+Qize+Yang+Ruiyang+Xu+Shun)

*Updated 2 November 2026*