---
title: "PaperScope — paper by Xiong et al. (2026) — summary and ideas"
description: "Agentic deep research systems are mostly tested on web browsing or on understanding a single document. 39 references."
authors: ["Lei Xiong", "Huaying Yuan", "Zheng Liu", "Zhao Cao", "Zhicheng Dou"]
year: 2026
venue: "Findings of the Association for Computational Linguistics: ACL 2026"
source: "https://aclanthology.org/2026.findings-acl.394/"
doi: "10.18653/v1/2026.findings-acl.394"
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/xiong-2026-paperscope-multi-modal-multi-document/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/xiong-2026-paperscope-multi-modal-multi-document/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/44/) / PaperScope: A Multi-Modal Multi-Document Benchmark for Agentic Deep Research Across Massive Scientific Papers

# PaperScope: A Multi-Modal Multi-Document Benchmark for Agentic Deep Research Across Massive Scientific Papers

**Authors:** Lei Xiong, Huaying Yuan, [Zheng Liu](https://md.research.elamur.ai/free/en/authors/zheng-liu/), [Zhao Cao](https://md.research.elamur.ai/free/en/authors/zhao-cao/) and [Zhicheng Dou](https://md.research.elamur.ai/free/en/authors/zhicheng-dou/) · **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.394/) · [PDF](https://aclanthology.org/2026.findings-acl.394.pdf) · [DOI 10.18653/v1/2026.findings-acl.394](https://doi.org/10.18653/v1/2026.findings-acl.394) · [OpenAlex](https://openalex.org/W7166874728)

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

## Summary
Agentic deep research systems are mostly tested on web browsing or on understanding a single document. Real scientific work is different: it means pulling evidence from many papers at once, including their text, tables, figures, formulas and pseudocode. PaperScope is a benchmark built to measure this skill.

The authors gathered AI papers from arXiv and OpenReview and turned them into a knowledge graph of key information nodes. They then used an optimized random-walk article selector (ORWAS) to pick sets of papers that share a theme. Questions were written in reverse, starting from these sampled sets, so that each answer is grounded and close to unique within a large local corpus.

The resulting tasks cover topic induction, multi-document reasoning, summarization and solution design. Sixteen ReAct-based and Deep Research agents were evaluated, including OpenAI Deep Research and Tongyi Deep Research, and none scored well. The weak points were retrieval over long contexts, multi-modal understanding and combining evidence from several sources. Beyond the benchmark itself, the work offers a reusable pipeline for building similar datasets and possibly training data.

## Key points
- **Source corpus and graph:** 25,495 papers were collected from more than 20 top AI venues (2023–2025). The knowledge graph is built from over 2,000 of them, and each question comes with a corpus of roughly 202–1500 documents.
- **Benchmark size and structure:** 2,400 questions across 11 sub-tasks, grouped into four meta-categories:
  - Topic Induction (implicit and explicit)
  - Reasoning (figure/table/chart comparison and reasoning, formula, algorithm, full-paper)
  - Summary
  - Solution
- **Main result:** among the 16 evaluated systems, the best was Grok 4, which scored only 40.95.
- **ORWAS settings:** the default hyperparameters are walk length 100, bias probability 0.3 and 10,000 walks. These maximize the number of unique paper combinations in about 60 seconds, while longer walks or stronger bias add noise or reduce diversity.
- **Cross-domain pilot:** a test on 24 Medicine and Mechanics papers produced graphs with more than 690 nodes and more than 35,000 edges per domain. Experts rated the result with 95% satisfaction. Code and data are at github.com/CherYou/PaperScope.

*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

- [Renmin University of China](https://md.research.elamur.ai/free/en/universities/renmin-university-of-china/) — University, Beijing, China · 139 works · 17,752 citations
- [Beijing Academy of Artificial Intelligence](https://md.research.elamur.ai/free/en/labs/beijing-academy-of-artificial-intelligence/) — Research institute, Beijing, China · 46 works · 8,682 citations

📚 Shelves (6): [🖥️ 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 · [🗄️ Information Systems](https://md.research.elamur.ai/free/en/shelves/computer-science/information-systems/) · 1,730 works

🧭 Topics (2): [📏 Evaluation & benchmarks](https://md.research.elamur.ai/free/en/topics/evaluation-benchmarks/) · 1,341 works · [🖼️ Vision & language](https://md.research.elamur.ai/free/en/topics/multimodal/) · 811 works

## Cite

Cite as: Lei Xiong, Huaying Yuan, Zheng Liu, Zhao Cao and Zhicheng Dou. 2026. PaperScope: A Multi-Modal Multi-Document Benchmark for Agentic Deep Research Across Massive Scientific Papers. 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{xiong2026paperscope,
  title = {{PaperScope: A Multi-Modal Multi-Document Benchmark for Agentic Deep Research Across Massive Scientific Papers}},
  author = {Lei Xiong, Huaying Yuan, Zheng Liu, Zhao Cao and Zhicheng Dou},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.394},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.394}
}
```

- [← previous PAM: Enhancing General Alignment of Large Reasoning Models through Priority-Aware Metacognition](https://md.research.elamur.ai/free/en/papers/xu-2026-pam-enhancing-general-alignment-large/)
- [next → Par-ITA: Benchmarking Seq2Seq and LLMs on a Human-Supervised Parallel Corpus for Italian Hyperpartisan Neutralization](https://md.research.elamur.ai/free/en/papers/maggini-2026-par-ita-benchmarking-seq2seq-llms/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/44/)

## References

39 references, 22 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Qi Chen, Jingxuan Wei, Zhuoya Yao, Haiguang Wang, Gaowei Wu, Bihui Yu, Siyuan Li, and Cheng Tan. 2025. Researchpulse: Building method-experiment chains through multi-document scientific inference. In Proceedings of the 33rd ACM International Conference on Multimedia, pages 9110–9119. [find](https://scholar.google.com/scholar?q=Qi+Chen%2C+Jingxuan+Wei%2C+Zhuoya+Yao%2C+Haiguang+Wang%2C+Gaowei+Wu%2C+Bihui+Yu%2C+Siyuan+Li%2C+and+Cheng+Tan%2E+2025%2E+Researchpulse%3A+Building+method%2Dexperiment+chains+through+multi%2Ddocument+scientific+inference%2E+In+)
2. Hao Cui, Zahra Shamsi, Gowoon Cheon, Xuejian Ma, and 1 others. 2025. [Curie: Evaluating llms on multitask scientific long-context understanding and reasoning](https://md.research.elamur.ai/free/en/papers/cui-2025-curie-evaluating-llms-multitask-scientific/). In The Thirteenth International Conference on Learning Representations.
3. John Dagdelen, Alexander Dunn, Sanghoon Lee, Nicholas Walker, Andrew S Rosen, Gerbrand Ceder, Kristin A Persson, and Anubhav Jain. 2024. [Structured information extraction from scientific text with large language models](https://md.research.elamur.ai/free/en/papers/dagdelen-2024-structured-information-extraction-scientific-text/). Nature communications, 15(1):1418.
4. DeepSeek-AI. 2024. Deepseek-v3 technical report. Preprint, arXiv:2412.19437. [find](https://scholar.google.com/scholar?q=DeepSeek%2DAI%2E+2024%2E+Deepseek%2Dv3+technical+report%2E+Preprint%2C+arXiv%3A2412%2E19437%2E)
5. Kuicai Dong, Shurui Huang, Fangda Ye, Wei Han, Zhi Zhang, Dexun Li, Wenjun Li, Qu Yang, Gang Wang, Yichao Wang, and 1 others. 2025. Doc-researcher: A unified system for multimodal document parsing and deep research. arXiv preprint arXiv:2510.21603. — [arXiv:2510.21603](https://arxiv.org/abs/2510.21603) [find](https://scholar.google.com/scholar?q=Kuicai+Dong%2C+Shurui+Huang%2C+Fangda+Ye%2C+Wei+Han%2C+Zhi+Zhang%2C+Dexun+Li%2C+Wenjun+Li%2C+Qu+Yang%2C+Gang+Wang%2C+Yichao+Wang%2C+and+1+others%2E+2025%2E+Doc%2Dresearcher%3A+A+unified+system+for+multimodal+document+parsing+and)
6. Jiaxuan Gao, Wei Fu, Minyang Xie, Shusheng Xu, Chuyi He, Zhiyu Mei, Banghua Zhu, and Yi Wu. 2025. Beyond ten turns: Unlocking long-horizon agentic search with large-scale asynchronous rl. Preprint, arXiv:2508.07976. — [arXiv:2508.07976](https://arxiv.org/abs/2508.07976) [find](https://scholar.google.com/scholar?q=Jiaxuan+Gao%2C+Wei+Fu%2C+Minyang+Xie%2C+Shusheng+Xu%2C+Chuyi+He%2C+Zhiyu+Mei%2C+Banghua+Zhu%2C+and+Yi+Wu%2E+2025%2E+Beyond+ten+turns%3A+Unlocking+long%2Dhorizon+agentic+search+with+large%2Dscale+asynchronous+rl%2E+Preprint%2C+ar)
7. Xinyu Geng, Peng Xia, Zhen Zhang, Xinyu Wang, Qiuchen Wang, Ruixue Ding, Chenxi Wang, Jialong Wu, Yida Zhao, Kuan Li, and 1 others. 2025. Webwatcher: Breaking new frontier of vision-language deep research agent. arXiv preprint arXiv:2508.05748. — [arXiv:2508.05748](https://arxiv.org/abs/2508.05748) [find](https://scholar.google.com/scholar?q=Xinyu+Geng%2C+Peng+Xia%2C+Zhen+Zhang%2C+Xinyu+Wang%2C+Qiuchen+Wang%2C+Ruixue+Ding%2C+Chenxi+Wang%2C+Jialong+Wu%2C+Yida+Zhao%2C+Kuan+Li%2C+and+1+others%2E+2025%2E+Webwatcher%3A+Breaking+new+frontier+of+vision%2Dlanguage+deep+rese)
8. Google. 2025a. Deep research is now available on gemini 2.5 pro experimental. [find](https://scholar.google.com/scholar?q=Google%2E+2025a%2E+Deep+research+is+now+available+on+gemini+2%2E5+pro+experimental%2E)
9. Google. 2025b. Gemini 2.5 pro. [https://deepmind.google/technologies/gemini/pro/](https://deepmind.google/technologies/gemini/pro/). [↗](https://deepmind.google/technologies/gemini/pro/)
10. Bowen Jin, Hansi Zeng, Zhenrui Yue, Jinsung Yoon, Sercan O Arik, Dong Wang, Hamed Zamani, and Jiawei Han. 2025. [Search-r1: Training llms to reason and leverage search engines with reinforcement learning](https://md.research.elamur.ai/free/en/papers/jin-2025-search-r1-training-llms-reason/). In Second Conference on Language Modeling.
11. Chuhan Li, Ziyao Shangguan, Yilun Zhao, Deyuan Li, Yixin Liu, and Arman Cohan. 2024a. M3sciqa: A multi-modal multi-document scientific qa benchmark for evaluating foundation models. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 15419–15446. [find](https://scholar.google.com/scholar?q=Chuhan+Li%2C+Ziyao+Shangguan%2C+Yilun+Zhao%2C+Deyuan+Li%2C+Yixin+Liu%2C+and+Arman+Cohan%2E+2024a%2E+M3sciqa%3A+A+multi%2Dmodal+multi%2Ddocument+scientific+qa+benchmark+for+evaluating+foundation+models%2E+In+Findings+of+the)
12. Lei Li, Yuqi Wang, Runxin Xu, Peiyi Wang, Xiachong Feng, Lingpeng Kong, and Qi Liu. 2024b. [Multimodal arxiv: A dataset for improving scientific comprehension of large vision-language models](https://md.research.elamur.ai/free/en/papers/li-2024-multimodal-arxiv-dataset-improving-scientific/). In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Pa…
13. Xiaoxi Li, Jiajie Jin, Guanting Dong, Hongjin Qian, Yongkang Wu, Ji-Rong Wen, Yutao Zhu, and Zhicheng Dou. 2025a. [Webthinker: Empowering large reasoning models with deep research capability](https://md.research.elamur.ai/free/en/papers/li-2025-webthinker-empowering-large-reasoning-models/). In The Thirty-ninth Annual Conference on Neural Information Processing Systems.
14. Zekun Li, Xianjun Yang, Kyuri Choi, Wanrong Zhu, Ryan Hsieh, HyeonJung Kim, Jin Hyuk Lim, Sungyoung Ji, Byungju Lee, Xifeng Yan, and 1 others. 2024c. Mmsci: A multimodal multi-discipline dataset for phd-level scientific comprehension. In AI for Accelerated Materials Design-Vienna 2024. [find](https://scholar.google.com/scholar?q=Zekun+Li%2C+Xianjun+Yang%2C+Kyuri+Choi%2C+Wanrong+Zhu%2C+Ryan+Hsieh%2C+HyeonJung+Kim%2C+Jin+Hyuk+Lim%2C+Sungyoung+Ji%2C+Byungju+Lee%2C+Xifeng+Yan%2C+and+1+others%2E+2024c%2E+Mmsci%3A+A+multimodal+multi%2Ddiscipline+dataset+for+p)
15. Zhuoqun Li, Haiyang Yu, Xuanang Chen, Hongyu Lin, Yaojie Lu, Fei Huang, Xianpei Han, Yongbin Li, and Le Sun. 2025b. [Deepsolution: Boosting complex engineering solution design via tree-based exploration and bi-point thinking](https://md.research.elamur.ai/free/en/papers/li-2025-deepsolution-boosting-complex-engineering-solution/). In Proceedings of the 63rd Annual Meeting of the Association for Computatio…
16. Yubo Ma, Yuhang Zang, Liangyu Chen, Meiqi Chen, Yizhu Jiao, Xinze Li, Xinyuan Lu, Ziyu Liu, Yan Ma, Xiaoyi Dong, and 1 others. 2024. [Mmlongbench-doc: Benchmarking long-context document understanding with visualizations](https://md.research.elamur.ai/free/en/papers/ma-2024-mmlongbench-doc-benchmarking-long-context/). Advances in Neural Information Processing Systems, 37:95963–96010.
17. Yu A Malkov and Dmitry A Yashunin. 2018. [Efficient and robust approximate nearest neighbor search using hierarchical navigable small world graphs](https://md.research.elamur.ai/free/en/papers/malkov-2016-efficient-robust-approximate-nearest-neighbor/). IEEE transactions on pattern analysis and machine intelligence, 42(4):824–836.
18. Ahmed Masry, Xuan Long Do, Jia Qing Tan, Shafiq Joty, and Enamul Hoque. 2022. [Chartqa: A benchmark for question answering about charts with visual and logical reasoning](https://md.research.elamur.ai/free/en/papers/masry-2022-chartqa-benchmark-question-answering-about/). In Findings of the association for computational linguistics: ACL 2022, pages 2263– 2279.
19. 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)
20. Minesh Mathew, Dimosthenis Karatzas, and CV Jawahar. 2021. [Docvqa: A dataset for vqa on document images](https://md.research.elamur.ai/free/en/papers/mathew-2020-docvqa-dataset-vqa-document-images/). In Proceedings of the IEEE/CVF winter conference on applications of computer vision, pages 2200–2209.
21. Grégoire Mialon, Clémentine Fourrier, Thomas Wolf, Yann LeCun, and Thomas Scialom. 2023a. [Gaia: a benchmark for general ai assistants](https://md.research.elamur.ai/free/en/papers/mialon-2023-gaia-benchmark-general-ai-assistants/). In The Twelfth International Conference on Learning Representations.
22. Grégoire Mialon, Clémentine Fourrier, Thomas Wolf, Yann LeCun, and Thomas Scialom. 2023b. [Gaia: a benchmark for general ai assistants](https://md.research.elamur.ai/free/en/papers/mialon-2023-gaia-benchmark-general-ai-assistants/). In The Twelfth International Conference on Learning Representations.
23. Junbo Niu, Zheng Liu, Zhuangcheng Gu, Bin Wang, Linke Ouyang, Zhiyuan Zhao, Tao Chu, Tianyao He, Fan Wu, Qintong Zhang, and 1 others. 2025. Mineru2. 5: A decoupled vision-language model for efficient high-resolution document parsing. arXiv preprint arXiv:2509.22186. — [MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing](https://md.research.elamur.ai/free/en/papers/niu-2026-mineru2-5-decoupled-vision-language/)
24. Rulin Shao, Akari Asai, Shannon Zejiang Shen, Hamish Ivison, Varsha Kishore, Jingming Zhuo, Xinran Zhao, Molly Park, Samuel G Finlayson, David Sontag, and 1 others. 2025. [Dr tulu: Reinforcement learning with evolving rubrics for deep research](https://md.research.elamur.ai/free/en/papers/shao-2025-dr-tulu-reinforcement-learning-evolving/). arXiv preprint arXiv:2511.19399.
25. Kimi Team, Yifan Bai, Yiping Bao, Guanduo Chen, Jiahao Chen, Ningxin Chen, Ruijue Chen, Yanru Chen, Yuankun Chen, Yutian Chen, and 1 others. 2025a. [Kimi k2: Open agentic intelligence](https://md.research.elamur.ai/free/en/papers/kimi-team-2025-kimi-k2-open-agentic/). arXiv preprint arXiv:2507.20534.
26. MiroMind Team, Song Bai, Lidong Bing, Carson Chen, Guanzheng Chen, Yuntao Chen, Zhe Chen, Ziyi Chen, Jifeng Dai, Xuan Dong, and 1 others. 2025b. Mirothinker: Pushing the performance boundaries of open-source research agents via model, context, and interactive scaling. arXiv preprint arXiv:2511.11793… — [arXiv:2511.11793](https://arxiv.org/abs/2511.11793) [find](https://scholar.google.com/scholar?q=MiroMind+Team%2C+Song+Bai%2C+Lidong+Bing%2C+Carson+Chen%2C+Guanzheng+Chen%2C+Yuntao+Chen%2C+Zhe+Chen%2C+Ziyi+Chen%2C+Jifeng+Dai%2C+Xuan+Dong%2C+and+1+others%2E+2025b%2E+Mirothinker%3A+Pushing+the+performance+boundaries+of+open)
27. Tongyi DeepResearch Team, Baixuan Li, Bo Zhang, Dingchu Zhang, Fei Huang, Guangyu Li, Guoxin Chen, Huifeng Yin, Jialong Wu, Jingren Zhou, and 1 others. 2025c. Tongyi deepresearch technical report. arXiv preprint arXiv:2510.24701. — [arXiv:2510.24701](https://arxiv.org/abs/2510.24701) [find](https://scholar.google.com/scholar?q=Tongyi+DeepResearch+Team%2C+Baixuan+Li%2C+Bo+Zhang%2C+Dingchu+Zhang%2C+Fei+Huang%2C+Guangyu+Li%2C+Guoxin+Chen%2C+Huifeng+Yin%2C+Jialong+Wu%2C+Jingren+Zhou%2C+and+1+others%2E+2025c%2E+Tongyi+deepresearch+technical+report%2E+arX)
28. V Team, Wenyi Hong, Wenmeng Yu, and 1 others. 2025d. [Glm-4.5v and glm-4.1v-thinking: Towards versatile multimodal reasoning with scalable reinforcement learning](https://md.research.elamur.ai/free/en/papers/team-2025-v-glm-4-5v-glm/). Preprint, arXiv:2507.01006.
29. Yang Tian, Zheng Lu, Mingqi Gao, Zheng Liu, and Bo Zhao. 2025. Mmcr: Benchmarking cross-source reasoning in scientific papers. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 488–497. [find](https://scholar.google.com/scholar?q=Yang+Tian%2C+Zheng+Lu%2C+Mingqi+Gao%2C+Zheng+Liu%2C+and+Bo+Zhao%2E+2025%2E+Mmcr%3A+Benchmarking+cross%2Dsource+reasoning+in+scientific+papers%2E+In+Proceedings+of+the+IEEE%2FCVF+International+Conference+on+Computer+Visio)
30. Zirui Wang, Mengzhou Xia, Luxi He, Howard Chen, Yitao Liu, Richard Zhu, Kaiqu Liang, Xindi Wu, Haotian Liu, Sadhika Malladi, and 1 others. 2024. [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/). Advances in Neural Information Processing Systems, 37:113569–113697.
31. Haoran Wei, Yaofeng Sun, and Yukun Li. 2025a. [Deepseek-ocr: Contexts optical compression](https://md.research.elamur.ai/free/en/papers/wei-2025-deepseek-ocr-contexts-optical/). arXiv preprint arXiv:2510.18234.
32. OpenAI. 2024. Gpt-4o mini: advancing cost-efficient intelligence. [https://openai.com/index/](https://openai.com/index/) gpt-4o-mini-advancing-cost-efficient-intelligence/. [↗](https://openai.com/index/)
33. Jason Wei, Zhiqing Sun, Spencer Papay, and 1 others. 2025b. [Browsecomp: A simple yet challenging benchmark for browsing agents](https://md.research.elamur.ai/free/en/papers/wei-2025-browsecomp-simple-yet-challenging-benchmark/). arXiv preprint arXiv:2504.12516.
34. OpenAI. 2025a. Deep research system card. [find](https://scholar.google.com/scholar?q=OpenAI%2E+2025a%2E+Deep+research+system+card%2E)
35. Jinming Wu, Zihao Deng, Wei Li, Yiding Liu, Bo You, Bo Li, Zejun Ma, and Ziwei Liu. 2025. [Mmsearch-r1: Incentivizing lmms to search](https://md.research.elamur.ai/free/en/papers/wu-2026-mmsearch-r1-incentivizing-lmms-search/). arXiv preprint arXiv:2506.20670.
36. OpenAI. 2025b. Gpt-5 is here. [https://openai.com/](https://openai.com/) gpt-5/. [↗](https://openai.com/)
37. Long Phan, Alice Gatti, Ziwen Han, Nathaniel Li, Josephina Hu, Hugh Zhang, Chen Bo Calvin Zhang, Mohamed Shaaban, John Ling, Sean Shi, and 1 others. 2025. [Humanity’s last exam](https://md.research.elamur.ai/free/en/papers/phan-2025-humanity-s-last-exam/). arXiv preprint arXiv:2501.14249.
38. Alibaba Cloud Qwen team. 2025. Qwen3-vl: Sharper vision, deeper thought, broader action. xAI. 2025. Grok 4. [find](https://scholar.google.com/scholar?q=Alibaba+Cloud+Qwen+team%2E+2025%2E+Qwen3%2Dvl%3A+Sharper+vision%2C+deeper+thought%2C+broader+action%2E+xAI%2E+2025%2E+Grok+4%2E)
39. Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik R Narasimhan, and Yuan Cao. 2022. [React: Synergizing reasoning and acting in language models](https://md.research.elamur.ai/free/en/papers/yao-2022-react-synergizing-reasoning-acting-language/). In The eleventh international conference on learning representations.

*Updated 2 November 2026*