---
title: "StreamMeCo — paper by Wang et al. (2026)"
description: "Text nodes describe visual content, and face and voice nodes represent entities. 67 references, cited by 3 papers here."
authors: ["Junxi Wang", "Te Sun", "Jiayi Zhu", "Junxian Li", "Haowen Xu", "Zichen Wen", "Xuming Hu", "Zhiyu li", "Linfeng Zhang"]
year: 2026
venue: "Findings of the Association for Computational Linguistics: ACL 2026"
source: "https://aclanthology.org/2026.findings-acl.647/"
doi: "10.18653/v1/2026.findings-acl.647"
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-streammeco-long-term-agent-memory/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/wang-2026-streammeco-long-term-agent-memory/)

[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/) / StreamMeCo: Long-Term Agent Memory Compression for Efficient Streaming Video Understanding

# StreamMeCo: Long-Term Agent Memory Compression for Efficient Streaming Video Understanding

**Authors:** Junxi Wang, Te Sun, Jiayi Zhu, Junxian Li, Haowen Xu, [Zichen Wen](https://md.research.elamur.ai/free/en/authors/zichen-wen/), [Xuming Hu](https://md.research.elamur.ai/free/en/authors/xuming-hu/), [Zhiyu li](https://md.research.elamur.ai/free/en/authors/zhiyu-li/) and [Linfeng Zhang](https://md.research.elamur.ai/free/en/authors/linfeng-zhang/) · **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.647/) · [PDF](https://aclanthology.org/2026.findings-acl.647.pdf) · [DOI 10.18653/v1/2026.findings-acl.647](https://doi.org/10.18653/v1/2026.findings-acl.647) · [OpenAlex](https://openalex.org/W7166841131)

**Citations:** 0 citations (OpenAlex, 2026-10-14) · [3](https://md.research.elamur.ai/free/en/papers/wang-2026-streammeco-long-term-agent-memory/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
Agent-based streaming video systems like M3-Agent store what they observe as a memory graph. Text nodes describe visual content, and face and voice nodes represent entities. As videos get longer, the number of text nodes grows sharply, and retrieval latency becomes too high for real-time question answering.

StreamMeCo is a training-free framework that shrinks this graph. It treats text nodes differently depending on whether they have edges:
- **Isolated nodes** (no links to entities) are clustered. Within each cluster, a minmax procedure keeps the node nearest the center, then repeatedly adds the node farthest from those already kept.
- **Connected nodes** are scored by combining entity importance, taken from edge weights to face and voice nodes, with dissimilarity between embeddings.

To offset losses from compression, a time-decay retrieval scheme gives each time segment a share of retrieved nodes based on its query relevance. It also applies a nonlinear decay that favors recent memories.

With about 70% of the graph removed, retrieval becomes 1.87× faster and accuracy rises by 1.0% on average. Long-video memory agents could therefore become cheaper to store and quicker to query.

## Key points
- Evaluated on M3-Bench-robot, M3-Bench-web and Video-MME-Long, building on M3-Agent memory graphs.
- The three components are EMsampling (spherical KMeans plus minmax sampling), EWpruning (fusion of entity importance and embedding similarity) and the TMR time-decay retrieval mechanism.
- In the ablation, the full method reached 30.7% on M3-Bench-robot (101.3% of the original M3-Agent) and 47.0% on M3-Bench-web (98.1%). Random compression scored 28.5% and 44.6%.
- The best hyperparameters were a cluster ratio of a = 0.05 and a balance coefficient of b = 0.1. On M3-Bench-robot, exponential decay with coefficient 0.1 scored 34.6%, beating both linear decay and a piecewise halving scheme (33.8%).
- Building memory graphs requires calls to Gemini-2.5-Pro and text-embedding-3-large, and this cost limited testing to just one additional dataset. Code is published at github.com/Celina-love-sweet/StreamMeCo.

*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

- [Fudan University](https://md.research.elamur.ai/free/en/universities/fudan-university/) — University, Shanghai, China · 167 works · 20,987 citations
- [Hong Kong University of Science and Technology](https://md.research.elamur.ai/free/en/universities/hong-kong-university-of-science-and-technology/) — University, Hong Kong, China · 142 works · 25,136 citations
- [Shanghai Jiao Tong University](https://md.research.elamur.ai/free/en/universities/shanghai-jiao-tong-university/) — University, Shanghai, China · 149 works · 16,161 citations
- [Shanghai Artificial Intelligence Laboratory](https://md.research.elamur.ai/free/en/labs/shanghai-artificial-intelligence-laboratory/) — Research institute, Shanghai, China · 117 works · 11,281 citations

📚 Shelves (2): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [👁️ Computer Vision and Pattern Recognition](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · 2,869 works

🧭 Topics (1): [🪶 Efficient models & compression](https://md.research.elamur.ai/free/en/topics/efficient-models/) · 242 works

## Cite

Cite as: Junxi Wang, Te Sun, Jiayi Zhu, Junxian Li, Haowen Xu, Zichen Wen, Xuming Hu, Zhiyu li and Linfeng Zhang. 2026. StreamMeCo: Long-Term Agent Memory Compression for Efficient Streaming Video Understanding. 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{wang2026streammeco,
  title = {{StreamMeCo: Long-Term Agent Memory Compression for Efficient Streaming Video Understanding}},
  author = {Junxi Wang, Te Sun, Jiayi Zhu, Junxian Li, Haowen Xu, Zichen Wen, Xuming Hu, Zhiyu li and Linfeng Zhang},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.647},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.647}
}
```

- [← previous Steering Large Language Models for Machine Translation Personalization](https://md.research.elamur.ai/free/en/papers/scalena-2026-steering-large-language-models-machine/)
- [next → STReasoner: Empowering LLMs for Spatio-Temporal Reasoning in Time Series via Spatial-Aware Reinforcement Learning](https://md.research.elamur.ai/free/en/papers/ni-2026-streasoner-empowering-llms-spatio-temporal/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/6/)

## References

67 references, 16 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Shuai Bai, Keqin Chen, Xuejing Liu, Jialin Wang, Wenbin Ge, Sibo Song, Kai Dang, Peng Wang, Shijie Wang, Jun Tang, and 1 others. 2025. [Qwen2.5-vl technical report](https://md.research.elamur.ai/free/en/papers/bai-2025-qwen2-5-vl-technical/). arXiv preprint arXiv:2502.13923.
2. Joya Chen, Zhaoyang Lv, Shiwei Wu, Kevin Qinghong Lin, Chenan Song, Difei Gao, Jia-Wei Liu, Ziteng Gao, Dongxing Mao, and Mike Zheng Shou. 2024. Videollm-online: Online video large language model for streaming video. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognitio… [find](https://scholar.google.com/scholar?q=Joya+Chen%2C+Zhaoyang+Lv%2C+Shiwei+Wu%2C+Kevin+Qinghong+Lin%2C+Chenan+Song%2C+Difei+Gao%2C+Jia%2DWei+Liu%2C+Ziteng+Gao%2C+Dongxing+Mao%2C+and+Mike+Zheng+Shou%2E+2024%2E+Videollm%2Donline%3A+Online+video+large+language+model+for+)
3. Xueyi Chen, Keda Tao, Kele Shao, and Huan Wang. 2025. Streamingtom: Streaming token compression for efficient video understanding. arXiv preprint arXiv:2510.18269. — [arXiv:2510.18269](https://arxiv.org/abs/2510.18269) [find](https://scholar.google.com/scholar?q=Xueyi+Chen%2C+Keda+Tao%2C+Kele+Shao%2C+and+Huan+Wang%2E+2025%2E+Streamingtom%3A+Streaming+token+compression+for+efficient+video+understanding%2E+arXiv+preprint+arXiv%3A2510%2E18269%2E+%E2%80%94+%5BarXiv%3A2510%2E18269%5D%28https%3A%2F%2Farxiv%2Eo)
4. Prateek Chhikara, Dev Khant, Saket Aryan, Taranjeet Singh, and Deshraj Yadav. 2025a. [Mem0: Building production-ready ai agents with scalable long-term memory](https://md.research.elamur.ai/free/en/papers/chhikara-2025-mem0-building-production-ready-ai/). arXiv preprint arXiv:2504.19413.
5. Prateek Chhikara, Dev Khant, Saket Aryan, Taranjeet Singh, and Deshraj Yadav. 2025b. [Mem0: Building production-ready ai agents with scalable long-term memory](https://md.research.elamur.ai/free/en/papers/chhikara-2025-mem0-building-production-ready-ai/). arXiv preprint arXiv:2504.19413.
6. Inderjit S Dhillon and Dharmendra S Modha. 2001. Concept decompositions for large sparse text data using clustering. Machine learning, 42(1):143–175. [find](https://scholar.google.com/scholar?q=Inderjit+S+Dhillon+and+Dharmendra+S+Modha%2E+2001%2E+Concept+decompositions+for+large+sparse+text+data+using+clustering%2E+Machine+learning%2C+42%281%29%3A143%E2%80%93175%2E)
7. Xingjian Diao, Chunhui Zhang, Keyi Kong, Weiyi Wu, Chiyu Ma, Zhongyu Ouyang, Peijun Qing, Soroush Vosoughi, and Jiang Gui. 2025b. [Soundmind: Rl-incentivized logic reasoning for audio-language models](https://md.research.elamur.ai/free/en/papers/diao-2025-soundmind-rl-incentivized-logic-reasoning/). In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 528…
8. Xingjian Diao, Chunhui Zhang, Tingxuan Wu, Ming Cheng, Zhongyu Ouyang, Weiyi Wu, and Jiang Gui. 2024. Learning musical representations for music performance question answering. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 2803–2813. [find](https://scholar.google.com/scholar?q=Xingjian+Diao%2C+Chunhui+Zhang%2C+Tingxuan+Wu%2C+Ming+Cheng%2C+Zhongyu+Ouyang%2C+Weiyi+Wu%2C+and+Jiang+Gui%2E+2024%2E+Learning+musical+representations+for+music+performance+question+answering%2E+In+Findings+of+the+Asso)
9. Xingjian Diao, Chunhui Zhang, Weiyi Wu, Zhongyu Ouyang, Peijun Qing, Ming Cheng, Soroush Vosoughi, and Jiang Gui. 2025c. Temporal working memory: Query-guided segment refinement for enhanced multimodal understanding. In Findings of the Association for Computational Linguistics: NAACL 2025, pages 339… [find](https://scholar.google.com/scholar?q=Xingjian+Diao%2C+Chunhui+Zhang%2C+Weiyi+Wu%2C+Zhongyu+Ouyang%2C+Peijun+Qing%2C+Ming+Cheng%2C+Soroush+Vosoughi%2C+and+Jiang+Gui%2E+2025c%2E+Temporal+working+memory%3A+Query%2Dguided+segment+refinement+for+enhanced+multimoda)
10. Vaggelis Dorovatas, Soroush Seifi, Gunshi Gupta, and Rahaf Aljundi. 2025. Recurrent attention-based token selection for efficient streaming video-llms. arXiv preprint arXiv:2510.17364. — [arXiv:2510.17364](https://arxiv.org/abs/2510.17364) [find](https://scholar.google.com/scholar?q=Vaggelis+Dorovatas%2C+Soroush+Seifi%2C+Gunshi+Gupta%2C+and+Rahaf+Aljundi%2E+2025%2E+Recurrent+attention%2Dbased+token+selection+for+efficient+streaming+video%2Dllms%2E+arXiv+preprint+arXiv%3A2510%2E17364%2E+%E2%80%94+%5BarXiv%3A2510%2E1)
11. Yue Fan, Xiaojian Ma, Rongpeng Su, Jun Guo, Rujie Wu, Xi Chen, and Qing Li. 2025. Embodied videoagent: Persistent memory from egocentric videos and embodied sensors enables dynamic scene understanding. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 6342–6352. [find](https://scholar.google.com/scholar?q=Yue+Fan%2C+Xiaojian+Ma%2C+Rongpeng+Su%2C+Jun+Guo%2C+Rujie+Wu%2C+Xi+Chen%2C+and+Qing+Li%2E+2025%2E+Embodied+videoagent%3A+Persistent+memory+from+egocentric+videos+and+embodied+sensors+enables+dynamic+scene+understanding)
12. Zhen Fang, Zhuoyang Liu, Jiaming Liu, Hao Chen, Yu Zeng, Shiting Huang, Zehui Chen, Lin Chen, Shanghang Zhang, and Feng Zhao. 2025. Dualvla: Building a generalizable embodied agent via partial decoupling of reasoning and action. arXiv preprint arXiv:2511.22134. — [arXiv:2511.22134](https://arxiv.org/abs/2511.22134) [find](https://scholar.google.com/scholar?q=Zhen+Fang%2C+Zhuoyang+Liu%2C+Jiaming+Liu%2C+Hao+Chen%2C+Yu+Zeng%2C+Shiting+Huang%2C+Zehui+Chen%2C+Lin+Chen%2C+Shanghang+Zhang%2C+and+Feng+Zhao%2E+2025%2E+Dualvla%3A+Building+a+generalizable+embodied+agent+via+partial+decoupl)
13. Chaoyou Fu, Yuhan Dai, Yongdong Luo, Lei Li, Shuhuai Ren, Renrui Zhang, Zihan Wang, Chenyu Zhou, Yunhang Shen, Mengdan Zhang, and 1 others. 2025. [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 Reco…
14. Shangzhe Di, Zhelun Yu, Guanghao Zhang, Haoyuan Li, Tao Zhong, Hao Cheng, Bolin Li, Wanggui He, Fangxun Shu, and Hao Jiang. 2025. Streaming video question-answering with in-context video kv-cache retrieval. arXiv preprint arXiv:2503.00540. [find](https://scholar.google.com/scholar?q=Shangzhe+Di%2C+Zhelun+Yu%2C+Guanghao+Zhang%2C+Haoyuan+Li%2C+Tao+Zhong%2C+Hao+Cheng%2C+Bolin+Li%2C+Wanggui+He%2C+Fangxun+Shu%2C+and+Hao+Jiang%2E+2025%2E+Streaming+video+question%2Danswering+with+in%2Dcontext+video+kv%2Dcache+retr)
15. Ruiyan Han, Zhen Fang, XinYu Sun, Yuchen Ma, Ziheng Wang, Yu Zeng, Zehui Chen, Lin Chen, Wenxuan Huang, Wei-Jie Xu, and 1 others. 2026. [Unicorn: Towards self-improving unified multimodal models through self-generated supervision](https://md.research.elamur.ai/free/en/papers/fang-2026-unicorn-self-improving-unified-multimodal/). arXiv preprint arXiv:2601.03193.
16. Xingjian Diao, Tianzhen Yang, Chunhui Zhang, Weiyi Wu, Ming Cheng, and Jiang Gui. 2025a. Learning sparsity for effective and efficient music performance question answering. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 136–… [find](https://scholar.google.com/scholar?q=Xingjian+Diao%2C+Tianzhen+Yang%2C+Chunhui+Zhang%2C+Weiyi+Wu%2C+Ming+Cheng%2C+and+Jiang+Gui%2E+2025a%2E+Learning+sparsity+for+effective+and+efficient+music+performance+question+answering%2E+In+Proceedings+of+the+63rd+)
17. Bo He, Hengduo Li, Young Kyun Jang, Menglin Jia, Xuefei Cao, Ashish Shah, Abhinav Shrivastava, and Ser-Nam Lim. 2024. Ma-lmm: Memory-augmented large multimodal model for long-term video understanding. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 13504–1… [find](https://scholar.google.com/scholar?q=Bo+He%2C+Hengduo+Li%2C+Young+Kyun+Jang%2C+Menglin+Jia%2C+Xuefei+Cao%2C+Ashish+Shah%2C+Abhinav+Shrivastava%2C+and+Ser%2DNam+Lim%2E+2024%2E+Ma%2Dlmm%3A+Memory%2Daugmented+large+multimodal+model+for+long%2Dterm+video+understanding%2E)
18. Shiting Huang, Zhen Fang, Zehui Chen, Siyu Yuan, Junjie Ye, Yu Zeng, Lin Chen, Qi Mao, and Feng Zhao. 2025a. [Critictool: Evaluating self-critique capabilities of large language models in tool-calling error scenarios](https://md.research.elamur.ai/free/en/papers/huang-2025-critictool-evaluating-self-critique-capabilities/). In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Proc…
19. Zhenpeng Huang, Xinhao Li, Jiaqi Li, Jing Wang, Xiangyu Zeng, Cheng Liang, Tao Wu, Xi Chen, Liang Li, and Limin Wang. 2025b. Online video understanding: Ovbench and videochat-online. In Proceedings of the Computer Vision and Pattern Recognition Conference, pages 3328–3338. [find](https://scholar.google.com/scholar?q=Zhenpeng+Huang%2C+Xinhao+Li%2C+Jiaqi+Li%2C+Jing+Wang%2C+Xiangyu+Zeng%2C+Cheng+Liang%2C+Tao+Wu%2C+Xi+Chen%2C+Liang+Li%2C+and+Limin+Wang%2E+2025b%2E+Online+video+understanding%3A+Ovbench+and+videochat%2Donline%2E+In+Proceedings+of)
20. Aaron Hurst, Adam Lerer, Adam P Goucher, Adam Perelman, Aditya Ramesh, Aidan Clark, AJ Ostrow, Akila Welihinda, Alan Hayes, Alec Radford, and 1 others. 2024. [Gpt-4o system card](https://md.research.elamur.ai/free/en/papers/openai-2024-gpt-4o-system-card/). arXiv preprint arXiv:2410.21276.
21. Kumara Kahatapitiya, Kanchana Ranasinghe, Jongwoo Park, and Michael S Ryoo. 2025. Language repository for long video understanding. In Findings of the Association for Computational Linguistics: ACL 2025, pages 5627–5646. [find](https://scholar.google.com/scholar?q=Kumara+Kahatapitiya%2C+Kanchana+Ranasinghe%2C+Jongwoo+Park%2C+and+Michael+S+Ryoo%2E+2025%2E+Language+repository+for+long+video+understanding%2E+In+Findings+of+the+Association+for+Computational+Linguistics%3A+ACL+20)
22. Minsoo Kim, Kyuhong Shim, Jungwook Choi, and Simyung Chang. 2025. Infinipot-v: Memory-constrained kv cache compression for streaming video understanding. arXiv preprint arXiv:2506.15745. [find](https://scholar.google.com/scholar?q=Minsoo+Kim%2C+Kyuhong+Shim%2C+Jungwook+Choi%2C+and+Simyung+Chang%2E+2025%2E+Infinipot%2Dv%3A+Memory%2Dconstrained+kv+cache+compression+for+streaming+video+understanding%2E+arXiv+preprint+arXiv%3A2506%2E15745%2E)
23. Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich Küttler, Mike Lewis, Wen-tau Yih, Tim Rocktäschel, and 1 others. 2020. [Retrieval-augmented generation for knowledge-intensive nlp tasks](https://md.research.elamur.ai/free/en/papers/lewis-2020-retrieval-augmented-generation-knowledge-intensive/). Advances in neural information processing systems, 33:9459–…
24. Chenghao Li, Chaoning Zhang, Yi Lu, Jiaquan Zhang, Qigan Sun, Xudong Wang, Jiwei Wei, Guoqing Wang, Yang Yang, and Heng Tao Shen. 2025a. Syzygy of thoughts: Improving llm cot with the minimal free resolution. arXiv preprint arXiv:2504.09566. [find](https://scholar.google.com/scholar?q=Chenghao+Li%2C+Chaoning+Zhang%2C+Yi+Lu%2C+Jiaquan+Zhang%2C+Qigan+Sun%2C+Xudong+Wang%2C+Jiwei+Wei%2C+Guoqing+Wang%2C+Yang+Yang%2C+and+Heng+Tao+Shen%2E+2025a%2E+Syzygy+of+thoughts%3A+Improving+llm+cot+with+the+minimal+free+res)
25. Ruanjun Li, Yuedong Tan, Yuanming Shi, and Jiawei Shao. 2025b. Videoscan: Enabling efficient streaming video understanding via frame-level semantic carriers. arXiv preprint arXiv:2503.09387. [find](https://scholar.google.com/scholar?q=Ruanjun+Li%2C+Yuedong+Tan%2C+Yuanming+Shi%2C+and+Jiawei+Shao%2E+2025b%2E+Videoscan%3A+Enabling+efficient+streaming+video+understanding+via+frame%2Dlevel+semantic+carriers%2E+arXiv+preprint+arXiv%3A2503%2E09387%2E)
26. Zhiyu Li, Chenyang Xi, Chunyu Li, Ding Chen, Boyu Chen, Shichao Song, Simin Niu, Hanyu Wang, Jiawei Yang, Chen Tang, and 1 others. 2025c. Memos: A memory os for ai system. arXiv preprint arXiv:2507.03724. — [arXiv:2507.03724](https://arxiv.org/abs/2507.03724) [find](https://scholar.google.com/scholar?q=Zhiyu+Li%2C+Chenyang+Xi%2C+Chunyu+Li%2C+Ding+Chen%2C+Boyu+Chen%2C+Shichao+Song%2C+Simin+Niu%2C+Hanyu+Wang%2C+Jiawei+Yang%2C+Chen+Tang%2C+and+1+others%2E+2025c%2E+Memos%3A+A+memory+os+for+ai+system%2E+arXiv+preprint+arXiv%3A2507%2E03)
27. Lin Long, Yichen He, Wentao Ye, Yiyuan Pan, Yuan Lin, Hang Li, Junbo Zhao, and Wei Li. 2025. Seeing, listening, remembering, and reasoning: A multimodal agent with long-term memory. arXiv preprint arXiv:2508.09736. — [arXiv:2508.09736](https://arxiv.org/abs/2508.09736) [find](https://scholar.google.com/scholar?q=Lin+Long%2C+Yichen+He%2C+Wentao+Ye%2C+Yiyuan+Pan%2C+Yuan+Lin%2C+Hang+Li%2C+Junbo+Zhao%2C+and+Wei+Li%2E+2025%2E+Seeing%2C+listening%2C+remembering%2C+and+reasoning%3A+A+multimodal+agent+with+long%2Dterm+memory%2E+arXiv+preprint+arX)
28. Zhicong Lu, Haijun Xia, Seongkook Heo, and Daniel Wigdor. 2018. You watch, you give, and you engage: a study of live streaming practices in china. In Proceedings of the 2018 CHI conference on human factors in computing systems, pages 1–13. [find](https://scholar.google.com/scholar?q=Zhicong+Lu%2C+Haijun+Xia%2C+Seongkook+Heo%2C+and+Daniel+Wigdor%2E+2018%2E+You+watch%2C+you+give%2C+and+you+engage%3A+a+study+of+live+streaming+practices+in+china%2E+In+Proceedings+of+the+2018+CHI+conference+on+human+fa)
29. Xueqi Ma, Shuo Yang, Yanbei Jiang, Shu Liu, Zhenzhen Liu, Jiayang Ao, Xingjun Ma, Sarah Monazam Erfani, and James Bailey. 2026. Attention in space: Functional roles of vlm heads for spatial reasoning. arXiv preprint arXiv:2603.20662. — [arXiv:2603.20662](https://arxiv.org/abs/2603.20662) [find](https://scholar.google.com/scholar?q=Xueqi+Ma%2C+Shuo+Yang%2C+Yanbei+Jiang%2C+Shu+Liu%2C+Zhenzhen+Liu%2C+Jiayang+Ao%2C+Xingjun+Ma%2C+Sarah+Monazam+Erfani%2C+and+James+Bailey%2E+2026%2E+Attention+in+space%3A+Functional+roles+of+vlm+heads+for+spatial+reasoning%2E)
30. Mohammad Reza Ghasemi Madani, Soyeon Caren Han, Shuo Yang, and Jey Han Lau. 2026. Inclusion-of-thoughts: Mitigating preference instability via purifying the decision space. Preprint, arXiv:2604.04944. — [arXiv:2604.04944](https://arxiv.org/abs/2604.04944) [find](https://scholar.google.com/scholar?q=Mohammad+Reza+Ghasemi+Madani%2C+Soyeon+Caren+Han%2C+Shuo+Yang%2C+and+Jey+Han+Lau%2E+2026%2E+Inclusion%2Dof%2Dthoughts%3A+Mitigating+preference+instability+via+purifying+the+decision+space%2E+Preprint%2C+arXiv%3A2604%2E04944%2E)
31. Zhenyu Ning, Guangda Liu, Qihao Jin, Wenchao Ding, Minyi Guo, and Jieru Zhao. 2025. Livevlm: Efficient online video understanding via streaming-oriented kv cache and retrieval. arXiv preprint arXiv:2505.15269. — [arXiv:2505.15269](https://arxiv.org/abs/2505.15269) [find](https://scholar.google.com/scholar?q=Zhenyu+Ning%2C+Guangda+Liu%2C+Qihao+Jin%2C+Wenchao+Ding%2C+Minyi+Guo%2C+and+Jieru+Zhao%2E+2025%2E+Livevlm%3A+Efficient+online+video+understanding+via+streaming%2Doriented+kv+cache+and+retrieval%2E+arXiv+preprint+arXiv%3A25)
32. Charles Packer, Sarah Wooders, Kevin Lin, Vivian Fang, Shishir G Patil, Ion Stoica, and Joseph E Gonzalez. 2023. Memgpt: Towards llms as operating systems. arXiv preprint arXiv:2310.08560. [find](https://scholar.google.com/scholar?q=Charles+Packer%2C+Sarah+Wooders%2C+Kevin+Lin%2C+Vivian+Fang%2C+Shishir+G+Patil%2C+Ion+Stoica%2C+and+Joseph+E+Gonzalez%2E+2023%2E+Memgpt%3A+Towards+llms+as+operating+systems%2E+arXiv+preprint+arXiv%3A2310%2E08560%2E)
33. Rui Qian, Shuangrui Ding, Xiaoyi Dong, Pan Zhang, Yuhang Zang, Yuhang Cao, Dahua Lin, and Jiaqi Wang. 2025. Dispider: Enabling video llms with active real-time interaction via disentangled perception, decision, and reaction. In Proceedings of the Computer Vision and Pattern Recognition Conference, p… [find](https://scholar.google.com/scholar?q=Rui+Qian%2C+Shuangrui+Ding%2C+Xiaoyi+Dong%2C+Pan+Zhang%2C+Yuhang+Zang%2C+Yuhang+Cao%2C+Dahua+Lin%2C+and+Jiaqi+Wang%2E+2025%2E+Dispider%3A+Enabling+video+llms+with+active+real%2Dtime+interaction+via+disentangled+perception%2C)
34. Aravinda S Rao, Marko Radanovic, Yuguang Liu, Songbo Hu, Yihai Fang, Kourosh Khoshelham, Marimuthu Palaniswami, and Tuan Ngo. 2022. Real-time monitoring of construction sites: Sensors, methods, and applications. Automation in construction, 136:104099. [find](https://scholar.google.com/scholar?q=Aravinda+S+Rao%2C+Marko+Radanovic%2C+Yuguang+Liu%2C+Songbo+Hu%2C+Yihai+Fang%2C+Kourosh+Khoshelham%2C+Marimuthu+Palaniswami%2C+and+Tuan+Ngo%2E+2022%2E+Real%2Dtime+monitoring+of+construction+sites%3A+Sensors%2C+methods%2C+and+ap)
35. Yuhao Shen, Tianyu Liu, Junyi Shen, Jinyang Wu, Quan Kong, Li Huan, and Cong Wang. 2026. Double: Breaking the acceleration limit via double retrieval speculative parallelism. arXiv preprint arXiv:2601.05524. [find](https://scholar.google.com/scholar?q=Yuhao+Shen%2C+Tianyu+Liu%2C+Junyi+Shen%2C+Jinyang+Wu%2C+Quan+Kong%2C+Li+Huan%2C+and+Cong+Wang%2E+2026%2E+Double%3A+Breaking+the+acceleration+limit+via+double+retrieval+speculative+parallelism%2E+arXiv+preprint+arXiv%3A2601)
36. Enxin Song, Wenhao Chai, Guanhong Wang, Yucheng Zhang, Haoyang Zhou, Feiyang Wu, Haozhe Chi, Xun Guo, Tian Ye, Yanting Zhang, and 1 others. 2024. Moviechat: From dense token to sparse memory for long video understanding. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recogn… [find](https://scholar.google.com/scholar?q=Enxin+Song%2C+Wenhao+Chai%2C+Guanhong+Wang%2C+Yucheng+Zhang%2C+Haoyang+Zhou%2C+Feiyang+Wu%2C+Haozhe+Chi%2C+Xun+Guo%2C+Tian+Ye%2C+Yanting+Zhang%2C+and+1+others%2E+2024%2E+Moviechat%3A+From+dense+token+to+sparse+memory+for+long+)
37. Xi Tang, Jihao Qiu, Lingxi Xie, Yunjie Tian, Jianbin Jiao, and Qixiang Ye. 2025. Adaptive keyframe sampling for long video understanding. In Proceedings of the Computer Vision and Pattern Recognition Conference, pages 29118–29128. [find](https://scholar.google.com/scholar?q=Xi+Tang%2C+Jihao+Qiu%2C+Lingxi+Xie%2C+Yunjie+Tian%2C+Jianbin+Jiao%2C+and+Qixiang+Ye%2E+2025%2E+Adaptive+keyframe+sampling+for+long+video+understanding%2E+In+Proceedings+of+the+Computer+Vision+and+Pattern+Recognition+)
38. Gemini Team, Petko Georgiev, Ving Ian Lei, Ryan Burnell, Libin Bai, Anmol Gulati, Garrett Tanzer, Damien Vincent, Zhufeng Pan, Shibo Wang, and 1 others. 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/). arXiv preprint arXiv:2403.05530.
39. Haibo Wang, Bo Feng, Zhengfeng Lai, Mingze Xu, Shiyu Li, Weifeng Ge, Afshin Dehghan, Meng Cao, and Ping Huang. 2025a. Streambridge: Turning your offline video large language model into a proactive streaming assistant. arXiv preprint arXiv:2505.05467. — [arXiv:2505.05467](https://arxiv.org/abs/2505.05467) [find](https://scholar.google.com/scholar?q=Haibo+Wang%2C+Bo+Feng%2C+Zhengfeng+Lai%2C+Mingze+Xu%2C+Shiyu+Li%2C+Weifeng+Ge%2C+Afshin+Dehghan%2C+Meng+Cao%2C+and+Ping+Huang%2E+2025a%2E+Streambridge%3A+Turning+your+offline+video+large+language+model+into+a+proactive+str)
40. Mengyue Wang, Shuo Chen, Kristian Kersting, Volker Tresp, and Yunpu Ma. 2025b. Metok: Multi-stage event-based token compression for efficient long video understanding. arXiv preprint arXiv:2506.02850. [find](https://scholar.google.com/scholar?q=Mengyue+Wang%2C+Shuo+Chen%2C+Kristian+Kersting%2C+Volker+Tresp%2C+and+Yunpu+Ma%2E+2025b%2E+Metok%3A+Multi%2Dstage+event%2Dbased+token+compression+for+efficient+long+video+understanding%2E+arXiv+preprint+arXiv%3A2506%2E02850%2E)
41. Tongxi Wang. 2026. [Fbs: Modeling native parallel reading inside a transformer](https://md.research.elamur.ai/free/en/papers/wang-2026-fbs-modeling-native-parallel-reading/). arXiv preprint arXiv:2601.21708.
42. Xudong Wang, Chaoning Zhang, Jiaquan Zhang, Chenghao Li, Qigan Sun, Sung-Ho Bae, Peng Wang, Ning Xie, Jie Zou, Yang Yang, and 1 others. 2026. Efficient and interpretable multi-agent llm routing via ant colony optimization. arXiv preprint arXiv:2603.12933. — [arXiv:2603.12933](https://arxiv.org/abs/2603.12933) [find](https://scholar.google.com/scholar?q=Xudong+Wang%2C+Chaoning+Zhang%2C+Jiaquan+Zhang%2C+Chenghao+Li%2C+Qigan+Sun%2C+Sung%2DHo+Bae%2C+Peng+Wang%2C+Ning+Xie%2C+Jie+Zou%2C+Yang+Yang%2C+and+1+others%2E+2026%2E+Efficient+and+interpretable+multi%2Dagent+llm+routing+via+an)
43. Yu Wang, Yifan Gao, Xiusi Chen, Haoming Jiang, Shiyang Li, Jingfeng Yang, Qingyu Yin, Zheng Li, Xian Li, Bing Yin, Jingbo Shang, and Julian McAuley. 2024. [Memoryllm: Towards self-updatable large language models](https://md.research.elamur.ai/free/en/papers/wang-2024-memoryllm-towards-self-updatable-large/). Preprint, arXiv:2402.04624.
44. Zichen Wen, Yifeng Gao, Shaobo Wang, Junyuan Zhang, Qintong Zhang, Weijia Li, Conghui He, and Linfeng Zhang. 2025. [Stop looking for important tokens in multimodal language models: Duplication matters more](https://md.research.elamur.ai/free/en/papers/wen-2025-stop-looking-important-tokens-multimodal/). arXiv preprint arXiv:2502.11494.
45. Jinyang Wu, Shuo Yang, Changpeng Yang, Yuhao Shen, Shuai Zhang, Zhengqi Wen, and Jianhua Tao. 2026. [Spark: Strategic policy-aware exploration via dynamic branching for long-horizon agentic learning](https://md.research.elamur.ai/free/en/papers/wu-2026-spark-strategic-policy-aware-exploration/). arXiv preprint arXiv:2601.20209.
46. Haomiao Xiong, Zongxin Yang, Jiazuo Yu, Yunzhi Zhuge, Lu Zhang, Jiawen Zhu, and Huchuan Lu. 2025. Streaming video understanding and multi-round interaction with memory-enhanced knowledge. arXiv preprint arXiv:2501.13468. — [arXiv:2501.13468](https://arxiv.org/abs/2501.13468) [find](https://scholar.google.com/scholar?q=Haomiao+Xiong%2C+Zongxin+Yang%2C+Jiazuo+Yu%2C+Yunzhi+Zhuge%2C+Lu+Zhang%2C+Jiawen+Zhu%2C+and+Huchuan+Lu%2E+2025%2E+Streaming+video+understanding+and+multi%2Dround+interaction+with+memory%2Denhanced+knowledge%2E+arXiv+prepri)
47. Haolin Yang, Feilong Tang, Lingxiao Zhao, Xiang An, Ming Hu, Huifa Li, Xinlin Zhuang, Yifan Lu, Xiaofeng Zhang, Abdalla Swikir, and 1 others. 2025a. Streamagent: Towards anticipatory agents for streaming video understanding. arXiv preprint arXiv:2508.01875. — [arXiv:2508.01875](https://arxiv.org/abs/2508.01875) [find](https://scholar.google.com/scholar?q=Haolin+Yang%2C+Feilong+Tang%2C+Lingxiao+Zhao%2C+Xiang+An%2C+Ming+Hu%2C+Huifa+Li%2C+Xinlin+Zhuang%2C+Yifan+Lu%2C+Xiaofeng+Zhang%2C+Abdalla+Swikir%2C+and+1+others%2E+2025a%2E+Streamagent%3A+Towards+anticipatory+agents+for+stream)
48. Shuo Yang, Caren Han, Siwen Luo, and Eduard Hovy. 2025b. Magic-vqa: Multimodal and grounded inference with commonsense knowledge for visual question answering. In Findings of the Association for Computational Linguistics: ACL 2025, pages 16967–16986. [find](https://scholar.google.com/scholar?q=Shuo+Yang%2C+Caren+Han%2C+Siwen+Luo%2C+and+Eduard+Hovy%2E+2025b%2E+Magic%2Dvqa%3A+Multimodal+and+grounded+inference+with+commonsense+knowledge+for+visual+question+answering%2E+In+Findings+of+the+Association+for+Compu)
49. Shuo Yang, Soyeon Caren Han, Yihao Ding, Shuhe Wang, and Eduard Hoy. 2026a. Tooltree: Efficient llm agent tool planning via dual-feedback monte carlo tree search and bidirectional pruning. arXiv preprint arXiv:2603.12740. — [arXiv:2603.12740](https://arxiv.org/abs/2603.12740) [find](https://scholar.google.com/scholar?q=Shuo+Yang%2C+Soyeon+Caren+Han%2C+Yihao+Ding%2C+Shuhe+Wang%2C+and+Eduard+Hoy%2E+2026a%2E+Tooltree%3A+Efficient+llm+agent+tool+planning+via+dual%2Dfeedback+monte+carlo+tree+search+and+bidirectional+pruning%2E+arXiv+prepr)
50. Shuo Yang, Soyeon Caren Han, Xueqi Ma, Yan Li, Mohammad Reza Ghasemi Madani, and Eduard Hovy. 2026b. [Evotool: Self-evolving tool-use policy optimization in llm agents via blame-aware mutation and diversity-aware selection](https://md.research.elamur.ai/free/en/papers/yang-2026-evotool-self-evolving-tool-use/). arXiv preprint arXiv:2603.04900.
51. Yanlai Yang, Zhuokai Zhao, Satya Narayan Shukla, Aashu Singh, Shlok Kumar Mishra, Lizhu Zhang, and Mengye Ren. 2025c. Streammem: Query-agnostic kv cache memory for streaming video understanding. arXiv preprint arXiv:2508.15717. — [arXiv:2508.15717](https://arxiv.org/abs/2508.15717) [find](https://scholar.google.com/scholar?q=Yanlai+Yang%2C+Zhuokai+Zhao%2C+Satya+Narayan+Shukla%2C+Aashu+Singh%2C+Shlok+Kumar+Mishra%2C+Lizhu+Zhang%2C+and+Mengye+Ren%2E+2025c%2E+Streammem%3A+Query%2Dagnostic+kv+cache+memory+for+streaming+video+understanding%2E+arXiv)
52. Linli Yao, Yicheng Li, Yuancheng Wei, Lei Li, Shuhuai Ren, Yuanxin Liu, Kun Ouyang, Lean Wang, Shicheng Li, Sida Li, and 1 others. 2025a. Timechat-online: 80% visual tokens are naturally redundant in streaming videos. In Proceedings of the 33rd ACM International Conference on Multimedia, pages 10807… [find](https://scholar.google.com/scholar?q=Linli+Yao%2C+Yicheng+Li%2C+Yuancheng+Wei%2C+Lei+Li%2C+Shuhuai+Ren%2C+Yuanxin+Liu%2C+Kun+Ouyang%2C+Lean+Wang%2C+Shicheng+Li%2C+Sida+Li%2C+and+1+others%2E+2025a%2E+Timechat%2Donline%3A+80%25+visual+tokens+are+naturally+redundant+in+)
53. Yiqun Yao, Naitong Yu, Xiang Li, Xin Jiang, Xuezhi Fang, Wenjia Ma, Xuying Meng, Jing Li, Aixin Sun, and Yequan Wang. 2025b. Egomem: Lifelong memory agent for full-duplex omnimodal models. arXiv preprint arXiv:2509.11914. — [arXiv:2509.11914](https://arxiv.org/abs/2509.11914) [find](https://scholar.google.com/scholar?q=Yiqun+Yao%2C+Naitong+Yu%2C+Xiang+Li%2C+Xin+Jiang%2C+Xuezhi+Fang%2C+Wenjia+Ma%2C+Xuying+Meng%2C+Jing+Li%2C+Aixin+Sun%2C+and+Yequan+Wang%2E+2025b%2E+Egomem%3A+Lifelong+memory+agent+for+full%2Dduplex+omnimodal+models%2E+arXiv+prepr)
54. Hongli Yu, Tinghong Chen, Jiangtao Feng, Jiangjie Chen, Weinan Dai, Qiying Yu, Ya-Qin Zhang, Wei-Ying Ma, Jingjing Liu, Mingxuan Wang, and 1 others. 2025a. Memagent: Reshaping long-context llm with multi-conv rl-based memory agent. arXiv preprint arXiv:2507.02259. — [arXiv:2507.02259](https://arxiv.org/abs/2507.02259) [find](https://scholar.google.com/scholar?q=Hongli+Yu%2C+Tinghong+Chen%2C+Jiangtao+Feng%2C+Jiangjie+Chen%2C+Weinan+Dai%2C+Qiying+Yu%2C+Ya%2DQin+Zhang%2C+Wei%2DYing+Ma%2C+Jingjing+Liu%2C+Mingxuan+Wang%2C+and+1+others%2E+2025a%2E+Memagent%3A+Reshaping+long%2Dcontext+llm+with+mu)
55. Jin Xu, Zhifang Guo, Jinzheng He, Hangrui Hu, Ting He, Shuai Bai, Keqin Chen, Jialin Wang, Yang Fan, Kai Dang, and 1 others. 2025a. Qwen2. 5-omni technical report. arXiv preprint arXiv:2503.20215. — [Qwen2.5-Omni Technical Report](https://md.research.elamur.ai/free/en/papers/xu-2025-qwen2-5-omni-technical/)
56. Xinlei Yu, Chengming Xu, Guibin Zhang, Zhangquan Chen, Yudong Zhang, Yongbo He, Peng-Tao Jiang, Jiangning Zhang, Xiaobin Hu, and Shuicheng Yan. 2025b. Vismem: Latent vision memory unlocks potential of vision-language models. arXiv preprint arXiv:2511.11007. — [arXiv:2511.11007](https://arxiv.org/abs/2511.11007) [find](https://scholar.google.com/scholar?q=Xinlei+Yu%2C+Chengming+Xu%2C+Guibin+Zhang%2C+Zhangquan+Chen%2C+Yudong+Zhang%2C+Yongbo+He%2C+Peng%2DTao+Jiang%2C+Jiangning+Zhang%2C+Xiaobin+Hu%2C+and+Shuicheng+Yan%2E+2025b%2E+Vismem%3A+Latent+vision+memory+unlocks+potential+of)
57. Ruyi Xu, Guangxuan Xiao, Yukang Chen, Liuning He, Kelly Peng, Yao Lu, and Song Han. 2025b. Stream-ingvlm: Real-time understanding for infinite video streams. arXiv preprint arXiv:2510.09608. [find](https://scholar.google.com/scholar?q=Ruyi+Xu%2C+Guangxuan+Xiao%2C+Yukang+Chen%2C+Liuning+He%2C+Kelly+Peng%2C+Yao+Lu%2C+and+Song+Han%2E+2025b%2E+Stream%2Dingvlm%3A+Real%2Dtime+understanding+for+infinite+video+streams%2E+arXiv+preprint+arXiv%3A2510%2E09608%2E)
58. Ekim Yurtsever, Jacob Lambert, Alexander Carballo, and Kazuya Takeda. 2020. A survey of autonomous driving: Common practices and emerging technologies. IEEE access, 8:58443–58469. [find](https://scholar.google.com/scholar?q=Ekim+Yurtsever%2C+Jacob+Lambert%2C+Alexander+Carballo%2C+and+Kazuya+Takeda%2E+2020%2E+A+survey+of+autonomous+driving%3A+Common+practices+and+emerging+technologies%2E+IEEE+access%2C+8%3A58443%E2%80%9358469%2E)
59. Xiangyu Zeng, Kefan Qiu, Qingyu Zhang, Xinhao Li, Jing Wang, Jiaxin Li, Ziang Yan, Kun Tian, Meng Tian, Xinhai Zhao, and 1 others. 2025. Streamforest: Efficient online video understanding with persistent event memory. arXiv preprint arXiv:2509.24871. — [arXiv:2509.24871](https://arxiv.org/abs/2509.24871) [find](https://scholar.google.com/scholar?q=Xiangyu+Zeng%2C+Kefan+Qiu%2C+Qingyu+Zhang%2C+Xinhao+Li%2C+Jing+Wang%2C+Jiaxin+Li%2C+Ziang+Yan%2C+Kun+Tian%2C+Meng+Tian%2C+Xinhai+Zhao%2C+and+1+others%2E+2025%2E+Streamforest%3A+Efficient+online+video+understanding+with+persist)
60. Yu Zeng, Wenxuan Huang, Zhen Fang, Shuang Chen, Yufan Shen, Yishuo Cai, Xiaoman Wang, Zhenfei Yin, Lin Chen, Zehui Chen, and 1 others. 2026. Vision-deepresearch benchmark: Rethinking visual and textual search for multimodal large language models. arXiv preprint arXiv:2602.02185. — [arXiv:2602.02185](https://arxiv.org/abs/2602.02185) [find](https://scholar.google.com/scholar?q=Yu+Zeng%2C+Wenxuan+Huang%2C+Zhen+Fang%2C+Shuang+Chen%2C+Yufan+Shen%2C+Yishuo+Cai%2C+Xiaoman+Wang%2C+Zhenfei+Yin%2C+Lin+Chen%2C+Zehui+Chen%2C+and+1+others%2E+2026%2E+Vision%2Ddeepresearch+benchmark%3A+Rethinking+visual+and+textua)
61. Guibin Zhang, Muxin Fu, and Shuicheng Yan. 2025. Memgen: Weaving generative latent memory for self-evolving agents. arXiv preprint arXiv:2509.24704. — [arXiv:2509.24704](https://arxiv.org/abs/2509.24704) [find](https://scholar.google.com/scholar?q=Guibin+Zhang%2C+Muxin+Fu%2C+and+Shuicheng+Yan%2E+2025%2E+Memgen%3A+Weaving+generative+latent+memory+for+self%2Devolving+agents%2E+arXiv+preprint+arXiv%3A2509%2E24704%2E+%E2%80%94+%5BarXiv%3A2509%2E24704%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2509%2E247)
62. Haoji Zhang, Yiqin Wang, Yansong Tang, Yong Liu, Jiashi Feng, Jifeng Dai, and Xiaojie Jin. 2024. Flash-vstream: Memory-based real-time understanding for long video streams. arXiv preprint arXiv:2406.08085. — [arXiv:2406.08085](https://arxiv.org/abs/2406.08085) [find](https://scholar.google.com/scholar?q=Haoji+Zhang%2C+Yiqin+Wang%2C+Yansong+Tang%2C+Yong+Liu%2C+Jiashi+Feng%2C+Jifeng+Dai%2C+and+Xiaojie+Jin%2E+2024%2E+Flash%2Dvstream%3A+Memory%2Dbased+real%2Dtime+understanding+for+long+video+streams%2E+arXiv+preprint+arXiv%3A2406%2E0)
63. Jiaquan Zhang, Qigan Sun, Chaoning Zhang, Xudong Wang, Zhenzhen Huang, Yitian Zhou, Pengcheng Zheng, Chi lok Andy Tai, Sung-Ho Bae, Zeyu Ma, Caiyan Qin, Jinyu Guo, Yang Yang, and Hengtao Shen. 2026a. Tda-rc: Task-driven alignment for knowledge-based reasoning chains in large language models. Preprin… — [arXiv:2604.04942](https://arxiv.org/abs/2604.04942) [find](https://scholar.google.com/scholar?q=Jiaquan+Zhang%2C+Qigan+Sun%2C+Chaoning+Zhang%2C+Xudong+Wang%2C+Zhenzhen+Huang%2C+Yitian+Zhou%2C+Pengcheng+Zheng%2C+Chi+lok+Andy+Tai%2C+Sung%2DHo+Bae%2C+Zeyu+Ma%2C+Caiyan+Qin%2C+Jinyu+Guo%2C+Yang+Yang%2C+and+Hengtao+Shen%2E+2026a%2E+)
64. Jiaquan Zhang, Chaoning Zhang, Shuxu Chen, Yibei Liu, Chenghao Li, Qigan Sun, Shuai Yuan, Fach-rina Dewi Puspitasari, Dongshen Han, Guoqing Wang, and 1 others. 2026b. Text summarization via global structure awareness. arXiv preprint arXiv:2602.09821. — [arXiv:2602.09821](https://arxiv.org/abs/2602.09821) [find](https://scholar.google.com/scholar?q=Jiaquan+Zhang%2C+Chaoning+Zhang%2C+Shuxu+Chen%2C+Yibei+Liu%2C+Chenghao+Li%2C+Qigan+Sun%2C+Shuai+Yuan%2C+Fach%2Drina+Dewi+Puspitasari%2C+Dongshen+Han%2C+Guoqing+Wang%2C+and+1+others%2E+2026b%2E+Text+summarization+via+global+str)
65. Jiaquan Zhang, Chaoning Zhang, Shuxu Chen, Xudong Wang, Zhenzhen Huang, Pengcheng Zheng, Shuai Yuan, Sheng Zheng, Qigan Sun, Jie Zou, and 1 others. 2026c. Learning global hypothesis space for enhancing synergistic reasoning chain. arXiv preprint arXiv:2602.09794. — [arXiv:2602.09794](https://arxiv.org/abs/2602.09794) [find](https://scholar.google.com/scholar?q=Jiaquan+Zhang%2C+Chaoning+Zhang%2C+Shuxu+Chen%2C+Xudong+Wang%2C+Zhenzhen+Huang%2C+Pengcheng+Zheng%2C+Shuai+Yuan%2C+Sheng+Zheng%2C+Qigan+Sun%2C+Jie+Zou%2C+and+1+others%2E+2026c%2E+Learning+global+hypothesis+space+for+enhancin)
66. Zijian Zhou, Ao Qu, Zhaoxuan Wu, Sunghwan Kim, Alok Prakash, Daniela Rus, Jinhua Zhao, Bryan Kian Hsiang Low, and Paul Pu Liang. 2025. Mem1: Learning to synergize memory and reasoning for efficient long-horizon agents. arXiv preprint arXiv:2506.15841. — [arXiv:2506.15841](https://arxiv.org/abs/2506.15841) [find](https://scholar.google.com/scholar?q=Zijian+Zhou%2C+Ao+Qu%2C+Zhaoxuan+Wu%2C+Sunghwan+Kim%2C+Alok+Prakash%2C+Daniela+Rus%2C+Jinhua+Zhao%2C+Bryan+Kian+Hsiang+Low%2C+and+Paul+Pu+Liang%2E+2025%2E+Mem1%3A+Learning+to+synergize+memory+and+reasoning+for+efficient+lo)
67. Jialong Zuo, Yongtai Deng, Lingdong Kong, Jingkang Yang, Rui Jin, Yiwei Zhang, Nong Sang, Liang Pan, Ziwei Liu, and Changxin Gao. 2025. Videolucy: Deep memory backtracking for long video understanding. arXiv preprint arXiv:2510.12422. — [arXiv:2510.12422](https://arxiv.org/abs/2510.12422) [find](https://scholar.google.com/scholar?q=Jialong+Zuo%2C+Yongtai+Deng%2C+Lingdong+Kong%2C+Jingkang+Yang%2C+Rui+Jin%2C+Yiwei+Zhang%2C+Nong+Sang%2C+Liang+Pan%2C+Ziwei+Liu%2C+and+Changxin+Gao%2E+2025%2E+Videolucy%3A+Deep+memory+backtracking+for+long+video+understanding)

*Updated 31 October 2026*