---
title: "PACE — paper by Wei et al. (2026) — summary and ideas"
description: "LLM agents working on tasks with hundreds or thousands of steps hit a trade-off. 47 references."
authors: ["Lei Wei", "Xiao Peng", "Tt", "Guannan Zhang", "Chenhao Jiang", "Hongyu Li", "Lanbo Lin", "Yuanwu Xu", "Jiayao Liu", "Kesu Wang", "Bin Wang"]
year: 2026
venue: "Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)"
source: "https://aclanthology.org/2026.acl-long.1252/"
doi: "10.18653/v1/2026.acl-long.1252"
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/wei-2026-pace-predictive-adaptive-context-extraction/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/wei-2026-pace-predictive-adaptive-context-extraction/)

[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/38/) / PACE: Predictive Adaptive Context Extraction for Long-Horizon LLM Agents

# PACE: Predictive Adaptive Context Extraction for Long-Horizon LLM Agents

**Authors:** Lei Wei, Xiao Peng, Tt, Guannan Zhang, Chenhao Jiang, [Hongyu Li](https://md.research.elamur.ai/free/en/authors/hongyu-li/), Lanbo Lin, Yuanwu Xu, Jiayao Liu, Kesu Wang and [Bin Wang](https://md.research.elamur.ai/free/en/authors/bin-wang/) · **Year:** 2026 · **Venue:** [Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)](https://md.research.elamur.ai/free/en/venues/acl/) ([ACL 2026](https://md.research.elamur.ai/free/en/venues/acl/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.acl-long.1252/) · [PDF](https://aclanthology.org/2026.acl-long.1252.pdf) · [DOI 10.18653/v1/2026.acl-long.1252](https://doi.org/10.18653/v1/2026.acl-long.1252) · [OpenAlex](https://openalex.org/W7166868320)

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

## Summary
LLM agents working on tasks with hundreds or thousands of steps hit a trade-off. Keeping the whole history fills the context window and forces blunt truncation. Summarizing at every step loses details too early. PACE (Lei Wei et al., Alibaba / Peking University, ACL 2026) treats context construction as a Next Step Prediction problem. Each past interaction chunk is stored externally in four versions: full text, detailed summary, brief summary and placeholder. A lightweight embedding-based scorer estimates how useful each chunk is for the upcoming action. Each chunk's score then sets the version that enters the prompt. Thresholds tighten automatically as the history grows, which the authors call adaptive pressure. No fine-tuning of the agent is required. Across six web/research benchmarks and four models, PACE raises success rates, with the largest gains on harder tasks. In a stress test it keeps an agent working for thousands of steps. This makes previously unmanageable long-horizon agent workloads practical.

## Key points
- **Architecture:** a Main Agent plus four supporting components.
  - An External Memory Store holds the full history.
  - A Representation Generator (e.g., Gemini 2.5 Flash-Lite) produces summaries asynchronously.
  - An Attention Scorer (local BGE-M3 dense retriever) rates relevance by semantic similarity.
  - A Context Builder assembles the prompt; the two most recent chunks (N = 2) always stay in full.
- **Benchmarks:** evaluation covered GAIA, WebWalkerQA, WideSearch, xbench-DeepResearch, BrowseComp and its Chinese counterpart BrowseComp-ZH. Results hold across languages, including the Chinese benchmark.
- **GAIA results with Claude-4-Sonnet:**
  - Level 2: PACE scores 71.2%, versus 59.1% for ReAct and 63.6% for the Folding Agent.
  - Level 3: PACE scores 63.2%, versus 42.1% for ReAct and 52.6% for the Folding Agent.
  - Level 1: the methods differ by less than 5 points.
- **Stress test setup:** all GAIA Level 2 and Level 3 questions were chained into one session, run with Gemini 2.5 Pro under a 256K-token budget.
- **Stress test results (steps before overflow):**
  - ReAct: 74
  - Summary Agent: 233
  - Folding Agent: 954
  - PACE with λ = 0.5: 2,776
  - PACE with λ = 1.0: 4,897, i.e., 66.2× ReAct and 5.1× the Folding Agent.
- **Limitations:** semantic similarity is only an approximation of true relevance, and the summarizer is fixed rather than adapted to each task.

*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

- [Peking University](https://md.research.elamur.ai/free/en/universities/peking-university/) — University, Beijing, China · 244 works · 39,359 citations
- [Alibaba Group](https://md.research.elamur.ai/free/en/companies/alibaba-group/) — Company, Hangzhou, China · 168 works · 15,386 citations

📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 16,194 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 16,039 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 15,891 works

## Cite

Cite as: Lei Wei, Xiao Peng, Tt, Guannan Zhang, Chenhao Jiang, Hongyu Li, Lanbo Lin, Yuanwu Xu, Jiayao Liu, Kesu Wang and Bin Wang. 2026. PACE: Predictive Adaptive Context Extraction for Long-Horizon LLM Agents. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).

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

```bibtex
@inproceedings{wei2026pace,
  title = {{PACE: Predictive Adaptive Context Extraction for Long-Horizon LLM Agents}},
  author = {Lei Wei, Xiao Peng, Tt, Guannan Zhang, Chenhao Jiang, Hongyu Li, Lanbo Lin, Yuanwu Xu, Jiayao Liu, Kesu Wang and Bin Wang},
  booktitle = {Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2026},
  doi = {10.18653/v1/2026.acl-long.1252},
  url = {https://doi.org/10.18653/v1/2026.acl-long.1252}
}
```

- [← previous P-QuASAR: A Unified Probabilistic Framework for Holistic Patent Quality Assessment and Refinement](https://md.research.elamur.ai/free/en/papers/song-2026-p-quasar-unified-probabilistic-framework/)
- [next → PAIR: A Pilot Dataset for Dual Perspective-based Video-Grounded Dialogue and Reconciliation](https://md.research.elamur.ai/free/en/papers/watson-2026-pair-pilot-dataset-dual-perspective/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/38/)

## References

47 references, 20 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Pranshav Gajjar, Cong Shen, and Vijay K Shah. 2025. Tele-llm-hub: Building context-aware multi-agent llm systems for telecom networks. Preprint, arXiv:2511.09087. — [arXiv:2511.09087](https://arxiv.org/abs/2511.09087) [find](https://scholar.google.com/scholar?q=Pranshav+Gajjar%2C+Cong+Shen%2C+and+Vijay+K+Shah%2E+2025%2E+Tele%2Dllm%2Dhub%3A+Building+context%2Daware+multi%2Dagent+llm+systems+for+telecom+networks%2E+Preprint%2C+arXiv%3A2511%2E09087%2E+%E2%80%94+%5BarXiv%3A2511%2E09087%5D%28https%3A%2F%2Farxiv%2Eor)
2. Yushi Bai, Xin Lv, Jiajie Zhang, Yuze He, Ji Qi, Lei Hou, Jie Tang, Yuxiao Dong, and Juanzi Li. 2024. [Longalign: A recipe for long context alignment of large language models](https://md.research.elamur.ai/free/en/papers/bai-2024-longalign-recipe-long-context/). In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 1376–1395.
3. Peter Belcak, Greg Heinrich, Shizhe Diao, Yonggan Fu, Xin Dong, Saurav Muralidharan, Yingyan Celine Lin, and Pavlo Molchanov. 2025. Small language models are the future of agentic ai. Preprint, arXiv:2506.02153. [find](https://scholar.google.com/scholar?q=Peter+Belcak%2C+Greg+Heinrich%2C+Shizhe+Diao%2C+Yonggan+Fu%2C+Xin+Dong%2C+Saurav+Muralidharan%2C+Yingyan+Celine+Lin%2C+and+Pavlo+Molchanov%2E+2025%2E+Small+language+models+are+the+future+of+agentic+ai%2E+Preprint%2C+arXiv%3A)
4. Maciej Besta, Nils Blach, Ales Kubicek, Robert Gerstenberger, Michal Podstawski, Lukas Gianinazzi, Joanna Gajda, Tomasz Lehmann, Hubert Niewiadomski, Piotr Nyczyk, and 1 others. 2024. Graph of thoughts: Solving elaborate problems with large language models. Proceedings of the AAAI Conference on Arti… [find](https://scholar.google.com/scholar?q=Maciej+Besta%2C+Nils+Blach%2C+Ales+Kubicek%2C+Robert+Gerstenberger%2C+Michal+Podstawski%2C+Lukas+Gianinazzi%2C+Joanna+Gajda%2C+Tomasz+Lehmann%2C+Hubert+Niewiadomski%2C+Piotr+Nyczyk%2C+and+1+others%2E+2024%2E+Graph+of+thought)
5. Chi-Min Chan, Weize Chen, Yusheng Su, Jianxuan Yu, Wei Xue, Shanghang Zhang, Jie Fu, and Zhiyuan DeepSeek-AI, Aixin Liu, Bei Feng, Bing Xue, Bingxuan Wang, Bochao Wu, Chengda Lu, Chenggang Zhao, Chengqi Deng, Chenyu Zhang, Chong Ruan, Damai Dai, Daya Guo, Dejian Yang, Deli Chen, Dongjie Ji, Erhang L… [find](https://scholar.google.com/scholar?q=Chi%2DMin+Chan%2C+Weize+Chen%2C+Yusheng+Su%2C+Jianxuan+Yu%2C+Wei+Xue%2C+Shanghang+Zhang%2C+Jie+Fu%2C+and+Zhiyuan+DeepSeek%2DAI%2C+Aixin+Liu%2C+Bei+Feng%2C+Bing+Xue%2C+Bingxuan+Wang%2C+Bochao+Wu%2C+Chengda+Lu%2C+Chenggang+Zhao%2C+Cheng)
6. Tianqing Fang, Hongming Zhang, Zhisong Zhang, Kaixin Ma, Wenhao Yu, Haitao Mi, and Dong Yu. 2025. [Webevolver: Enhancing web agent self-improvement with co-evolving world model](https://md.research.elamur.ai/free/en/papers/fang-2025-webevolver-enhancing-web-agent-self/). In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 8970– 8986.
7. Mengkang Hu, Tianxing Chen, Qiguang Chen, Yao Mu, Wenqi Shao, and Ping Luo. 2025a. [HiAgent: Hierarchical working memory management for solving long-horizon agent tasks with large language model](https://md.research.elamur.ai/free/en/papers/hu-2025-hiagent-hierarchical-working-memory-management/). In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Lon…
8. Xueyu Hu, Tao Xiong, Biao Yi, Zishu Wei, Ruixuan Xiao, Yurun Chen, Jiasheng Ye, Meiling Tao, Xiangxin Zhou, Ziyu Zhao, Yuhuai Li, Shengze Xu, Shenzhi Wang, Xinchen Xu, Shuofei Qiao, Zhaokai Wang, Kun Kuang, Tieyong Zeng, Liang Wang, and 10 others. 2025b. [OS agents: A survey on MLLM-based agents for…](https://md.research.elamur.ai/free/en/papers/hu-2025-os-agents-survey-mllm-based/)
9. Huiqiang Jiang, Qianhui Wu, Chin-Yew Lin, Yuqing Yang, and Lili Qiu. 2023. [Llmlingua: Compressing prompts for accelerated inference of large language models](https://md.research.elamur.ai/free/en/papers/jiang-2023-llmlingua-compressing-prompts-accelerated-inference/). Preprint, arXiv:2310.05736.
10. Minki Kang, Wei-Ning Chen, Dongge Han, Huseyin A. Inan, Lukas Wutschitz, Yanzhi Chen, Robert Sim, and Saravan Rajmohan. 2025. Acon: Optimizing context compression for long-horizon llm agents. Preprint, arXiv:2510.00615. — [arXiv:2510.00615](https://arxiv.org/abs/2510.00615) [find](https://scholar.google.com/scholar?q=Minki+Kang%2C+Wei%2DNing+Chen%2C+Dongge+Han%2C+Huseyin+A%2E+Inan%2C+Lukas+Wutschitz%2C+Yanzhi+Chen%2C+Robert+Sim%2C+and+Saravan+Rajmohan%2E+2025%2E+Acon%3A+Optimizing+context+compression+for+long%2Dhorizon+llm+agents%2E+Preprint)
11. Woosuk Kwon. 2025. vLLM: An Efficient Inference Engine for Large Language Models. Ph.D. thesis, UC Berkeley. [find](https://scholar.google.com/scholar?q=Woosuk+Kwon%2E+2025%2E+vLLM%3A+An+Efficient+Inference+Engine+for+Large+Language+Models%2E+Ph%2ED%2E+thesis%2C+UC+Berkeley%2E)
12. Guohao Li, Hasan Hammoud, Hani Itani, Dmitrii Khizbullin, and Bernard Ghanem. 2023. [Camel: Communicative agents for" mind" exploration of large language model society](https://md.research.elamur.ai/free/en/papers/li-2023-camel-communicative-agents-mind/). Advances in neural information processing systems, 36:51991–52008.
13. Kuan Li, Zhongwang Zhang, Huifeng Yin, Liwen Zhang, Litu Ou, Jialong Wu, Wenbiao Yin, Baixuan Li, Zhengwei Tao, Xinyu Wang, Weizhou Shen, Junkai Zhang, Dingchu Zhang, Xixi Wu, Yong Jiang, Ming Yan, Pengjun Xie, Fei Huang, and Jingren Zhou. 2025a. Websailor: Navigating super-human reasoning for web a… [find](https://scholar.google.com/scholar?q=Kuan+Li%2C+Zhongwang+Zhang%2C+Huifeng+Yin%2C+Liwen+Zhang%2C+Litu+Ou%2C+Jialong+Wu%2C+Wenbiao+Yin%2C+Baixuan+Li%2C+Zhengwei+Tao%2C+Xinyu+Wang%2C+Weizhou+Shen%2C+Junkai+Zhang%2C+Dingchu+Zhang%2C+Xixi+Wu%2C+Yong+Jiang%2C+Ming+Yan%2C+Pe)
14. Mo Li, L. H. Xu, Qitai Tan, Long Ma, Ting Cao, and Yunxin Liu. 2025b. Sculptor: Empowering llms with cognitive agency via active context management. Preprint, arXiv:2508.04664. — [arXiv:2508.04664](https://arxiv.org/abs/2508.04664) [find](https://scholar.google.com/scholar?q=Mo+Li%2C+L%2E+H%2E+Xu%2C+Qitai+Tan%2C+Long+Ma%2C+Ting+Cao%2C+and+Yunxin+Liu%2E+2025b%2E+Sculptor%3A+Empowering+llms+with+cognitive+agency+via+active+context+management%2E+Preprint%2C+arXiv%3A2508%2E04664%2E+%E2%80%94+%5BarXiv%3A2508%2E04664%5D%28ht)
15. Bin Liu, Yanjie Zhao, Guoai Xu, and Haoyu Wang. 2025a. Llm agents for automated web vulnerability reproduction: Are we there yet? arXiv preprint arXiv:2510.14700. — [arXiv:2510.14700](https://arxiv.org/abs/2510.14700) [find](https://scholar.google.com/scholar?q=Bin+Liu%2C+Yanjie+Zhao%2C+Guoai+Xu%2C+and+Haoyu+Wang%2E+2025a%2E+Llm+agents+for+automated+web+vulnerability+reproduction%3A+Are+we+there+yet%3F+arXiv+preprint+arXiv%3A2510%2E14700%2E+%E2%80%94+%5BarXiv%3A2510%2E14700%5D%28https%3A%2F%2Farxiv%2Eor)
16. Nelson F Liu, Kevin Lin, John Hewitt, Ashwin Paranjape, Michele Bevilacqua, Fabio Petroni, and Percy Liang. 2024. [Lost in the middle: How language models use long contexts](https://md.research.elamur.ai/free/en/papers/liu-2023-lost-middle-language-models-use/). Transactions of the association for computational linguistics, 12:157–173.
17. Shukai Liu, Jian Yang, Bo Jiang, Yizhi Li, Jinyang Guo, Xianglong Liu, and Bryan Dai. 2025b. Context as a tool: Context management for long-horizon swe-agents. Preprint, arXiv:2512.22087. [find](https://scholar.google.com/scholar?q=Shukai+Liu%2C+Jian+Yang%2C+Bo+Jiang%2C+Yizhi+Li%2C+Jinyang+Guo%2C+Xianglong+Liu%2C+and+Bryan+Dai%2E+2025b%2E+Context+as+a+tool%3A+Context+management+for+long%2Dhorizon+swe%2Dagents%2E+Preprint%2C+arXiv%3A2512%2E22087%2E)
18. Keer Lu, Xiaonan Nie, Zheng Liang, Da Pan, Shusen Zhang, Keshi Zhao, Weipeng Chen, Zenan Zhou, Guosheng Dong, Bin Cui, and Wentao Zhang. 2024. Datasculpt: Crafting data landscapes for long-context llms through multi-objective partitioning. Preprint, arXiv:2409.00997. — [arXiv:2409.00997](https://arxiv.org/abs/2409.00997) [find](https://scholar.google.com/scholar?q=Keer+Lu%2C+Xiaonan+Nie%2C+Zheng+Liang%2C+Da+Pan%2C+Shusen+Zhang%2C+Keshi+Zhao%2C+Weipeng+Chen%2C+Zenan+Zhou%2C+Guosheng+Dong%2C+Bin+Cui%2C+and+Wentao+Zhang%2E+2024%2E+Datasculpt%3A+Crafting+data+landscapes+for+long%2Dcontext+llm)
19. Lingrui Mei, Jiayu Yao, Yuyao Ge, Yiwei Wang, Baolong Bi, Yujun Cai, Jiazhi Liu, Mingyu Li, Zhong-Zhi Li, Duzhen Zhang, Chenlin Zhou, Jiayi Mao, Tianze Xia, Jiafeng Guo, and Shenghua Liu. 2025. A survey of context engineering for large language models. Preprint, arXiv:2507.13334. — [arXiv:2507.13334](https://arxiv.org/abs/2507.13334) [find](https://scholar.google.com/scholar?q=Lingrui+Mei%2C+Jiayu+Yao%2C+Yuyao+Ge%2C+Yiwei+Wang%2C+Baolong+Bi%2C+Yujun+Cai%2C+Jiazhi+Liu%2C+Mingyu+Li%2C+Zhong%2DZhi+Li%2C+Duzhen+Zhang%2C+Chenlin+Zhou%2C+Jiayi+Mao%2C+Tianze+Xia%2C+Jiafeng+Guo%2C+and+Shenghua+Liu%2E+2025%2E+A+surv)
20. Grégoire Mialon, Clémentine Fourrier, Thomas Wolf, Yann LeCun, and Thomas Scialom. 2023. [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.
21. Zehan Qi, Xiao Liu, Iat Long Iong, Hanyu Lai, Xueqiao Sun, Jiadai Sun, Xinyue Yang, Yu Yang, Shuntian Yao, Wei Xu, Jie Tang, and Yuxiao Dong. 2025. WebRL: Training LLM web agents via self-evolving online curriculum reinforcement learning. In The Thirteenth International Conference on Learning Repres… [find](https://scholar.google.com/scholar?q=Zehan+Qi%2C+Xiao+Liu%2C+Iat+Long+Iong%2C+Hanyu+Lai%2C+Xueqiao+Sun%2C+Jiadai+Sun%2C+Xinyue+Yang%2C+Yu+Yang%2C+Shuntian+Yao%2C+Wei+Xu%2C+Jie+Tang%2C+and+Yuxiao+Dong%2E+2025%2E+WebRL%3A+Training+LLM+web+agents+via+self%2Devolving+onl)
22. Timo Schick, Jane Dwivedi-Yu, Roberto Dessì, Roberta Raileanu, Maria Lomeli, Eric Hambro, Luke Zettlemoyer, Nicola Cancedda, and Thomas Scialom. 2023. [Toolformer: Language models can teach themselves to use tools](https://md.research.elamur.ai/free/en/papers/schick-2023-toolformer-language-models-can-teach/). Advances in neural information processing systems, 36:68539–68551.
23. Noah Shinn, Federico Cassano, Ashwin Gopinath, Karthik Narasimhan, and Shunyu Yao. 2023. [Reflexion: Language agents with verbal reinforcement learning](https://md.research.elamur.ai/free/en/papers/shinn-2023-reflexion-language-agents-verbal-reinforcement/). Advances in neural information processing systems, 36:8634–8652.
24. Weiwei Sun, Miao Lu, Zhan Ling, Kang Liu, Xuesong Yao, Yiming Yang, and Jiecao Chen. 2025. Scaling long-horizon llm agent via context-folding. arXiv preprint arXiv:2510.11967. — [arXiv:2510.11967](https://arxiv.org/abs/2510.11967) [find](https://scholar.google.com/scholar?q=Weiwei+Sun%2C+Miao+Lu%2C+Zhan+Ling%2C+Kang+Liu%2C+Xuesong+Yao%2C+Yiming+Yang%2C+and+Jiecao+Chen%2E+2025%2E+Scaling+long%2Dhorizon+llm+agent+via+context%2Dfolding%2E+arXiv+preprint+arXiv%3A2510%2E11967%2E+%E2%80%94+%5BarXiv%3A2510%2E11967%5D%28htt)
25. Haoran Tan, Zeyu Zhang, Chen Ma, Xu Chen, Quanyu Dai, and Zhenhua Dong. 2025. Membench: Towards more comprehensive evaluation on the memory of llm-based agents. Preprint, arXiv:2506.21605. [find](https://scholar.google.com/scholar?q=Haoran+Tan%2C+Zeyu+Zhang%2C+Chen+Ma%2C+Xu+Chen%2C+Quanyu+Dai%2C+and+Zhenhua+Dong%2E+2025%2E+Membench%3A+Towards+more+comprehensive+evaluation+on+the+memory+of+llm%2Dbased+agents%2E+Preprint%2C+arXiv%3A2506%2E21605%2E)
26. Anthropic Team. 2025. Claude 4: Advancing multimodal reasoning and agent capabilities. Technical Report. [find](https://scholar.google.com/scholar?q=Anthropic+Team%2E+2025%2E+Claude+4%3A+Advancing+multimodal+reasoning+and+agent+capabilities%2E+Technical+Report%2E)
27. Tongyi DeepResearch Team, Baixuan Li, Bo Zhang, Dingchu Zhang, Fei Huang, Guangyu Li, Guoxin Chen, Huifeng Yin, Jialong Wu, Jingren Zhou, Kuan Li, Liangcai Su, Litu Ou, Liwen Zhang, Pengjun Xie, Rui Ye, Wenbiao Yin, Xinmiao Yu, Xinyu Wang, and 38 others. 2025. Tongyi deepresearch technical report. P… — [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+Kuan+Li%2C+Liangcai+Su%2C+Litu+Ou%2C+Liwen+Zhang%2C+Pengjun+Xie%2C+Rui+Y)
28. Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. 2017. [Attention is all you need](https://md.research.elamur.ai/free/en/papers/vaswani-2017-attention-all-need/). Advances in neural information processing systems, 30.
29. Jason Wei, Zhiqing Sun, Spencer Papay, Scott McKinney, Jeffrey Han, Isa Fulford, Hyung Won Chung, Alex Tachard Passos, William Fedus, and Amelia Glaese. 2025. Browsecomp: A simple yet challenging benchmark for browsing agents. arXiv preprint arXiv:2504.12516. [find](https://scholar.google.com/scholar?q=Jason+Wei%2C+Zhiqing+Sun%2C+Spencer+Papay%2C+Scott+McKinney%2C+Jeffrey+Han%2C+Isa+Fulford%2C+Hyung+Won+Chung%2C+Alex+Tachard+Passos%2C+William+Fedus%2C+and+Amelia+Glaese%2E+2025%2E+Browsecomp%3A+A+simple+yet+challenging+benc)
30. Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, Quoc V Le, Denny Zhou, and 1 others. 2022. [Chain-of-thought prompting elicits reasoning in large language models](https://md.research.elamur.ai/free/en/papers/wei-2022-chain-thought-prompting-elicits-reasoning/). Advances in neural information processing systems, 35:24824– 24837.
31. Ryan Wong, Jiawei Wang, Junjie Zhao, Li Chen, Yan Gao, Long Zhang, Xuan Zhou, Zuo Wang, Kai Xiang, Ge Zhang, Wenhao Huang, Yang Wang, and Ke Wang. 2025. [Widesearch: Benchmarking agentic broad info-seeking](https://md.research.elamur.ai/free/en/papers/wong-2025-widesearch-benchmarking-agentic-broad-info/). Preprint, arXiv:2508.07999.
32. Jialong Wu, Wenbiao Yin, Yong Jiang, Zhenglin Wang, Zekun Xi, Runnan Fang, Linhai Zhang, Yulan He, Deyu Zhou, Pengjun Xie, and Fei Huang. 2025. [Webwalker: Benchmarking llms in web traversal](https://md.research.elamur.ai/free/en/papers/wu-2025-webwalker-benchmarking-llms-web-traversal/). Preprint, arXiv:2501.07572.
33. Qingyun Wu, Gagan Bansal, Jieyu Zhang, Yiran Wu, Beibin Li, Erkang Zhu, Li Jiang, Xiaoyun Zhang, Shaokun Zhang, Jiale Liu, Ahmed Hassan Awadallah, Ryen W White, Doug Burger, and Chi Wang. 2023. [Autogen: Enabling next-gen llm applications via multi-agent conversation](https://md.research.elamur.ai/free/en/papers/wu-2023-autogen-enabling-next-gen-llm/). Preprint, arXiv:2308.08155.
34. Xixi Wu, Kuan Li, Yida Zhao, Liwen Zhang, Litu Ou, Huifeng Yin, Zhongwang Zhang, Xinmiao Yu, Dingchu Zhang, Yong Jiang, Pengjun Xie, Fei Huang, Minhao Cheng, Shuai Wang, Hong Cheng, and Jingren Zhou. 2026. [Resum: Unlocking long-horizon search intelligence via context summarization](https://md.research.elamur.ai/free/en/papers/wu-2025-resum-unlocking-long-horizon-search/). Preprint, arXiv:2…
35. Zhiheng Xi, Wenxiang Chen, Xin Guo, Wei He, Yiwen Ding, Boyang Hong, Ming Zhang, Junzhe Wang, Senjie Jin, Enyu Zhou, Rui Zheng, Xiaoran Fan, Xiao Wang, Limao Xiong, Yuhao Zhou, Weiran Wang, Changhao Jiang, Yicheng Zou, Xiangyang Liu, and 10 others. 2023. [The rise and potential of large language mode…](https://md.research.elamur.ai/free/en/papers/xi-2023-rise-potential-large-language/)
36. Guangxuan Xiao, Yuandong Tian, Beidi Chen, Song Han, and Mike Lewis. 2023. Efficient streaming language models with attention sinks. arXiv preprint arXiv:2309.17453. [find](https://scholar.google.com/scholar?q=Guangxuan+Xiao%2C+Yuandong+Tian%2C+Beidi+Chen%2C+Song+Han%2C+and+Mike+Lewis%2E+2023%2E+Efficient+streaming+language+models+with+attention+sinks%2E+arXiv+preprint+arXiv%3A2309%2E17453%2E)
37. Tianbao Xie, Fan Zhou, Zhoujun Cheng, Peng Shi, Luoxuan Weng, Yitao Liu, Toh Jing Hua, Junning Zhao, Qian Liu, Che Liu, Leo Z. Liu, Yiheng Xu, Hongjin Su, Dongchan Shin, Caiming Xiong, and Tao Yu. 2023. [Openagents: An open platform for language agents in the wild](https://md.research.elamur.ai/free/en/papers/xie-2023-openagents-open-platform-language-agents/). Preprint, arXiv:2310.10634.
38. 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.
39. Rui Ye, Zhongwang Zhang, Kuan Li, Huifeng Yin, Zhengwei Tao, Yida Zhao, Liangcai Su, Liwen Zhang, Zile Qiao, Xinyu Wang, Pengjun Xie, Fei Huang, Siheng Chen, Jingren Zhou, and Yong Jiang. 2025. Agentfold: Long-horizon web agents with proactive context management. Preprint, arXiv:2510.24699. — [arXiv:2510.24699](https://arxiv.org/abs/2510.24699) [find](https://scholar.google.com/scholar?q=Rui+Ye%2C+Zhongwang+Zhang%2C+Kuan+Li%2C+Huifeng+Yin%2C+Zhengwei+Tao%2C+Yida+Zhao%2C+Liangcai+Su%2C+Liwen+Zhang%2C+Zile+Qiao%2C+Xinyu+Wang%2C+Pengjun+Xie%2C+Fei+Huang%2C+Siheng+Chen%2C+Jingren+Zhou%2C+and+Yong+Jiang%2E+2025%2E+Agentf)
40. Yusen Zhang, Ruoxi Sun, Yanfei Chen, Tomas Pfister, Rui Zhang, and Sercan Ö Arık. 2024a. Chain of agents: Large language models collaborating on long-context tasks. Advances in Neural Information Processing Systems, 37:132208–132237. [find](https://scholar.google.com/scholar?q=Yusen+Zhang%2C+Ruoxi+Sun%2C+Yanfei+Chen%2C+Tomas+Pfister%2C+Rui+Zhang%2C+and+Sercan+%C3%96+Ar%C4%B1k%2E+2024a%2E+Chain+of+agents%3A+Large+language+models+collaborating+on+long%2Dcontext+tasks%2E+Advances+in+Neural+Information+Proc)
41. Yuxiang Zhang, Jiangming Shu, Ye Ma, Xueyuan Lin, Shangxi Wu, and Jitao Sang. 2025a. [Memory as action: Autonomous context curation for long-horizon agentic tasks](https://md.research.elamur.ai/free/en/papers/zhang-2026-memory-as-action-autonomous-context/). arXiv preprint arXiv:2510.12635.
42. Zeyu Zhang, Xiaohe Bo, Chen Ma, Rui Li, Xu Chen, Quanyu Dai, Jieming Zhu, Zhenhua Dong, and Ji-Rong Wen. 2024b. A survey on the memory mechanism of large language model based agents. Preprint, arXiv:2404.13501. [find](https://scholar.google.com/scholar?q=Zeyu+Zhang%2C+Xiaohe+Bo%2C+Chen+Ma%2C+Rui+Li%2C+Xu+Chen%2C+Quanyu+Dai%2C+Jieming+Zhu%2C+Zhenhua+Dong%2C+and+Ji%2DRong+Wen%2E+2024b%2E+A+survey+on+the+memory+mechanism+of+large+language+model+based+agents%2E+Preprint%2C+arXiv%3A2)
43. Zeyu Zhang, Quanyu Dai, Xiaohe Bo, Chen Ma, Rui Li, Xu Chen, Jieming Zhu, Zhenhua Dong, and Ji-Rong Wen. 2025b. A survey on the memory mechanism of large language model-based agents. ACM Transactions on Information Systems, 43(6):1–47. [find](https://scholar.google.com/scholar?q=Zeyu+Zhang%2C+Quanyu+Dai%2C+Xiaohe+Bo%2C+Chen+Ma%2C+Rui+Li%2C+Xu+Chen%2C+Jieming+Zhu%2C+Zhenhua+Dong%2C+and+Ji%2DRong+Wen%2E+2025b%2E+A+survey+on+the+memory+mechanism+of+large+language+model%2Dbased+agents%2E+ACM+Transactions+)
44. Peilin Zhou, Bruce Leon, Xiang Ying, Can Zhang, Yifan Shao, Qichen Ye, Dading Chong, Zhiling Jin, Chenxuan Xie, Meng Cao, Yuxin Gu, Sixin Hong, Jing Ren, Jian Chen, Chao Liu, and Yining Hua. 2025. Browsecomp-zh: Benchmarking web browsing ability of large language models in chinese. Preprint, arXiv:2… — [arXiv:2504.19314](https://arxiv.org/abs/2504.19314) [find](https://scholar.google.com/scholar?q=Peilin+Zhou%2C+Bruce+Leon%2C+Xiang+Ying%2C+Can+Zhang%2C+Yifan+Shao%2C+Qichen+Ye%2C+Dading+Chong%2C+Zhiling+Jin%2C+Chenxuan+Xie%2C+Meng+Cao%2C+Yuxin+Gu%2C+Sixin+Hong%2C+Jing+Ren%2C+Jian+Chen%2C+Chao+Liu%2C+and+Yining+Hua%2E+2025%2E+Bro)
45. Youxiang Zhu, Ruochen Li, Danqing Wang, Daniel Haehn, and Xiaohui Liang. 2025. Focus directions make your language models pay more attention to relevant contexts. arXiv preprint arXiv:2503.23306. — [arXiv:2503.23306](https://arxiv.org/abs/2503.23306) [find](https://scholar.google.com/scholar?q=Youxiang+Zhu%2C+Ruochen+Li%2C+Danqing+Wang%2C+Daniel+Haehn%2C+and+Xiaohui+Liang%2E+2025%2E+Focus+directions+make+your+language+models+pay+more+attention+to+relevant+contexts%2E+arXiv+preprint+arXiv%3A2503%2E23306%2E+%E2%80%94+%5Ba)
46. Heng-Da Xu, Xian-Ling Mao, Puhai Yang, Fanshu Sun, and Heyan Huang. 2024. Rethinking task-oriented dialogue systems: From complex modularity to zero-shot autonomous agent. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2748–… [find](https://scholar.google.com/scholar?q=Heng%2DDa+Xu%2C+Xian%2DLing+Mao%2C+Puhai+Yang%2C+Fanshu+Sun%2C+and+Heyan+Huang%2E+2024%2E+Rethinking+task%2Doriented+dialogue+systems%3A+From+complex+modularity+to+zero%2Dshot+autonomous+agent%2E+In+Proceedings+of+the+62nd+A)
47. Bufang Yang, Lilin Xu, Liekang Zeng, Kaiwei Liu, Siyang Jiang, Wenrui Lu, Hongkai Chen, Xiaofan Jiang, Guoliang Xing, and Zhenyu Yan. 2025. Contextagent: Context-aware proactive llm agents with open-world sensory perceptions. Preprint, arXiv:2505.14668. — [arXiv:2505.14668](https://arxiv.org/abs/2505.14668) [find](https://scholar.google.com/scholar?q=Bufang+Yang%2C+Lilin+Xu%2C+Liekang+Zeng%2C+Kaiwei+Liu%2C+Siyang+Jiang%2C+Wenrui+Lu%2C+Hongkai+Chen%2C+Xiaofan+Jiang%2C+Guoliang+Xing%2C+and+Zhenyu+Yan%2E+2025%2E+Contextagent%3A+Context%2Daware+proactive+llm+agents+with+open%2Dw)

*Updated 1 November 2026*