Hello🙋, I’m Litu Ou, a first year PhD student at the University of Edinburgh, supervised by Prof. Mirella Lapata. Previously, I was an intern at the Tongyi Lab working on the Tongyi DeepResearch project. My current research interests lie in improving long context understanding and long horizon task solving abilities in LLMs. Below list the specific areas I’m focusing on:

• Explore current limitations of LLMs dealing with tasks requiring very long input contexts
• Enhance long context capabilities through various techniques, such as synthetic data generation, post-training and architectural modifications
• Develop LLM Agents capable of engaging in multi-step reasoning and planning to solve difficult tasks
• Resolve dilemmas between long context and long horizon task solving through context engineering and memory mechanisms

👨‍💻 Research Experiences

• PhD at Institute for Language, Cognition and Computation - University of Edinburgh (2025.09 - Present)
• Research Intern - Tongyi DeepResearch Team (2025.06 - 2025.09)
• Research Intern (Remote) - Tsinghua University (2024.08 - 2025.05)
• Research Assistant - University of Edinburgh (2023.06 - 2024.11)

📝 Publications

• Tongyi DeepResearch Technical Report

  arXiv

  _{Tongyi DeepResearch Team}

• BrowseConf: Confidence-Guided Test-Time Scaling for Web Agents

  arXiv

  _{Litu Ou*, Kuan Li*, Huifeng Yin*, Liwen Zhang, Zhongwang Zhang, Xixi Wu, Rui Ye, Zile Qiao, Yong Jiang, Pengjun Xie, Fei Huang, Jingren Zhou}

• WebSailor-V2: Bridging the Chasm to Proprietary Agents via Synthetic Data and Scalable Reinforcement Learning

  arXiv

  _{Kuan Li*, Zhongwang Zhang*, Huifeng Yin*, Rui Ye*, Yida Zhao*, Liwen Zhang*, Litu Ou, Dingchu Zhang, Xixi Wu, Jialong Wu, Xinyu Wang, Zile Qiao, Zhen Zhang, Yong Jiang, Pengjun Xie, Fei Huang, Jingren Zhou}

• ReSum: Unlocking Long-Horizon Search Intelligence via Context Summarization

  arXiv

  _{Xixi Wu*, Kuan Li*, Yida Zhao, Liwen Zhang, Litu Ou, Huifeng Yin, Zhongwang Zhang, Yong Jiang, Pengjun Xie, Fei Huang, Minhao Cheng, Shuai Wang, Hong Cheng, Jingren Zhou}

• WebSailor: Navigating Super-human Reasoning for Web Agent

  arXiv

  _{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, Jingren Zhou}

• ToLeaP: Rethinking Development of Tool Learning with Large Language Models

  arXiv

  _{Haotian Chen*, Zijun Song*, Boye Niu*, Ke Zhang*, Litu Ou*, Yaxi Lu, Zhong Zhang, Xin Cong, Yankai Lin, Zhiyuan Liu, Maosong Sun}

• Context-Aware Hierarchical Merging for Long Document Summarization

  ACL 2025 Findings

  _{Litu Ou, Mirella Lapata}

• Open-Source vs Close-Source: The Context Utilization Challenge

  ICLR 2025 Blogpost Track

  _{Litu Ou}

• Chain-of-Thought Hub: A Continuous Effort to Measure Large Language Models’ Reasoning Performance

  ICML 2023 DeployableGenerativeAI

  _{Yao Fu, Litu Ou, Mingyu Chen, Yuhao Wan, Hao Peng, Tushar Khot}

• Specializing smaller language models towards multi-step reasoning

  ICML 2023 OralPoster

  _{Yao Fu, Hao Peng, Litu Ou, Ashish Sabharwal, Tushar Khot}