About me

I am currently a 3rd year PhD student at the Gaoling School of Artificial Intelligence, Renmin University of China, mentored by Prof. Zhicheng Dou. I earned my bachelor’s degree (2019-2023) at Nankai University.

I’m currently a RedStar research intern focusing on foundation agent research at Xiaohongshu Inc. I have published 20+ papers in top-tier AI conferences and journals (8 first-author papers), including NeurIPS, ICML, ICLR, ACL, EMNLP, AAAI, SIGIR, WWW, and TOIS. Citations: ; Project Stars:

Research Interests：

• Omni-Modal Agents: Building real-world omni-modal AI assistants (OmniGAIA);
• Foundation Agents: Developing general-purpose agentic LLMs (DeepAgent, AEPO, Tool-Star);
• Deep Research: Enhancing long-horizon reasoning with web information seeking (WebThinker, Search-o1, HiRA);
• Retrieval-Augmented LLMs: Improving large language models with knowledge retrieval (RetroLLM, CorpusLM, UniGen).

I aim to build Real-World AI Agents that are reliable, capable, and genuinely helpful in everyday life.

🔥 News

💻 Experiences

• Incoming | ByteDance Seed, Foundation LLM Team
  Research Intern on General Agents (Seed-LLM Talent Program)
  Mentors: Wanjun Zhong, Yujia Qin
• 2025.06 - 2026.05 | Xiaohongshu, Agent R&D Team
  Research Intern on General Agents (RedStar Program)
  Mentors: Wenxiang Jiao, Yuan Lu

📝 Selected Work

Preprint

OmniGAIA: Towards Native Omni-Modal AI Agents

Xiaoxi Li, Wenxiang Jiao, Jiarui Jin, Shijian Wang, Guanting Dong, 6 More Authors Jiajie Jin, Hao Wang, Yinuo Wang, Ji-Rong Wen, Yuan Lu, and Zhicheng Dou.

• Introduces OmniGAIA, a comprehensive benchmark for evaluating omni-modal agents on complex reasoning and tool-use across videos, images, and audios.
• Presents OmniAtlas, a native omni-modal reasoning agent with active perception and autonomous tool use.

WWW 2026 (Oral)

DeepAgent: A General Reasoning Agent with Scalable Toolsets

Xiaoxi Li, Wenxiang Jiao, Jiarui Jin, Guanting Dong, Jiajie Jin, 6 More Authors Yinuo Wang, Hao Wang, Yutao Zhu, Ji-Rong Wen, Yuan Lu, and Zhicheng Dou.

• A general reasoning agent that can autonomously discover and use tools, while compressing memory to support long-horizon interactions.
• Introduces ToolPO, an end-to-end agentic RL training strategy that improves overall performance.

NeurIPS 2025

WebThinker: Empowering Large Reasoning Models with Deep Research Capability

Xiaoxi Li, Jiajie Jin, Guanting Dong, Hongjin Qian, Yutao Zhu, 3 More Authors Yongkang Wu, Ji-Rong Wen, and Zhicheng Dou.

Most Influential NeurIPS 2025 Papers -- Top 11/5827

• An reasoning agent designed to autonomously search, deeply explore web pages, and draft research reports, all within its thinking process.

EMNLP 2025 (Oral)

Search-o1: Agentic Search-Enhanced Large Reasoning Models

Xiaoxi Li, Guanting Dong, Jiajie Jin, Yuyao Zhang, Yujia Zhou, 3 More Authors Yutao Zhu, Peitian Zhang, and Zhicheng Dou.

Most Influential EMNLP 2025 Papers -- Top 2/3228

• The first framework that enables o1-style reasoning models to autonomously search for and consult external information when they encounter missing or unfamiliar knowledge.

• RetroLLM: Empowering Large Language Models to Retrieve Fine-grained Evidence within Generation
  Xiaoxi Li, Jiajie Jin, Yujia Zhou, Yongkang Wu, Zhonghua Li, 2 More Authors Qi Ye and Zhicheng Dou.
  ACL 2025 Main
  
• From Matching to Generation: A Survey on Generative Information Retrieval
  Xiaoxi Li, Jiajie Jin, Yujia Zhou, Yuyao Zhang, Peitian Zhang, 2 More Authors Yutao Zhu and Zhicheng Dou.
  TOIS 2025 (JCR Q1, IF=9.1) (Most Influential arXiv IR Papers in 2024 – Top 11/All)
  
• CorpusLM: Towards a Unified Language Model on Corpus for Knowledge-intensive Tasks
  Xiaoxi Li, Zhicheng Dou, Yujia Zhou, Fangchao Liu.
  SIGIR 2024 (Oral)
  
• UniGen: A Unified Generative Framework for Retrieval and Question Answering with Large Language Models
  Xiaoxi Li, Yujia Zhou, Zhicheng Dou.
  AAAI 2024
  
• Hierarchical Document Refinement for Long-context Retrieval-augmented Generation
  Jiajie Jin, Xiaoxi Li, Guanting Dong, Yuyao Zhang, Yutao Zhu, 4 More Authors Yongkang Wu, Zhonghua Li, Qi Ye, and Zhicheng Dou.
  ACL 2025 Main (Oral)
  
• RAG-Critic: Leveraging Automated Critic-Guided Agentic Workflow for Retrieval Augmented Generation
  Guanting Dong, Jiajie Jin, Xiaoxi Li, Yutao Zhu, Zhicheng Dou, 1 More Author Ji-Rong Wen.
  ACL 2025 Main
• Agentic Entropy-Balanced Policy Optimization
  Guanting Dong, Licheng Bao, Zhongyuan Wang, Kangzhi Zhao, Xiaoxi Li, 9 More Authors Jiajie Jin, Jinghan Yang, Hangyu Mao, Fuzheng Zhang, Kun Gai, Guorui Zhou, Yutao Zhu, Ji-Rong Wen, and Zhicheng Dou.
  WWW 2026 (Oral)
  
• ImplicitRM: Unbiased Reward Modeling from Implicit Preference Data for LLM alignment
  Hao Wang, Haocheng Yang, Licheng Pan, Lei Shen, Xiaoxi Li, 5 More AuthorsYinuo Wang, Zhichao Chen, Yuan Lu, Haoxuan Li, Zhouchen Lin.
  ICML 2026
• HiRA: A Hierarchical Reasoning Framework for Decoupled Planning and Execution in Deep Search
  Jiajie Jin, Xiaoxi Li, Guanting Dong, Yuyao Zhang, Yutao Zhu, 3 More Authors Yang Zhao, Hongjin Qian, and Zhicheng Dou.
  SIGIR 2026
  
• Tool-Star: Empowering LLM-Brained Multi-Tool Reasoner via Reinforcement Learning
  Guanting Dong, Yifei Chen, Xiaoxi Li, Jiajie Jin, Hongjin Qian, 5 More Authors Yutao Zhu, Hangyu Mao, Guorui Zhou, Zhicheng Dou, and Ji-Rong Wen.
  SIGIR 2026
  

📖 Educations

• 2023.09 - Present | Ph.D. in Artificial Intelligence
  Gaoling School of Artificial Intelligence, Renmin University of China
• 2019.09 - 2023.06 | B.Sc. in Intelligence Science and Technology
  College of Artificial Intelligence, Nankai University

🎤 Invited Talks

• 2026.05: “Reason, Search, and Act: Towards Real-World AI Agents”, MLNLP Community. [Link]
• 2026.03: “Reason, Search, and Act: Towards Real-World AI Agents”, CCIR PhD Forum.
• 2025.04: “WebThinker: Empowering Large Reasoning Models with Deep Research Capability”, MLNLP Community. [Link]

📚 Academic Services

• PC Member: ACL Rolling Review, NeurIPS, ICML, ICLR, SIGIR, AAAI (Silver Reviewer Award @ ICML’26)
• Journal Reviewer: ACM Computing Surveys, TOIS