🧑‍🔬 Xu Chen

🏛️ Affiliations

🎓Renmin University of ChinaBeijing · China2020–2026 · 176 papersEmploymentcurrent🎓Tsinghua UniversityBeijing · China2015–2021 · 27 papers🎓University College LondonLondon · United Kingdom2020–2021 · 7 papers🏢MetaMenlo Park · United States2021 · 2 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 2 more institutions on single bylines are not listed.

🧭 Fields, topics and concepts

Of its works in our library, with the number of works on each.

📅 Works by year

2020s

📄 Papers

The most cited first (OpenAlex and our library).

1. A Survey on Large Language Model based Autonomous Agents (2023 · 2,284 citations)
   The survey maps the fast-growing research on autonomous agents that use a large language model as their central controller.
2. Cool-Fusion: Fuse Large Language Models without Training (2025 · 8 citations)
   Cool-Fusion addresses how to combine several heterogeneous LLMs so they benefit from each other's strengths.
3. LLM Prompt Duel Optimizer: Efficient Label-Free Prompt Optimization (2026 · 2 citations)
   Automatic prompt optimization usually scores candidate instructions against labeled validation data. Such data is often missing early in a deployment. The authors, from Penn State and Meta, propose the Prompt Duel Optimizer (PDO), which needs no labels. An LLM judge sees the outputs of two prompts on the same…
4. RepoGenesis: Benchmarking End-to-End Microservice Generation from Readme to Repository (2026 · 1 citation)
   Most code-generation benchmarks test single functions or classes, or ask models to edit existing codebases.
5. From Coarse to Fine: Self-Adaptive Hierarchical Planning for LLM Agents (2026)
   LLM agents that plan explicitly usually produce plans at a single, fixed level of detail. Such plans are too verbose for easy tasks and too shallow for hard ones. The authors propose AdaPlan-H, a planner inspired by the cognitive-science idea of progressive refinement. It first drafts a coarse global plan and then…
6. Learning from Cognition: Enhancing RL Efficiency for LLM Reasoning via Hierarchical Metacognitive Decomposition and Refinement (2026)
   Zero-RL training with verifiable rewards wastes much of its compute on weaker base LLMs. With a fixed prompt template, many problems yield no correct rollout, so accuracy-based filtering discards them. Cog-Rethinker tackles this by adding two cognition-inspired rollout stages on top of a DAPO-style pipeline. Problems…

All works

11 works of theirs in our library, the most cited first; 6 with a page here, the others link their original until we summarise them.

1. A Survey on Large Language Model based Autonomous AgentsFrontiers of Computer ScienceLei Wang, Chen Ma, Xueyang Feng, et al.2023 · 2,284 citations
2. Counterfactual Data-Augmented Sequential Recommendation ↗International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · no summary yetZhenlei Wang et al.2021 · 129 citations
3. Bridge Text and Knowledge by Learning Multi-Prototype Entity Mention Embedding ↗Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · no summary yetYixin Cao et al.2017 · 124 citations
4. Don't Make Your LLM an Evaluation Benchmark Cheater ↗arXiv:2311.01964 · no summary yetKun Zhou et al.2023 · 112 citations
5. Time Matters ↗International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · no summary yetWenwen Ye et al.2020 · 88 citations
6. User Behavior Simulation with Large Language Model based Agents ↗arXiv:2306.02552 · no summary yetLei Wang et al.2023 · 64 citations
7. Cool-Fusion: Fuse Large Language Models without TrainingAnnual Meeting of the Association for Computational Linguistics (ACL)Cong Liu, Xiaojun Quan, Yan Pan, et al.2025 · 8 citations
8. LLM Prompt Duel Optimizer: Efficient Label-Free Prompt OptimizationFindings of the Association for Computational LinguisticsYuanchen Wu, Saurabh Verma, Justin Lee, et al.2026 · 2 citations
9. RepoGenesis: Benchmarking End-to-End Microservice Generation from Readme to RepositoryAnnual Meeting of the Association for Computational Linguistics (ACL)Zhiyuan Peng, Xin Yin, Pu Zhao, et al.2026 · 1 citation
10. From Coarse to Fine: Self-Adaptive Hierarchical Planning for LLM AgentsFindings of the Association for Computational LinguisticsHaoran Tan, Zeyu Zhang, Chen Ma, et al.2026
11. Learning from Cognition: Enhancing RL Efficiency for LLM Reasoning via Hierarchical Metacognitive Decomposition and RefinementAnnual Meeting of the Association for Computational Linguistics (ACL)Zexu Sun, Yongcheng Zeng, Erxue Min, et al.2026

🤝 Co-authors here

12 of 19 co-authors with a page, the most papers together first.

• Chen Ma ×2
• Zeyu Zhang ×2
• Cong Liu
• Dongmei Zhang
• Dugang Liu
• Erxue Min
• Fangkai Yang
• Hao Yang
• Justin Lee
• Lei Wang
• Liang Lin
• Lu Wang

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

• Annual Meeting of the Association for Computational Linguistics (ACL) ×5: ACL 2026 ×2, ACL 2025
• Findings of the Association for Computational Linguistics ×2: Findings of the Association for Computational Linguistics 2026 ×2
• International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) ×2
• Frontiers of Computer Science: Frontiers of Computer Science 2023

🔗 Cited by

Papers of our library cite their works 674 times (of the 149,439 papers whose bibliographies we read); 145 citing papers with a page here →.

Updated 1 November 2026

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/xu-chen/