Liwen Zhang
Liwen Zhang has 3 papers in our library, in 2025–2026, most of them on Summarization; often with Fei Huang, Pengjun Xie, Yong Jiang.
OpenAlex · ORCID · Wikidata · h-index 29 · 105 works · 4,191 citations OpenAlex, 2026-10-14
📄 3 works in our library · 🔗 Cited 73 times in our library · 1 more in our library without a page yet · ⭐ Paper Stars ranking: #7221
Affiliations
🎓Beihang UniversityBeijing ·
China2012–2026 · 62 papersEducation since 2012Employment🎓Nankai UniversityTianjin ·
China2025–2026 · 3 papers🎓Zhejiang UniversityHangzhou ·
China2022–2026 · 3 papers🎓Chang'an UniversityXi'an ·
China2025–2026 · 2 papers🎓Xiangtan UniversityXiangtan ·
China2026 · 1 paper🎓East China University of Science and TechnologyShanghai ·
China2020–2025 · 5 papers🎓Dalian University of TechnologyDalian ·
China2012–2022 · 3 papers🏢Alibaba GroupGeorge Town ·
Cayman Islands2025 · 2 papers🏢Alibaba GroupHangzhou ·
China2025 · 2 papers🎓Shanghai Jiao Tong UniversityShanghai ·
China2008–2012Education 2008–2012
Fields, topics and concepts
📚 Shelves 5The field of science this work belongs to (OpenAlex fields).Arts and Humanities · 3 worksComputer Science · 3 worksArtificial Intelligence · 3 worksInformation Systems · 3 worksLanguage and Linguistics · 3 works
🧭 Topics 1Research subjects and languages the work is about.Summarization · 1 work
Works by year
2020s
Papers
- WebDancer: Towards Autonomous Information Seeking Agency (2025 · 50 citations)
WebDancer addresses how to train, from scratch, an open web agent that can carry out the long, multi-step research associated with systems like Deep Research. - ReSum: Unlocking Long-Horizon Search Intelligence via Context Summarization (2025 · 26 citations)
Web agents built on LLMs often fail on hard multi-hop questions. The ReAct loop keeps adding every search result to the prompt, so the context window fills up before the agent finds the answer. Earlier fixes such as MEM1 or MemAgent change the model's architecture and require full retraining. ReSum avoids this with a… - BrowseConf: Confidence-Guided Test-Time Scaling for Web Agents (2026)
The paper asks whether LLM-based web search agents can meaningfully report how sure they are after long chains of browsing and reasoning.
All works
- WebDancer: Towards Autonomous Information Seeking AgencyConference on Neural Information Processing Systems (NeurIPS)Jialong Wu, Baixuan Li, Runnan Fang, et al.2025 · 50 citations
- ReSum: Unlocking Long-Horizon Search Intelligence via Context SummarizationarXiv:2509.13313Xixi Wu, Kuan Li, Yida Zhao, et al.2025 · 26 citations
- BrowseConf: Confidence-Guided Test-Time Scaling for Web AgentsFindings of the Association for Computational LinguisticsLitu Ou, Kuan Li, Huifeng Yin, et al.2026
- WebAnchor: Anchoring Agent Planning to Stabilize Long-Horizon Web Reasoning ↗Findings of the Association for Computational Linguistics: ACL 2026 · no summary yetXinmiao Yu et al.2026
Co-authors here
- Fei Huang ×3
- Pengjun Xie ×3
- Yong Jiang ×3
- Dingchu Zhang ×2
- Huifeng Yin ×2
- Kuan Li ×2
- Litu Ou ×2
- Xixi Wu ×2
- Zhongwang Zhang ×2
- Jialong Wu
- Jingren Zhou
- Rui Ye
Venues
- Findings of the Association for Computational Linguistics: Findings of the Association for Computational Linguistics 2026
- Conference on Neural Information Processing Systems (NeurIPS): NeurIPS 2025
- Findings of the Association for Computational Linguistics: ACL 2026
Cited by
Updated
This page in Markdown → https://md.research.elamur.ai/free/en/authors/liwen-zhang/