🧑‍🔬 Zifeng Wang

🏛️ Affiliations

🎓East China University of Science and TechnologyShanghai · China2025–2026 · 2 paperscurrent🎓Wuhan UniversityWuhan · China2014–2025 · 11 papers🎓City University of Hong KongHong Kong · China2015–2019 · 7 papers🔬State Key Laboratory of Information Engineering in Surveying Mapping and Remote SensingWuhan · China2014–2016 · 5 papers🏢GoogleMountain View · United States2024–2025 · 4 papers🎓University of Illinois Urbana-ChampaignUrbana · United States2022–2024 · 3 papers🎓Shanghai Jiao Tong UniversityShanghai · China2019–2021 · 2 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 3 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. MindMap: Knowledge Graph Prompting Sparks Graph of Thoughts in Large Language Models (2024 · 158 citations)
   LLMs struggle to absorb new knowledge, often hallucinate, and do not show how they reach answers. These problems matter most in high-stakes settings such as medical diagnosis. MindMap is a plug-and-play prompting pipeline that pairs a frozen LLM, such as GPT-3.5 or GPT-4, with a knowledge graph. It works in three…
2. In Prospect and Retrospect: Reflective Memory Management for Long-term Personalized Dialogue Agents (2025 · 46 citations)
   LLM dialogue agents keep no state between sessions, so long-term personalization depends on external memory.
3. Speculative Knowledge Distillation: Bridging the Teacher-Student Gap Through Interleaved Sampling (2024 · 41 citations)
   Distilling a large language model into a smaller one runs into two failure modes. Supervised KD trains on a fixed set of outputs, so it never sees the kind of text the student produces at inference time. On-policy KD trains on the student's own generations, but early on these are often poor and unfamiliar to the…
4. PlanGEN: A Multi-Agent Framework for Generating Planning and Reasoning Trajectories for Complex Problem Solving (2025 · 16 citations)
   LLM-based agents and test-time search methods often fail on "natural planning" tasks, such as scheduling meetings or planning trips described in plain language.
5. When One LLM Drools, Multi-LLM Collaboration Rules (2026 · 14 citations)
   This position paper by Feng et al. (ACL 2026) argues that a single general-purpose LLM cannot reliably handle complex, context-dependent, or subjective settings. It contributes no new dataset or model. Instead, it makes a conceptual case that any one model leaves gaps on three fronts. It misses parts of real-world…
6. s3: You Don't Need That Much Data to Train a Search Agent via RL (2025 · 12 citations)
   Training LLM search agents with reinforcement learning usually takes one of two routes. Some methods reward retrieval metrics such as NDCG, which may not reflect answer quality. Others fine-tune a single model to both search and answer, which mixes the two skills and rules out frozen or proprietary generators. The…

All works

8 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. MindMap: Knowledge Graph Prompting Sparks Graph of Thoughts in Large Language ModelsAnnual Meeting of the Association for Computational Linguistics (ACL)Yilin Wen, Zifeng Wang, Jimeng Sun2024 · 158 citations
2. Found in the middle: Calibrating Positional Attention Bias Improves Long Context Utilization ↗Findings of the Association for Computational Linguistics: ACL 2024 · no summary yetCheng-Yu Hsieh et al.2024 · 61 citations
3. In Prospect and Retrospect: Reflective Memory Management for Long-term Personalized Dialogue AgentsAnnual Meeting of the Association for Computational Linguistics (ACL)Zhen Tan, Jun Yan, I-Hung Hsu, et al.2025 · 46 citations
4. Speculative Knowledge Distillation: Bridging the Teacher-Student Gap Through Interleaved SamplingarXiv:2410.11325Wenda Xu, Rujun Han, Zifeng Wang, et al.2024 · 41 citations
5. PlanGEN: A Multi-Agent Framework for Generating Planning and Reasoning Trajectories for Complex Problem SolvingConference on Empirical Methods in Natural Language Processing (EMNLP)Mihir Parmar, Xin Liu, Palash Goyal, et al.2025 · 16 citations
6. When One LLM Drools, Multi-LLM Collaboration RulesAnnual Meeting of the Association for Computational Linguistics (ACL)Shangbin Feng, Wenxuan Ding, Alisa Liu, et al.2026 · 14 citations
7. s3: You Don't Need That Much Data to Train a Search Agent via RLConference on Empirical Methods in Natural Language Processing (EMNLP)Pengcheng Jiang, Xueqiang Xu, Jiacheng Lin, et al.2025 · 12 citations
8. Adaptation of Agentic AI: A Survey of Post-Training, Memory, and Skills ↗arXiv (Cornell University) · no summary yetJiang, Pengcheng et al.2025 · 3 citations

🤝 Co-authors here

12 of 32 co-authors with a page, the most papers together first.

• Chen-Yu Lee ×3
• Long Le ×3
• Jimeng Sun ×2
• Rujun Han ×2
• Tomas Pfister ×2
• Yanfei Chen ×2
• Alisa Liu
• Chitta Baral
• Hamid Palangi
• Hootan Nakhost
• Hunter Lang
• I-Hung Hsu

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) ×3: ACL 2026, ACL 2025, ACL 2024
• Conference on Empirical Methods in Natural Language Processing (EMNLP) ×2: EMNLP 2025 ×2
• Findings of the Association for Computational Linguistics: ACL 2024

🔗 Cited by

Papers of our library cite their works 189 times (of the 149,439 papers whose bibliographies we read); 49 citing papers with a page here →.

Updated 30 October 2026

↑ back to top

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