--- title: "Wentao Zhang — author profile and papers · Reasoning" description: "Wentao Zhang, University of Electronic Science and Technology of China: 13 papers on Elamur Research (2024–2026), h-index 2…" canonical: "https://research.elamur.ai/free/en/authors/wentao-zhang/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/wentao-zhang/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Wentao Zhang # Wentao Zhang Wentao Zhang has 13 papers in our library, in 2024–2026, most of them on [Reasoning](https://md.research.elamur.ai/free/en/topics/reasoning/), [Information retrieval & search](https://md.research.elamur.ai/free/en/topics/information-retrieval/), [Evaluation & benchmarks](https://md.research.elamur.ai/free/en/topics/evaluation-benchmarks/); often with [Hao Liang](https://md.research.elamur.ai/free/en/authors/hao-liang/), [Bihui Yu](https://md.research.elamur.ai/free/en/authors/bihui-yu/), [Bin Cui](https://md.research.elamur.ai/free/en/authors/bin-cui/). 13 papers in our library · 2024–2026 [OpenAlex](https://openalex.org/A5139787093) · [ORCID](https://orcid.org/0009-0007-1905-3603) · [**h-index 2**](https://openalex.org/authors/A5139787093) · [28 works](https://openalex.org/works?filter=author.id:A5139787093) · [11 citations](https://openalex.org/works?filter=author.id:A5139787093&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [📄 13 works in our library](https://md.research.elamur.ai/free/en/authors/wentao-zhang/#papers) · [🔗 Cited 202 times in our library](https://md.research.elamur.ai/free/en/authors/wentao-zhang/cited-by/) · [⭐ Paper Stars ranking: #4737](https://md.research.elamur.ai/free/en/paper-stars/page/48/#star-4737) The profile is the library's match of the name; two people with one name are not always told apart. Elsewhere: [Google Scholar](https://scholar.google.com/citations?view_op=search_authors&mauthors=Wentao+Zhang) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Wentao+Zhang) · [dblp](https://dblp.org/search?q=Wentao+Zhang) · [ACL Anthology](https://aclanthology.org/search/?q=Wentao+Zhang) ## Affiliations [🎓**University of Electronic Science and Technology of China** Chengdu · China 2024–2027 · 8 papersEducation 2024–2027 · Master of Science in Computer Science and Technology, School of Computer Science and Engineering(School of Cyber Security))*current*](https://md.research.elamur.ai/free/en/universities/university-of-electronic-science-and-technology-of-china/) · [🎓**Peking University** Beijing · China 2026 · 8 papers*current*](https://md.research.elamur.ai/free/en/universities/peking-university/) · [🏢**ByteDance** Beijing · China 2026 · 1 paper*current*](https://md.research.elamur.ai/free/en/companies/bytedance/) · [🎓**ShanghaiTech University** Shanghai · China 2026 · 1 paper*current*](https://md.research.elamur.ai/free/en/universities/shanghaitech-university/) · [🎓**Guangdong University of Technology** Guangzhou · China 2020–2024Education 2020–2024 · B.S. in Artificial Intelligence, School of Computer Science and Technology](https://md.research.elamur.ai/free/en/universities/guangdong-university-of-technology/) From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. ## Fields, topics and concepts Of its works in our library, with the number of works on each. 📚 Shelves 12 The field of science this work belongs to (OpenAlex fields).[Computer Science · 13 works](https://md.research.elamur.ai/free/en/shelves/computer-science/) · [Arts and Humanities · 12 works](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · [Artificial Intelligence · 12 works](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · [Language and Linguistics · 12 works](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · [Computer Vision and Pattern Recognition · 5 works](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · [Information Systems · 4 works](https://md.research.elamur.ai/free/en/shelves/computer-science/information-systems/) · [Computer Science Applications · 1 work](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-science-applications/) · [Computer Networks and Communications · 2 works](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-networks-and-communications/) · [Business, Management and Accounting · 1 work](https://md.research.elamur.ai/free/en/shelves/business-management-and-accounting/) · [Control and Systems Engineering · 1 work](https://md.research.elamur.ai/free/en/shelves/engineering/control-and-systems-engineering/) · [Engineering · 1 work](https://md.research.elamur.ai/free/en/shelves/engineering/) · [Management Information Systems · 1 work](https://md.research.elamur.ai/free/en/shelves/business-management-and-accounting/management-information-systems/) 🧭 Topics 8 Research subjects and languages the work is about.[Information retrieval & search · 3 works](https://md.research.elamur.ai/free/en/topics/information-retrieval/) · [Reasoning · 3 works](https://md.research.elamur.ai/free/en/topics/reasoning/) · [Vision & language · 2 works](https://md.research.elamur.ai/free/en/topics/multimodal/) · [Evaluation & benchmarks · 2 works](https://md.research.elamur.ai/free/en/topics/evaluation-benchmarks/) · [Code & programming languages · 2 works](https://md.research.elamur.ai/free/en/topics/code-and-programming/) · [Language models & pretraining · 1 work](https://md.research.elamur.ai/free/en/topics/language-models/) · [Low-resource languages · 1 work](https://md.research.elamur.ai/free/en/topics/low-resource-languages/) · [Semantic parsing & meaning representation · 1 work](https://md.research.elamur.ai/free/en/topics/semantic-parsing/) 💡 Concepts 1 Key ideas and methods explained on our concept pages.[Retrieval-augmented generation · 1 work](https://md.research.elamur.ai/free/en/concepts/retrieval-augmented-generation/) ## Works by year ### 2020s [**2026** 9 papers](https://md.research.elamur.ai/free/en/authors/wentao-zhang/year/2026/) · [**2025** 2 papers](https://md.research.elamur.ai/free/en/authors/wentao-zhang/year/2025/) · [**2024** 2 papers](https://md.research.elamur.ai/free/en/authors/wentao-zhang/year/2024/) ## Papers The most cited first (OpenAlex and our library). 1. **[Retrieval-Augmented Generation for AI-Generated Content: A Survey](https://md.research.elamur.ai/free/en/papers/zhao-2024-retrieval-augmented-generation-ai-generated/)** *(2024 · 301 citations)* Generative models for text, code, images, video and other media still have trouble with outdated knowledge, rare (long-tail) facts, leakage of private training data, and costly training and inference. 2. **[Buffer of Thoughts: Thought-Augmented Reasoning with Large Language Models](https://md.research.elamur.ai/free/en/papers/yang-2024-buffer-thoughts-thought-augmented-reasoning/)** *(2024 · 67 citations)* Prompting strategies for LLM reasoning fall into two camps. Single-query methods such as CoT or few-shot prompting rely on hand-made, task-specific exemplars. Multi-query methods such as ToT and GoT explore many reasoning paths but are computationally expensive. Neither reuses general lessons from problems already… 3. **[TC–RAG: Turing–Complete RAG's Case study on Medical LLM Systems](https://md.research.elamur.ai/free/en/papers/jiang-2025-tc-rag-turing-complete-rag/)** *(2025 · 25 citations)* Retrieval-augmented generation can reduce hallucinations and stale knowledge in medical LLMs. However, existing RAG pipelines lack an explicit state variable that tells the system when to stop retrieving, so they can loop without converging or pile up noisy context. The authors propose TC–RAG, which they prove to be… 4. **[MM-Verify: Enhancing Multimodal Reasoning with Chain-of-Thought Verification](https://md.research.elamur.ai/free/en/papers/sun-2025-mm-verify-enhancing-multimodal-reasoning/)** *(2025 · 19 citations)* The paper targets two gaps in multimodal math reasoning. There is no strong verifier for checking answers from multimodal LLMs, and there is little long chain-of-thought (CoT) training data with images. The authors build two 7B models. MM-Verifier is an outcome reward model that judges whether a solution to an… 5. **[AgenticRAGTracer: A Hop-Aware Benchmark for Diagnosing Multi-Step Retrieval Reasoning in Agentic RAG](https://md.research.elamur.ai/free/en/papers/you-2026-agenticragtracer-hop-aware-benchmark-diagnosing/)** *(2026 · 1 citation)* Popular multi-hop QA benchmarks such as HotpotQA, 2WikiMultihopQA and MuSiQue give only a question and its final answer. 6. **[CodeFlowBench: A Multi-turn, Iterative Benchmark for Complex Code Generation](https://md.research.elamur.ai/free/en/papers/wang-2026-codeflowbench-multi-turn-iterative-benchmark/)** *(2026 · 1 citation)* Most code-generation benchmarks test LLMs in a single turn, but real software is built step by step from modular functions that reuse earlier ones. The authors call this incremental, reuse-driven process "codeflow" and present CodeFlowBench as the first benchmark for evaluating it. 7. **[SciFlow-Bench: Evaluating Structure-Aware Scientific Diagram Generation via Inverse Parsing](https://md.research.elamur.ai/free/en/papers/zhang-2026-sciflow-bench-evaluating-structure-aware/)** *(2026 · 1 citation)* Text-to-image systems can produce scientific figures that look polished but are logically wrong: they skip steps, invent labels, or point arrows in the wrong direction. 8. **[Beyond Explicit Refusals: Soft-Failure Attacks on Retrieval-Augmented Generation](https://md.research.elamur.ai/free/en/papers/zhang-2026-beyond-explicit-refusals-soft-failure/)** *(2026)* Known jamming attacks on Retrieval-Augmented Generation (RAG) make the system refuse to answer. Such refusals are easy to spot, and the injected text often has unusually high perplexity. This paper defines a quieter availability threat called soft failure. Here the model still writes a fluent, on-topic reply, but it… 9. **[Reinforcement Learning with Semantic Rewards Enables Low-Resource Language Expansion without Alignment Tax](https://md.research.elamur.ai/free/en/papers/su-2026-reinforcement-learning-semantic-rewards-enables/)** *(2026)* When LLMs are adapted to a poorly supported language, they often lose ground on skills they already had. This is known as the alignment tax. The authors blame supervised fine-tuning (SFT): its token-level likelihood objective forces the model to copy small, skewed datasets, which overwrites pretrained knowledge. They… 10. **[Rethinking Text-to-SQL: Dynamic Multi-turn SQL Interaction for Real-world Database Exploration](https://md.research.elamur.ai/free/en/papers/sun-2026-rethinking-text-sql-dynamic-multi/)** *(2026)* Most Text-to-SQL benchmarks test one-shot translation of a fixed question into a read-only query. Real database work is different: users refine goals over several turns and often need to change data, not just read it. The authors introduce DySQL-Bench to evaluate LLM agents in this setting. It contains 1,072… 11. **[The Data Frontier for Large Language Models: Selection, Synthesis, and Tools](https://md.research.elamur.ai/free/en/papers/wu-2026-data-frontier-large-language-models/)** *(2026)* This is a tutorial abstract, not an empirical study, so it reports no experiments or benchmark figures. It argues that LLM progress now depends more on training data (its quality, variety, and mixture) than on sheer volume, and that collecting and curating such data remains expensive and difficult. The presenters… 12. **[Training Verifier to Assessing Complex Real-World Tool-Use Trajectories](https://md.research.elamur.ai/free/en/papers/sun-2026-training-verifier-assessing-complex-real/)** *(2026)* LLM agents that handle multi-turn customer-service style tasks need training dialogues that reflect real user–agent collaboration. 13. **[UniDataBench: Evaluating Data Analytics Agents Across Structured and Unstructured Data](https://md.research.elamur.ai/free/en/papers/weng-2026-unidatabench-evaluating-data-analytics-agents/)** *(2026)* In business analytics, useful conclusions often require combining several kinds of storage: relational tables, NoSQL collections, and plain-text files. ## Co-authors here 12 of 48 co-authors with a page, the most papers together first. - [Hao Liang](https://md.research.elamur.ai/free/en/authors/hao-liang/) ×4 - [Bihui Yu](https://md.research.elamur.ai/free/en/authors/bihui-yu/) ×3 - [Bin Cui](https://md.research.elamur.ai/free/en/authors/bin-cui/) ×3 - [Jingxuan Wei](https://md.research.elamur.ai/free/en/authors/jingxuan-wei/) ×3 - [Linzhuang Sun](https://md.research.elamur.ai/free/en/authors/linzhuang-sun/) ×3 - [Zhou Liu](https://md.research.elamur.ai/free/en/authors/zhou-liu/) ×3 - [Fan Yang](https://md.research.elamur.ai/free/en/authors/fan-yang/) ×2 - [Ling Yang](https://md.research.elamur.ai/free/en/authors/ling-yang/) ×2 - [Tianpeng Li](https://md.research.elamur.ai/free/en/authors/tianpeng-li/) ×2 - [Tianyu Guo](https://md.research.elamur.ai/free/en/authors/tianyu-guo/) ×2 - [Zhengren Wang](https://md.research.elamur.ai/free/en/authors/zhengren-wang/) ×2 - [Chenzheng Zhu](https://md.research.elamur.ai/free/en/authors/chenzheng-zhu/) ## 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)](https://md.research.elamur.ai/free/en/venues/acl/) ×9: [ACL 2026](https://md.research.elamur.ai/free/en/venues/acl/2026/) ×5, [ACL 2025](https://md.research.elamur.ai/free/en/venues/acl/2025/) ×2 - [Findings of the Association for Computational Linguistics](https://md.research.elamur.ai/free/en/venues/findings/) ×5: [Findings of the Association for Computational Linguistics 2026](https://md.research.elamur.ai/free/en/venues/findings/2026/) ×4 - [Conference on Neural Information Processing Systems (NeurIPS)](https://md.research.elamur.ai/free/en/venues/neural-information-processing-systems/): [NeurIPS 2024](https://md.research.elamur.ai/free/en/venues/neural-information-processing-systems/2024/) ## Cited by Papers of our library cite their works 202 times (of the 149,439 papers whose bibliographies we read); [76 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/wentao-zhang/cited-by/). Updated 2 November 2026