--- title: "Shuyan Zhou — author profile and papers" description: "Shuyan Zhou, University of Shanghai for Science and Technology: 3 papers on Elamur Research (2023–2024), h-index 15 — affiliations, topics, co-authors…" canonical: "https://research.elamur.ai/free/en/authors/shuyan-zhou/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/shuyan-zhou/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Shuyan Zhou # Shuyan Zhou Shuyan Zhou works on autonomous agents driven by large language models and on ways of evaluating and improving language generation. A recurring question in the papers here is how to test such systems under realistic conditions instead of simplified or frozen ones. The methods centre on building reproducible environments and benchmarks, and on organising existing approaches to steering model output, with work spanning [Text generation](https://md.research.elamur.ai/free/en/topics/text-generation/) and [Vision & language](https://md.research.elamur.ai/free/en/topics/multimodal/). The most cited of these papers is [WebArena](https://md.research.elamur.ai/free/en/papers/zhou-2023-webarena-realistic-web-environment-building/) (2023). It offers a self-hosted, resettable sandbox of functioning websites, populated with content drawn from real platforms such as an online store, a discussion forum, a code-hosting service and a content-management back end. Helper tools and reference material are packaged alongside them, so agents can be judged on whether tasks are actually accomplished rather than on matching a single reference sequence of actions. Also widely cited is the survey [Bridging the Gap](https://md.research.elamur.ai/free/en/papers/fernandes-2023-bridging-gap-survey-integrating-human/) (2023). It reviews how human judgments can guide natural language generation, treats feedback as a mapping from inputs and outputs to a signal, and arranges methods along a taxonomy of format, objective, use and modeling, covering both training-time and decoding-time techniques. The newest work extends the web-agent line into the visual domain. [VisualWebArena](https://md.research.elamur.ai/free/en/papers/koh-2024-visualwebarena-evaluating-multimodal-agents-realistic/) (2024) builds on the earlier framework with tasks that depend on how a page or a reference image looks, so they cannot be completed from text alone. This shifts the evaluation toward multimodal agents. The agent and generation papers are associated with [Carnegie Mellon University](https://md.research.elamur.ai/free/en/universities/carnegie-mellon-university/), where Zhou worked between 2019 and 2024. Collaborators on several of these projects include [Graham Neubig](https://md.research.elamur.ai/free/en/authors/graham-neubig/), [Daniel Fried](https://md.research.elamur.ai/free/en/authors/daniel-fried/) and [Robert Lo](https://md.research.elamur.ai/free/en/authors/robert-lo/). The feedback survey was written with a wider group of language-generation researchers. Shuyan Zhou has 3 papers in our library, in 2023–2024, most of them on [Text generation](https://md.research.elamur.ai/free/en/topics/text-generation/), [Vision & language](https://md.research.elamur.ai/free/en/topics/multimodal/); often with [Graham Neubig](https://md.research.elamur.ai/free/en/authors/graham-neubig/), [Daniel Fried](https://md.research.elamur.ai/free/en/authors/daniel-fried/), [Robert Lo](https://md.research.elamur.ai/free/en/authors/robert-lo/). 3 papers in our library · 2023–2024 [OpenAlex](https://openalex.org/A5071869999) · [ORCID](https://orcid.org/0000-0001-8815-5098) · [**h-index 15**](https://openalex.org/authors/A5071869999) · [36 works](https://openalex.org/works?filter=author.id:A5071869999) · [887 citations](https://openalex.org/works?filter=author.id:A5071869999&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [📄 3 works in our library](https://md.research.elamur.ai/free/en/authors/shuyan-zhou/#papers) · [🔗 705 citations in our library](https://md.research.elamur.ai/free/en/authors/shuyan-zhou/cited-by/) · [1 more in our library without a page yet](#also) · [⭐ Paper Star rank #2679](https://md.research.elamur.ai/free/en/paper-stars/page/27/#star-2679) 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=Shuyan+Zhou) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Shuyan+Zhou) · [dblp](https://dblp.org/search?q=Shuyan+Zhou) · [ACL Anthology](https://aclanthology.org/search/?q=Shuyan+Zhou) ## Affiliations [🎓**China University of Mining and Technology** Xuzhou · China 2021–2026 · 11 papers*current*](https://ror.org/01xt2dr21) · [🎓**University of Shanghai for Science and Technology** Shanghai · China 2026 · 1 paper*current*](https://ror.org/00ay9v204) · [🎓**Carnegie Mellon University** Pittsburgh · United States 2019–2024 · 10 papers](https://md.research.elamur.ai/free/en/universities/carnegie-mellon-university/) · [🎓**Chongqing University** Chongqing · China 2016–2020 · 9 papers](https://ror.org/023rhb549) · [🔬**State Key Laboratory of Power Transmission and Distribution Equipment and System Safety and New Technology** Chongqing 2020 · 2 papers](https://ror.org/05qwajj55) 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. ## Topics [Text generation (1)](https://md.research.elamur.ai/free/en/topics/text-generation/) · [Vision & language (1)](https://md.research.elamur.ai/free/en/topics/multimodal/) ## Works by year ### 2020s [**2024** 1 paper](https://md.research.elamur.ai/free/en/papers/koh-2024-visualwebarena-evaluating-multimodal-agents-realistic/) · [**2023** 2 papers](https://md.research.elamur.ai/free/en/authors/shuyan-zhou/year/2023/) ## Papers The most cited first (OpenAlex and our library). 1. **[WebArena: A Realistic Web Environment for Building Autonomous Agents](https://md.research.elamur.ai/free/en/papers/zhou-2023-webarena-realistic-web-environment-building/)** *(2023 · 371 citations)* Most LLM-driven web agents are built and tested in simplified or frozen settings, such as toy sites or cached page snapshots. 2. **[VisualWebArena: Evaluating Multimodal Agents on Realistic Visual Web Tasks](https://md.research.elamur.ai/free/en/papers/koh-2024-visualwebarena-evaluating-multimodal-agents-realistic/)** *(2024 · 156 citations)* Most benchmarks for autonomous web agents rely on text alone. Many everyday web tasks, however, depend on what a page or a reference picture looks like. VisualWebArena addresses this gap. It is a benchmark that extends the WebArena framework with tasks that cannot be solved without visual understanding. 3. **[Bridging the Gap: A Survey on Integrating (Human) Feedback for Natural Language Generation](https://md.research.elamur.ai/free/en/papers/fernandes-2023-bridging-gap-survey-integrating-human/)** *(2023 · 84 citations)* Large language models trained by maximum likelihood on web-scraped text can produce toxic, wrong or unhelpful output. ## Also in our library 1 more work of theirs is in our library without a page here yet; it will appear as we publish them. ## Co-authors here 12 of 16 co-authors with a page, the most papers together first. - [Graham Neubig](https://md.research.elamur.ai/free/en/authors/graham-neubig/) ×3 - [Daniel Fried](https://md.research.elamur.ai/free/en/authors/daniel-fried/) ×2 - [Robert Lo](https://md.research.elamur.ai/free/en/authors/robert-lo/) ×2 - [Aman Madaan](https://md.research.elamur.ai/free/en/authors/aman-madaan/) - [Amanda Bertsch](https://md.research.elamur.ai/free/en/authors/amanda-bertsch/) - [André F. T. Martins](https://md.research.elamur.ai/free/en/authors/andre-f-t-martins/) - [António Farinhas](https://md.research.elamur.ai/free/en/authors/antonio-farinhas/) - [Emmy Liu](https://md.research.elamur.ai/free/en/authors/emmy-liu/) - [Frank F. Xu](https://md.research.elamur.ai/free/en/authors/frank-f-xu/) - [Hao Zhu](https://md.research.elamur.ai/free/en/authors/hao-zhu/) - [José G. C. de Souza](https://md.research.elamur.ai/free/en/authors/jose-g-c-de-souza/) - [Patrick Fernandes](https://md.research.elamur.ai/free/en/authors/patrick-fernandes/) ## Cited by Papers of our library cite their works 705 times (of the 140,884 papers whose bibliographies we read); [31 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/shuyan-zhou/cited-by/).