Tianyang Liu

Curriculum vitae

Tianyang Liu

Ph.D. candidate in Computer Science, UC San Diego. Expected to graduate in early 2027.

San Diego, CAtil040@ucsd.eduleoii22.comGoogle ScholarGitHubLinkedIn

I study the understanding, evaluation, and post-training of LLMs and AI agents, with an emphasis on their behavior across diverse real-world settings. My work develops methods and evaluations that better reflect practical utility and user experience.

Official PDFOct 2026

Education

3 degrees, 2018 –⁠ 2027

  1. Ph.D.

    2024 – 2027, expected

    Ph.D. in Computer Science

    University of California, San DiegoSan Diego, CA, USA

    Advisor: Julian McAuley

  2. M.S.

    2022 – 2024

    M.S. in Computer Science

    University of California, San DiegoSan Diego, CA, USA

    Advisors: Zhiting Hu, Julian McAuley · GPA 4.00 / 4.00

  3. B.Eng.

    2018 – 2022

    B.Eng. in Software Engineering

    Wuhan UniversityWuhan, Hubei, China

    Advisors: Peng Liang, Chong Wang · GPA 3.85 / 4.00

Industry research

3 internships, 2024 –⁠ 2026

  1. Snowflake

    Sep 2025 – Mar 2026

    Snowflake

    Part-time Research Scientist InternRemote

    Developed an AI SQL benchmark for evaluating LLMs on real-world workflows.

  2. Amazon

    Jun – Sep 2025

    Amazon AWS, Developer Q Team

    Applied Scientist InternSanta Clara, CA, USA

    Evaluated LLM-generated UIs across usability, interactivity, and aesthetics.

  3. NVIDIA

    Apr – Sep 2024

    NVIDIA

    Summer InternSanta Clara, CA, USA

    Built a CUDA optimization agent that uses profiler feedback to improve generated kernel performance.

Publications

19 papers, *equal contribution

  1. 2026

    1. CocoaBench: Evaluating Unified Digital Agents in the Wild

      Shibo Hao, Zhining Zhang, Zhiqi Liang, Tianyang Liu, Yuheng Zha, Qiyue Gao, Jixuan Chen, Zilong Wang, Zhoujun Cheng, Haoxiang Zhang, Junli Wang, Hexi Jin, and 19 more authors

      COLM 2026

      arXivBlogCodeLeaderboard

    2. Spider 2.0-AIFunc: Extending Real-World Text-to-SQL to AI-Native SQL Workflows

      Tianyang Liu, Canwen Xu, Fangyu Lei, Nikki Lijing Kuang, Jixuan Chen, Tao Yu, Julian McAuley, Zhewei Yao, and Yuxiong He

      Preprint 2026

      arXivCode

    3. BigCodeArena: Unveiling More Reliable Human Preferences in Code Generation via Execution

      Terry Yue Zhuo, Xiaolong Jin, Hange Liu, Juyong Jiang, Tianyang Liu, Chen Gong, Bhupesh Bishnoi, Vaisakhi Mishra, Marek Suppa, Noah Ziems, Saiteja Utpala, Ming Xu, and 28 more authors

      COLM 2026

      arXivBlogCodeWebsite

  2. 2025

    1. Decompose to Compose: Multidimensional Evaluation of LLM-Generated UIs

      Tianyang Liu, Xiaoyang Wang, Zijian Wang, Murali Krishna Ramanathan, and Varun Kumar

      Pending

    2. You Don’t Know Until You Click: Automated GUI Testing for Production-Ready Software Evaluation

      Yutong Bian, Xianhao Lin, Yupeng Xie, Tianyang Liu, Mingchen Zhuge, Siyuan Lu, Haoming Tang, Jinlin Wang, Jiayi Zhang, Jiaqi Chen, Xiangru Tang, Yongxin Ni, and 2 more authors

      Preprint 2025

      arXivCode

    3. Revisiting Reinforcement Learning for LLM Reasoning from A Cross-Domain Perspective

      Zhoujun Cheng*, Shibo Hao*, Tianyang Liu*, Fan Zhou, Yutao Xie, Feng Yao, Yuexin Bian, Yonghao Zhuang, Nilabjo Dey, Yuheng Zha, Yi Gu, Kun Zhou, and 12 more authors

      NeurIPS 2025

      arXivBlogCodeDatasetModel

    4. Decentralized Arena: Towards Democratic and Scalable Automatic Evaluation of Language Models

      Yanbin Yin, Kun Zhou, Zhen Wang, Xiangdong Zhang, Yifei Shao, Shibo Hao, Yi Gu, Jieyuan Liu, Somanshu Singla, Tianyang Liu, Eric P. Xing, Zhengzhong Liu, and 2 more authors

      Preprint 2025

      arXivBlog

    5. Code to Think, Think to Code: A Survey on Code-Enhanced Reasoning and Reasoning-Driven Code Intelligence in LLMs

      Dayu Yang*, Tianyang Liu*, Daoan Zhang*, Antoine Simoulin, Xiaoyi Liu, Yuwei Cao, Zhaopu Teng, Xin Qian, Grey Yang, Jiebo Luo, and Julian McAuley

      EMNLP 2025 (main)

      arXiv

    6. Symbolic Representation for Any-to-Any Generative Tasks

      Jiaqi Chen, Xiaoye Zhu, Yue Wang, Tianyang Liu, Xinhui Chen, Ying Chen, Chak Tou Leong, Yifei Ke, Joseph Liu, Yiwen Yuan, Julian McAuley, and Li-jia Li

      CVPR 2025

      arXiv

    7. Imitate Before Detect: Aligning Machine Stylistic Preference for Machine-Revised Text Detection

      Jiaqi Chen*, Xiaoye Zhu*, Tianyang Liu*, Ying Chen, Xinhui Chen, Yiwen Yuan, Chak Tou Leong, Zuchao Li, Long Tang, Lei Zhang, Chenyu Yan, Guanghao Mei, and 2 more authors

      AAAI 2025Oral Presentation

      arXivBlogCodeDemo

  3. 2024

    1. Dynamic Rewarding with Prompt Optimization Enables Tuning-free Self-Alignment of Language Models

      Somanshu Singla*, Zhen Wang*, Tianyang Liu, Abdullah Ashfaq, Zhiting Hu, and Eric P. Xing

      EMNLP 2024 (main)

      arXivCode

    2. LLM Reasoners: New Evaluation, Library, and Analysis of Step-by-Step Reasoning with Large Language Models

      Shibo Hao*, Yi Gu*, Haotian Luo*, Tianyang Liu, Xiyan Shao, Xinyuan Wang, Shuhua Xie, Haodi Ma, Adithya Samavedhi, Qiyue Gao, Zhen Wang, and Zhiting Hu

      COLM 2024Also to appear at Large Language Model (LLM) Agents workshop at ICLR 2024

      arXivCode

    3. StarCoder 2 and The Stack v2: The Next Generation

      Anton Lozhkov, Raymond Li, Loubna Ben Allal, Federico Cassano, Joel Lamy-Poirier, Nouamane Tazi, Ao Tang, Dmytro Pykhtar, Jiawei Liu, Yuxiang Wei, Tianyang Liu, Max Tian, and 54 more authors

      Technical Report 2024

      arXivBlogCode

    4. Rethinking Tabular Data Understanding with Large Language Models

      Tianyang Liu, Fei Wang, and Muhao Chen

      NAACL 2024

      arXivCode

    5. RepoBench: Benchmarking Repository-Level Code Auto-Completion Systems

      Tianyang Liu, Canwen Xu, and Julian McAuley

      ICLR 2024

      arXivCode

  4. 2023

    1. ToolkenGPT: Augmenting Frozen Language Models with Massive Tools via Tool Embeddings

      Shibo Hao, Tianyang Liu, Zhen Wang, and Zhiting Hu

      NeurIPS 2023Oral (67 out of 12345 submissions), Best Paper Award at SoCal NLP 2023

      arXivCodePoster

    2. Architecture Decisions in AI-based Systems Development: An Empirical Study

      Beiqi Zhang, Tianyang Liu, Peng Liang, Chong Wang, Mojtaba Shahin, and Jiaxin Yu

      SANER 2023

      arXiv

    3. RoseMatcher: Identifying the Impact of User Reviews on App Updates

      Tianyang Liu, Chong Wang, Kun Huang, Peng Liang, Beiqi Zhang, Maya Daneva, and Marten van Sinderen

      IST 2023

      arXiv

  5. 2021

    1. The Role of User Reviews in App Updates: A Preliminary Investigation on App Release Notes

      Chong Wang*, Tianyang Liu*, Peng Liang, Maya Daneva, and Marten van Sinderen

      APSEC 2021

      arXiv

Service and talks

since 2023

  1. 2023 – 2026

    Reviewer

    ACL ARR, NeurIPS, ICLR, ICML, COLM, AAAI, AISTATS, NLPCC

  2. Invited speaker

    LlamaIndex Seminar on Tabular Data Understanding

Honors and awards

3 honors, 2021 –⁠ 2024

  1. 2024

    Honorable Mention for Excellence in Research

    CSE Department Award, UC San Diego

  2. 2023

    Best Paper Award

    SoCal NLP Symposium

  3. 2021

    Second Level Scholarship

    Wuhan University

To keep a copy, or download the official PDF (October 2026).