From Personas to Simulated Users: A Fitness-for-Purpose Survey
Liu, X., et al. (including Wu, K.) (2027). "From Personas to Simulated Users: A Fitness-for-Purpose Survey." Submitted to the AAAI 2027 Artificial Intelligence for Social Impact Track.
CV - Koutian Wu | AI4Geoscience PhD Student at UT Austin
Highlights
- Seeking internships in AI Agent Development/Test/Evaluation, ML/DL/DS, and Full-Stack Engineering
- 2+ years work experience (US/International)
- 4+ years research/programming experience
- 300+ stars on GitHub
Education
- Ph.D. Student in AI for Geosciences, University of Texas at Austin, 2024 - Expected: May 2029
- TA for 1,000+ students (Rating: 4.5/5.0)
- Invited Reviewer for Planetary and Space Sciences (Elsevier, Scopus Q2)
- B.S. in Geosciences (Honors Class), University of Science and Technology of China, 2020 - 2024
- Nominated for the Highest Honor for USTC undergraduates (one of the two ESS School nominees)
- Founded one of the largest student clubs, grew from 0 to 1,300+ members. [News]
Work Experience
- AI Intern, AI Agent Knowledge Base Evaluation (Jul 2025 - Aug 2025)
- 19Pine.AI (Singapore), Remote
- Implemented a multi-dimensional evaluation system from scratch for PineAgent’s RAG knowledge base.
- Developed a data sanitization module removing 2,000+ PII entries and noise from 1,000+ call sessions.
- Extracted 3,000+ Q&A pairs (knowledge/method/strategy) from call sessions to form the evaluation dataset.
- Deployed concurrent LLM-as-judge + rule-based engine, measuring precision/recall/F1 to enable RLHF optimization.
- Full-Stack Intern, LLM Text Processing System (Jun 2025 - Jul 2025)
- ZaiwenAI.com, Beijing, China
- Developed a 3-module MVP: LLM-footprint detection, removal, and plagiarism checking for researchers.
- Built a RESTful backend with FastAPI and an asynchronous task queue with Celery + Redis.
- Created a Vue.js frontend with 9-format document upload and SSE-based real-time LLM response streaming.
- AI Consulting Expert (May 2025 - Jun 2025)
- Invited by the CEO, Keshi Edu, Remote (Beijing)
- Designed an architecture for a RAG-based knowledge base to customize student graduate program applications.
- Identified critical bugs and exposed API keys, helping avoid significant potential losses.
- Research Assistant, ML Model/Multi-agent Development (Aug 2025 - Jan 2026)
- UT Austin, Austin, TX
- Project Lead, High-Performance Computing Allocation (Aug 2025 - Present)
- NSF NCAR, Remote
- Proposed and secured NSF NCAR allocation: 1k GPU + 22k CPU hours.
- Integrating machine learning parameter calibration for a SOTA physics-based land surface model (Noah-MP).
- Developing a multi-expert AI agent system for automated parameterization for physics-based climate models.
Publications
- Wu, K., He, C., & Yang, Z.-L.* (in preparation). Noah-Agent: A Multi-Expert AI Agent Framework for Automated Parameterization and Validation of Large-Scale Fortran Climate Models [Preprint]
- Wu, K., Yi, W., Xue, X., Reid, I., & Lu, M. (2024). Diurnal and Seasonal Variations of Meteor Speed and Arrival Angle Observed by Mengcheng Meteor Radar. JGR: Space Physics. [Paper] [Code] [Data]
Skills
- Python, FastAPI, JavaScript, TypeScript, React, SQL, PyTorch, TensorFlow, LangChain, RAG
- Docker, HPC, AWS/GCP, Redis, Git, HuggingFace
Education
- Ph.D. in Geological and Earth Sciences/Geosciences, The University of Texas at Austin, Aug 2024 - May 2029
- Focus: Model Optimization of Physics-based Land Surface Models (Noah-MP, CTSM, HRLDAS)
- Activities: Model Optimization research
- Advisors: Dr. Zong-Liang Yang
- B.S. with Honors in Geological and Earth Sciences/Geosciences, University of Science and Technology of China, Sep 2020 - Jul 2024
- Founding President, USTC Student Xingyun Poetry Club (Currently 1,197+ members) 2020-2022
- Second youngest student club president in USTC history (age 17 in Sep 2021)
Work Experience
- Graduate Research Assistant (Aug 2025 - Present)
- Jackson School of Geosciences, The University of Texas at Austin
- AI for Noah-MP Land Surface Model: Implementing rock and wood moisture into the Noah-MP land surface model
- Skills: Machine Learning, Land Surface Model development
- Project Admin (Aug 2025 - Present)
- NSF NCAR - The National Center for Atmospheric Research
- Project Admin for NCAR/CISL Allocation Project UTAA0012: “Explainable AI for Improving Physics-Based Noah-MP Land Surface Modeling of Plant–Rock–Water Interactions”
- Coordinated with PI (Prof. Zong-Liang Yang, UT Austin), responsible for technical leadership and implementation
- Awarded resources: 1,000 GPU hours on NSF NCAR Derecho-GPU, 20,000 CPU core-hours on NSF NCAR Derecho, 2,000 CPU core-hours on Casper, and 2 TB campaign storage
- AI Agent Evaluation Engineer Intern (Jul 2025)
- PineAI, Shanghai, China (Remote)
- Designed and implemented AI evaluation system architecture for AI Agent knowledge base assessment
- Developed automated data anonymization algorithms processing 1000+ conversation texts with 70%+ accuracy
- Built standardized Prompt engineering workflows with LLM-powered automatic Q&A extraction
- Tech Stack: Python, Shell, FastAPI, Celery, Redis, LLM APIs
- Full-Stack LLM Developer Intern (Jun 2025 - Jul 2025)
- Beijing ZaiwenAI Technology Co., Ltd., Beijing, China (Remote)
- Independently completed full development cycle including product design, tech stack selection, full-stack development, and cloud deployment
- Built comprehensive LLM text processing system integrating text polishing, AI detection, and plagiarism reduction features
- Developed RESTful API backend using FastAPI with Celery+Redis asynchronous task queue, improving processing efficiency by 65%+
- Project: https://github.com/ktwu01/1AI-polish/
- Graduate Teaching Assistant (Aug 2024 - May 2025)
- The University of Texas at Austin
- Helped prepare course syllabus, office hours, and grade homework for ~1040 students
- Skills: Quantitative Data, Perl, Shell Scripting, Python
- Scientific Visitor (Jun 2024 - Aug 2024)
- Peking University, Beijing, China
- Hydrology and Water Resources Science, Model evaluation of Physics-based Land Surface Models
- Advisor: Prof. Peirong Lin
- Visiting Scholar (Jul 2023 - Dec 2023)
- NSF NCAR - The National Center for Atmospheric Research, Boulder, Colorado
- Research on volcanic perturbations in the MLT region using WACCM-X simulation and meteor radar observations
- Re-confirmed that a single volcano can send shockwaves around Earth, seen in simulations and observations
- Student Fellow (Oct 2021 - Feb 2024)
- Shenzhen X-Institute (A Shenzhen Government-Tsinghua Univ. Initiative)
- Skills: Quantitative Data, Scientific Communications, Analytical Reasoning, Academic Writing, Python, Scholarly Research, Machine Learning
- President & Founder (Nov 2020 - Jun 2022)
- USTC Student Xingyun Poetry Club
- Founded & Led USTC’s first poetry club, managing all operations from inception to official establishment
- Built & Managed a core team of 8 co-founders and 4 vice presidents
- Directed 25+ events, including weekly poetry salons (202+ attendees), poetry competitions, and cross-club collaborations
- Grew club to 1,096+ members as of 2025
Research Interests
- AI for Land Surface Modeling: Implementing explainable AI/ML to improve physics-based Noah-MP land surface modeling
- Plant-Rock-Water Interactions: Developing models for rock and wood moisture in land surface systems
- High Performance Computing: Utilizing GPU and CPU clusters for large-scale geoscience simulations
- Model Optimization: Physics-based land surface models including Noah-MP, CTSM, and HRLDAS
- Climate Modeling: Physics-based community climate models (e.g., WACCM)
Skills
- Programming Languages
- Python, MATLAB, Fortran, Shell Scripting, Perl, HTML, JavaScript
- AI/ML Technologies
- Machine Learning, LLM APIs, Prompt Engineering, AI Agent Evaluation, LLM-as-a-judge
- Frameworks and Tools
- FastAPI, Celery, Redis, Vue.js, LaTeX
- Geoscience Specialties
- Land Surface Model Development, Model Evaluation, High Performance Computing (HPC)
- Physics-based Land Surface Models (Noah-MP, CTSM, HRLDAS)
- Physics-based Community Climate Models (WACCM)
- Research Skills
- Quantitative Data Analysis, Scientific Communications, Academic Writing, Scholarly Research
Publications
ResearchClawBench: A Benchmark for End-to-End Autonomous Scientific Research
Xu, W., et al. (including Wu, K.) (2026). "ResearchClawBench: A Benchmark for End-to-End Autonomous Scientific Research." arXiv preprint. Submitted to AAAI 2027.
On the Ethics of Generative GeoAI: Explainability, Bias, Hallucination, Accountability, Privacy, and Trust
Mai, G., Lao, N., Zhang, J., Mao, L., Wang, Z., Wu, N., Janowicz, K., Wu, K., Rao, J., Gao, S., & Zhu, R. (2026). "On the Ethics of Generative GeoAI: Explainability, Bias, Hallucination, Accountability, Privacy, and Trust." In Geography According to Foundation Models, Vol. 422, pp. 215-232. IOS Press. DOI 10.3233/FAIA260483.
ESM-bench: A Benchmark for Evaluating Whether AI Agents Understand Earth System Model Physics and Code
Wu, K., Cao, Y., & Mai, G. (2026). "ESM-bench: A Benchmark for Evaluating Whether AI Agents Understand Earth System Model Physics and Code." Preprint, Zenodo. https://zenodo.org/records/19802836
Noah-Agent: A Multi-Expert AI Agent Framework for Automated Parameterization and Validation of Large-Scale Fortran Climate Models (v0.1)
Wu, K. (2025). "Noah-Agent: A Multi-Expert AI Agent Framework for Automated Parameterization and Validation of Large-Scale Fortran Climate Models (v0.1)." Preprint, Zenodo. https://zenodo.org/records/17862049
Diurnal and seasonal variations of meteor speed and arrival angle observed by Mengcheng meteor radar
Wu, K., Yi, W.*, Xue, X.*, Reid, I., & Lu, M. (2024). "Diurnal and seasonal variations of meteor speed and arrival angle observed by Mengcheng meteor radar." JGR: Space Physics.
A Summary Report on the Space Physics Practical Education in 2022
Wu, K.*, Xu, X., Jiang, J., & Shen, A. (2024). "A Summary Report on the Space Physics Practical Education in 2022." Review of Geophysics and Planetary Physics.
Talks
ESM-bench: Can AI Agents Understand Earth System Model Physics and Code?
Oral Presentation at 4th Annual Good Systems Smart Cities and AI Innovations Symposium, Austin, TX
Noah-MP land surface model with plant hydraulics scheme (Noah-MP-PHS) Evaluation
Poster at 106th AMS Annual Meeting, Houston, TX
An open-source geospatial AI platform based on the AlphaEarth Foundation Model
Oral Presentation at Geoscience Hackathon '25, Austin, TX
Noah-MP land surface model with plant hydraulics scheme (Noah-MP-PHS) Evaluation
Poster at Advancing Land Modeling Symposium, Austin, TX
Noah-MP land surface model with plant hydraulics scheme (Noah-MP-PHS) Evaluation
Poster at JSG Research Symposium, Austin, TX
Perturbations by the 2022 Hunga-Tonga Volcano Eruption in the MLT Region Investigated Using the WACCM-X Simulation and Meteor Radar Observations
Poster at AGU Fall Meeting 2023, San Francisco, CA
Perturbations by the 2022 Hunga-Tonga Volcano Eruption in the MLT Region Investigated Using WACCM-X Simulation and Meteor Radar Observations
Oral Presentation at 4th NASA DRIVE CGS Workshop, Boulder, CO
Teaching
Service and Leadership
- Project Admin, NCAR/CISL Allocation Project UTAA0012 (Aug 2025 - Present)
- Technical leadership and implementation of project workflows for “Explainable AI for Improving Physics-Based Noah-MP Land Surface Modeling”
- President & Founder, USTC Student Xingyun Poetry Club (Nov 2020 - Jun 2022)
- Founded USTC’s first poetry club, grew to 1,096+ members as of 2025
- Organized 25+ cultural events with 202+ attendees
- Managed team of 8 co-founders and 4 vice presidents
- Graduate Teaching Assistant, The University of Texas at Austin (Aug 2024 - May 2025)
- Course preparation, office hours, and grading for ~1040 students
Research Projects and Publications
- Perturbations by the 2022 Hunga-Tonga Volcano Eruption in the MLT Region
- Investigated using WACCM-X Simulation and Meteor Radar Observations
- Abstract: https://ui.adsabs.harvard.edu/abs/2023AGUFMSA33B2892W/abstract
- Re-confirmed that a single volcano can send shockwaves around Earth
Awards and Honors
- NSF NCAR Computational Resource Allocation (Aug 2025)
- 1,000 GPU hours on NSF NCAR Derecho-GPU
- 20,000 CPU core-hours on NSF NCAR Derecho
- 2,000 CPU core-hours on Casper
- 2 TB campaign storage
- Bachelor of Science with Honors (Jul 2024)
- University of Science and Technology of China
- Second Youngest Student Club President in USTC History (Sep 2021)
- Age 17 when elected as President of USTC Student Xingyun Poetry Club