Koutian Wu

Koutian Wu

23 yo founder + researcher @ UT Austin, automating scientific research. Git contributor; coauthored work featured by Forbes. Owner of ASI the hamster 🐹

Sponsor

Publications

You can also find my articles on my Google Scholar profile.

BibTeX for all works: ktwu01.bib | GitHub

2027

Preprint / working paper

From Personas to Simulated Users: A Fitness-for-Purpose Survey

Submitted to AAAI 2027 Artificial Intelligence for Social Impact Track

A fitness-for-purpose survey of the progression from static personas to simulated users, submitted to the AAAI 2027 Artificial Intelligence for Social Impact Track.

BibTeX
Citation for 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.

2026

Conference / workshop

What Git Does Not Record: Provenance Legibility in Two AI-Assisted Research Repositories

NeurIPS 2026 Workshop on AI-Native Academia

Accepted as a poster at the NeurIPS 2026 Workshop on AI-Native Academia.

Paper BibTeX
Citation for What Git Does Not Record: Provenance Legibility in Two AI-Assisted Research Repositories

Wu, K., Huang, Z., & Geng, H. (2026). "What Git Does Not Record: Provenance Legibility in Two AI-Assisted Research Repositories." NeurIPS 2026 Workshop on AI-Native Academia. Accepted as a poster.

Preprint / working paper

ScienceIDE: Turning World's Scientific Codebase into Agent Learnable Environments

arXiv preprint arXiv:2609.19134

Preprint. Turns scientific codebases into environments that AI agents can learn from.

Paper BibTeX
Citation for ScienceIDE: Turning World's Scientific Codebase into Agent Learnable Environments

Geng, H., et al. (including Wu, K.) (2026). "ScienceIDE: Turning World's Scientific Codebase into Agent Learnable Environments." arXiv preprint arXiv:2609.19134.

Preprint / working paper

Benchmark Radar: A Living Database and Search Engine for AI Benchmarks and Evaluation

arXiv preprint arXiv:2609.11115

Preprint. A living database and search engine for AI benchmarks and evaluation.

Paper BibTeX
Citation for Benchmark Radar: A Living Database and Search Engine for AI Benchmarks and Evaluation

Wu, K., Zhou, J., Shang, E., Wang, J., Han, P., Wang, J., Xu, W., Lu, S., & Shi, L. (2026). "Benchmark Radar: A Living Database and Search Engine for AI Benchmarks and Evaluation." arXiv preprint arXiv:2609.11115.

Conference / workshop

Cartographer in the Loop: Interactive Land Cover Change Screening Using Geospatial Foundation Model Embeddings

CaGIS 2026

Conference paper at CaGIS 2026 on interactive land cover change screening with geospatial foundation model embeddings.

BibTeX
Citation for Cartographer in the Loop: Interactive Land Cover Change Screening Using Geospatial Foundation Model Embeddings

Yao, X., Wu, K., Bhatt, R., Kim, M., & Kang, Y. (2026). "Cartographer in the Loop: Interactive Land Cover Change Screening Using Geospatial Foundation Model Embeddings." CaGIS 2026.

Preprint / working paper

ASI-Bench: At the Dawn of Artificial Superintelligence

arXiv preprint arXiv:2608.17271

A benchmark with 60 project-level tasks across 11 scientific domains that evaluates frontier models on open-ended scientific research beyond human-expert benchmarks.

Paper BibTeX
Citation for ASI-Bench: At the Dawn of Artificial Superintelligence

Zhou, J., et al. (including Wu, K.) (2026). "ASI-Bench: At the Dawn of Artificial Superintelligence." arXiv preprint arXiv:2608.17271.

Preprint / working paper

MicroVerse: An Instrument for Measuring Self-Authored Identity Drift in Long-Horizon Multi-Agent Language-Model Simulations

arXiv preprint arXiv:2608.15844

A behavioral-science instrument that measures identity drift in generative agents carrying an immutable “soul file” through a resource-scarce, long-horizon multi-agent simulation.

Paper BibTeX
Citation for MicroVerse: An Instrument for Measuring Self-Authored Identity Drift in Long-Horizon Multi-Agent Language-Model Simulations

Ng, S., et al. (including Wu, K.) (2026). "MicroVerse: An Instrument for Measuring Self-Authored Identity Drift in Long-Horizon Multi-Agent Language-Model Simulations." arXiv preprint arXiv:2608.15844.

Preprint / working paper

MatrAIx: Simulating the World with 8.3 Billion Persona Agents

arXiv preprint arXiv:2608.04205

A population-scale simulated-user evaluation infrastructure with 8.3 billion persona records, four interactive playground environments, and 1,010 application tasks across 25+ domains.

Paper BibTeX
Citation for MatrAIx: Simulating the World with 8.3 Billion Persona Agents

Li, X., et al. (including Wu, K.) (2026). "MatrAIx: Simulating the World with 8.3 Billion Persona Agents." arXiv preprint arXiv:2608.04205.

Preprint / working paper

ResearchClawBench: A Benchmark for End-to-End Autonomous Scientific Research

arXiv preprint; submitted to AAAI 2027

A benchmark for end-to-end autonomous scientific research across 40 tasks from 10 scientific domains, with real-paper grounding and expert-curated multimodal rubrics.

Paper BibTeX
Citation for 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.

Conference / workshop

How Does Integrating Plant Hydraulics Improve Noah-MP Land Surface Model

106th AMS Annual Meeting

Conference poster presenting the integration and evaluation of a plant hydraulics scheme in the Noah-MP land surface model.

BibTeX
Citation for How Does Integrating Plant Hydraulics Improve Noah-MP Land Surface Model

Wu, K., Li, L., Rempe, D., Matheny, A., Mbarak, M., & Yang, Z.-L. (2026). "How Does Integrating Plant Hydraulics Improve Noah-MP Land Surface Model." Poster presented at the 106th AMS Annual Meeting, Houston, TX.

Book chapter

On the Ethics of Generative GeoAI: Explainability, Bias, Hallucination, Accountability, Privacy, and Trust

Geography According to Foundation Models, Vol. 422, IOS Press

Peer-reviewed book chapter reviewing key ethical issues in generative GeoAI. Wu authored Section 8, “Trust in AI and GeoAI Models,” covering geo-hallucination, uncertainty as an ethical requirement, and provenance-aware protocols.

Paper BibTeX
Citation for 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.

Preprint / working paper

ESM-bench: A Benchmark for Evaluating Whether AI Agents Understand Earth System Model Physics and Code

Preprint (Zenodo); in preparation for NeurIPS Datasets and Benchmarks

Preprint. A 243-task benchmark testing whether AI agents understand Earth System Model physics and code, with multi-model evaluation, a classification rubric, precision/recall/F1 scoring, and leakage detection. In preparation for NeurIPS Datasets and Benchmarks.

Paper BibTeX
Citation for 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

2025

Preprint / working paper

Noah-Agent: A Multi-Expert AI Agent Framework for Automated Parameterization and Validation of Large-Scale Fortran Climate Models (v0.1)

Preprint (Zenodo); in preparation

Preprint. A multi-expert AI agent framework for automated parameterization and validation of large-scale Fortran climate models. Version 0.1, in preparation.

Paper BibTeX
Citation for 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

2024

Journal article

Diurnal and seasonal variations of meteor speed and arrival angle observed by Mengcheng meteor radar

JGR: Space Physics

This study investigates diurnal and seasonal variations of meteor speed and arrival angle using Mengcheng meteor radar observations, providing insights into meteoroid dynamics in the mesosphere and lower thermosphere.

Paper BibTeX
Citation for 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.

Journal article

A Summary Report on the Space Physics Practical Education in 2022

Review of Geophysics and Planetary Physics

A comprehensive report on space physics practical education initiatives in 2022, documenting educational programs and outcomes in space science education.

Paper BibTeX
Citation for 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.

2023

Conference / workshop

Perturbations by the 2022 Hunga-Tonga Volcano Eruption in the MLT Region Investigated Using the WACCM-X Simulation and Meteor Radar Observations

AGU Fall Meeting 2023

AGU Fall Meeting abstract studying wave perturbations from the 2022 Hunga-Tonga eruption in the mesosphere and lower thermosphere using WACCM-X simulations and meteor radar observations.

Paper BibTeX
Citation for Perturbations by the 2022 Hunga-Tonga Volcano Eruption in the MLT Region Investigated Using the WACCM-X Simulation and Meteor Radar Observations

Wu, K., Liu, H.-L., Yi, W., & Xue, X. (2023). "Perturbations by the 2022 Hunga-Tonga Volcano Eruption in the MLT Region Investigated Using the WACCM-X Simulation and Meteor Radar Observations." AGU Fall Meeting Abstracts, SA33B-2892.