Curriculum vitae

CV

Web CV · updated Aug 2026

General information

Full name
Chih-Hsuan (Bella) Yang
Current position
Postdoctoral Researcher, Argonne National Laboratory
Research identity
Multi-Agent Systems · AI for Science · Materials Discovery
Email
bellayang@anl.gov
Profiles

Research experience

  1. Jul 2025–present

    Postdoctoral Researcher

    Argonne National Laboratory · Lemont, Illinois

    Develops evaluation and post-training methods for reliable multi-agent scientific reasoning, including protocol routing, critique uptake, credit assignment, and large-scale experimentation on leadership computing systems.

  2. Sep 2024–Jan 2025

    Visiting Scientist

    Corteva Agriscience · Des Moines, Iowa

    Applied RLHF with preference-based insights for domain-specific model customization.

  3. Sep–Dec 2023

    AI Resident

    X, Google LLC (Google X) · Mountain View, California

    Developed multi-agent collaboration frameworks using a Mixture-of-Experts architecture with multimodal data streams.

  4. 2022

    Deep Learning Engineer Intern

    FLX AI · New York, New York

    Worked on deep representation learning and forecasting methods for image and time-series applications.

  5. Jan 2020–Jun 2025

    AI Graduate Researcher

    Iowa State University · Ames, Iowa

    Led and contributed to research in molecular language modeling, materials design, multi-fidelity learning, neural PDE solvers, and multimodal AI for biodiversity.

Education

  1. 2025

    Ph.D. · Mechanical Engineering; co-major in Computer Engineering; minor in Applied Mathematics

    Iowa State University

  2. 2025

    M.S. · Computer Science

    Iowa State University

  3. 2019

    B.S. · Bioenvironmental Systems Engineering

    National Taiwan University

Doctoral dissertationAI for Materials Design: Generative AI with Multi-Fidelity Strategies

Research areas

Scholarly work

Google Scholar ↗
  1. 2026
    Wrong but Useful: Trajectory Value Beyond Answer Correctness in Multi-Agent MessagesarXiv preprint, 2026
  2. 2026
    LLMs Can Predict Failure Risk, But Struggle to Predict Which Collaboration Protocol Pays Off: Cost-Aware Protocol Routing Across Reasoning TasksarXiv preprint, 2026
  3. 2026
    Precise but Uncoupled: Reviewer Precision Does Not Guarantee Critique Uptake in Multi-Agent Math ReasoningarXiv preprint, 2026
  4. 2026
    MolGen-Transformer: A Molecule Language Model for the Generation and Latent Space Exploration of Organic MoleculesComputational Materials Science 269, 114549, 2026
  5. 2025
    Who Gets the Reward & Who Gets the Blame? Evaluation-Aligned Training Signals for Multi-LLM AgentsLAW 2025 Workshop at NeurIPS 2025; revised 2026
  6. 2025
    Evaluating Molecular Similarity Measures: Do Similarity Measures Reflect Electronic Structure Properties?Journal of Chemical Information and Modeling 65(9), 4311–4319, 2025
  7. 2024
    BioTrove: A Large Curated Image Dataset Enabling AI for BiodiversityAdvances in Neural Information Processing Systems 37, Datasets and Benchmarks Track, Spotlight, 2024
  8. 2024
    Neural PDE Solvers for Irregular DomainsComputer-Aided Design 172, 103709, 2024
  9. 2024
    Google Trends as an Early Indicator of African Swine Fever Outbreaks in Southeast AsiaFrontiers in Veterinary Science 11, 1425394, 2024
  10. 2024
    In the Mix: A Workshop Merging Computational Chemistry and Electrochemistry Alongside Data ScienceJournal of Chemical Education 101(11), 5060–5067, 2024
  11. 2023
    Deep Reinforcement Learning Exploration in Continuous Latent Space for Molecular DesignAAAI Workshop on AI to Accelerate Science and Engineering, 2023
  12. 2022
    Multi-Fidelity Machine Learning Models for Structure–Property Mapping of Organic ElectronicsComputational Materials Science 213, 111599, 2022
  13. 2021
    Fast Inverse Design of Microstructures via Generative Invariance NetworksNature Computational Science 1, 229–238, 2021

Mentoring & collaboration

Alongside hands-on research, I mentor students working on collaborative AI and AI for Science. I am open to research collaborations across multi-agent systems, scientific foundation models, and AI-enabled scientific discovery. Team member profiles will be added with their permission.