arXiv2026
Wrong but Useful: Trajectory Value Beyond Answer Correctness in Multi-Agent Messages
arXiv preprint, 2026.
Studies how even incorrect messages can improve downstream reasoning through their trajectory value.
Research papers
Publications
Work spanning collaborative AI, materials and molecular discovery, scientific machine learning, biodiversity, and public health. Bella's name is highlighted in each author list.
2026
arXiv2026
LLMs Can Predict Failure Risk, But Struggle to Predict Which Collaboration Protocol Pays Off: Cost-Aware Protocol Routing Across Reasoning Tasks
arXiv preprint, 2026.
Evaluates cost-aware routing across reasoning protocols and the gap between failure prediction and protocol selection.
arXiv2026
Comp. Mater.2026
MolGen-Transformer: A Molecule Language Model for the Generation and Latent Space Exploration of Organic Molecules
Computational Materials Science 269, 114549, 2026.
Introduces a transformer trained on 198 million organic molecules, with complete reconstruction and controllable latent-space generation for molecular discovery.
2025
LAW @ NeurIPS2025
Who Gets the Reward & Who Gets the Blame? Evaluation-Aligned Training Signals for Multi-LLM Agents
LAW 2025 Workshop at NeurIPS 2025; revised 2026.
Develops evaluation-aligned agent- and message-level training signals from system-level outcomes.
JCIM2025
Evaluating Molecular Similarity Measures: Do Similarity Measures Reflect Electronic Structure Properties?
Journal of Chemical Information and Modeling 65(9), 4311–4319, 2025.
Evaluates molecular fingerprints and distance metrics against electronic, redox, and optical properties across more than 350 million molecular pairs.
2024
NeurIPS2024
BioTrove: A Large Curated Image Dataset Enabling AI for Biodiversity
Advances in Neural Information Processing Systems 37, Datasets and Benchmarks Track, Spotlight, 2024.
Presents 161.9 million research-grade images across approximately 366,600 species, together with multimodal models and biodiversity benchmarks.
CAD2024
Neural PDE Solvers for Irregular Domains
Computer-Aided Design 172, 103709, 2024.
Develops a physics-informed neural framework for solving PDEs across irregular geometries and boundary conditions.
Frontiers2024
Google Trends as an Early Indicator of African Swine Fever Outbreaks in Southeast Asia
Frontiers in Veterinary Science 11, 1425394, 2024.
Studies whether online search behavior can provide an early signal of African swine fever outbreaks in Southeast Asia.
J. Chem. Ed.2024
In the Mix: A Workshop Merging Computational Chemistry and Electrochemistry Alongside Data Science
Journal of Chemical Education 101(11), 5060–5067, 2024.
Describes an interdisciplinary workshop joining computational chemistry, electrochemistry, and data science.
2023
AAAI WS2023
Deep Reinforcement Learning Exploration in Continuous Latent Space for Molecular Design
AAAI Workshop on AI to Accelerate Science and Engineering, 2023.
Explores reinforcement learning in a continuous molecular latent space for feedback-guided molecule design.
2022
Comp. Mater.2022
Multi-Fidelity Machine Learning Models for Structure–Property Mapping of Organic Electronics
Computational Materials Science 213, 111599, 2022.
Combines inexpensive low-fidelity and scarce high-fidelity simulation data for efficient organic photovoltaic structure–property prediction.
2021
Nat. Comp. Sci.2021
Fast Inverse Design of Microstructures via Generative Invariance Networks
Nature Computational Science 1, 229–238, 2021.
Uses generative invariance networks and multi-fidelity surrogates for rapid, target-conditioned photovoltaic microstructure design.