arXiv subjects

Hancheng Zhao

Publications and source records attributed to Hancheng Zhao.

3 recordsLinked to original sources

arXiv2026

Differentiable Solvation Shell Model for Rational Electrolyte Design

Tailoring Li+ solvation structures has emerged as a promising design principle across multiple Li metal battery (LMB) electrolytes, with localized high concentration electrolytes (LHCE) emerging as a leading candidate. However, rational design of these electrolytes remains limited by a poor quantitative understanding of how molecular properties govern Li+ solvation shell composition. Here we introduce a mean field modeling framework, built on an Ising model, that predicts solvation shell composition from donor number (DN), acceptor number (AN), molar ratio, and molecular size. This framework is end-to-end differentiable, which enables parameterization directly from molecular dynamics (MD) solvation structures via gradient-based optimization. Focusing on LHCE, the model achieves 10.7% RMSE and R2=0.87 for shell composition, 2.3% RMSE on free solvent ratio, and further reproduces solvation trends in real LHCE electrolytes, at a fraction of MD's cost. Our model also shows good generalizability on other electrolyte systems in addition to LHCE. Analysis of its interaction terms shows that DN dominates Li+ solvation energetics, providing a thermodynamic basis for empirical DN-based design rules. We further demonstrate the model's design utility on the LiTFSI/tetraglyme (G4) system absent from training. The model identifies fluorobenzene (FB) as a promising diluent and predicts a salt-concentration window with anion-rich solvation shells and low free solvent, favorable for stable anion-derived SEIs and high oxidative stability, respectively. This prediction is validated by higher-fidelity MD. This work establishes an interpretable differentiable framework for predicting Li+ solvation shell composition, with potential to extend to other electrolyte classes.

physics.chem-ph↗

arXiv2025

Foundation Models for Discovery and Exploration in Chemical Space

Accurate prediction of atomistic, thermodynamic, and kinetic properties from molecular structures underpins materials innovation. Existing computational and experimental approaches lack the scalability required to navigate chemical space efficiently. Scientific foundation models trained on large unlabelled datasets offer a path towards navigating chemical space across application domains. Here, we develop MIST, a family of molecular foundation models with up to an order of magnitude more parameters and data than prior works. Trained using a novel tokenizer, Smirk, which comprehensively captures nuclear, electronic, and geometric information, MIST learns a diverse range of molecules. MIST models have been fine-tuned to predict more than 400 structure-property relationships and have been shown to match or exceed state-of-the-art performance across diverse benchmarks, from physiology to electrochemistry. We demonstrate the ability of these models to solve real-world problems across chemical space from multiobjective electrolyte solvent screening to stereochemical reasoning for organometallics and mixture property prediction. The clearest demonstration of a foundation model is its ability to solve problems that were neither explicit targets of training nor central to the intentions of its developers. We identify olfactory perception mapping as such a problem, and show that MIST accurately predicted scent profiles and learned a hierarchical representation of olfactory space consistent with hyperbolic geometry. We formulated hyperparameter aware Bayesian neural scaling laws which eliminate the need for hyperparameter sweeps at every scale, making training large compute-optimal models feasible on a limited compute budget. The methods and findings presented here represent a significant step towards accelerating materials discovery, design, and optimization using foundation models.

physics.chem-ph↗

arXiv2025

DREAMS: Density Functional Theory Based Research Engine for Agentic Materials Simulation

Large language model (LLM) agents can execute long-horizon scientific workflows, but their numerical outputs are difficult to trust: agents lose context, game verification checks, and can produce large volumes of plausible yet invalid results. We introduce the DFT-based Research Engine for Agentic Materials Simulation (DREAMS), a hierarchical multi-agent framework for density functional theory (DFT) built around a multi-tier safety guard. The guard applies deterministic checks wherever explicit criteria exist and scoped LLM judgment elsewhere, evaluating one parameter at a time and tracing every value to its registered source. Verification extends from tool-call time, where fabricated, laundered, or unsourced values are rejected before entering the workflow, to report time, where a judge audits the full provenance graph behind every claim; a shared canvas preserves information integrity across hundreds of steps. DREAMS achieves average errors below 1% on the Sol27LC lattice-constant benchmark, reproduces expert-level adsorption-energy differences on the CO/Pt(111) puzzle, and quantifies functional-driven uncertainty with Bayesian ensemble sampling, confirming the face-centered-cubic (FCC) site preference at the generalized gradient approximation (GGA) level. Compared with its unguarded counterpart, which reached a nearly correct answer while only 81% of its essential steps succeeded, the guarded system verifies every essential step at approximately 13 times the input tokens; verification layers can be disabled individually to balance trustworthiness against cost, and the tuned judge rules transfer across five judge models. DREAMS operates at an enhanced L2 (L2+) automation level and demonstrates capabilities approaching L3 automation, providing a path toward trustworthy, high-throughput autonomous materials simulation.

cs.AI↗