arXiv subjects

Haojun Jia

Publications and source records attributed to Haojun Jia.

13 recordsLinked to original sources

arXiv2025

Accelerating Scientific Discovery with Autonomous Goal-evolving Agents

There has been unprecedented interest in developing agents that expand the boundary of scientific discovery, primarily by optimizing quantitative objective functions specified by scientists. However, for grand challenges in science, these objectives may only be imperfect proxies. We argue that automating objective function design is a central, yet unmet need for scientific discovery agents. In this work, we introduce the Scientific Autonomous Goal-evolving Agent (SAGA) to address this challenge. SAGA employs a bi-level architecture in which an outer loop of LLM agents analyzes optimization outcomes, proposes new objectives, and converts them into computable scoring functions, while an inner loop performs solution optimization under the current objectives. This bi-level design enables systematic exploration of the space of objectives and their trade-offs, rather than treating them as fixed inputs. We demonstrate the framework through a wide range of design applications, including antibiotics, nanobodies, functional DNA sequences, inorganic materials, and chemical processes. Notably, our experimental validation identifies a structurally novel hit with promising potency and safety profiles for E. coli in the antibiotic design task, and three de novo PD-L1 binders in the nanobody design task. These results suggest that automating objective formulation can substantially improve the effectiveness of scientific discovery agents.

cs.AI↗

arXiv2025

Evaluating Large Language Models in Scientific Discovery

Large language models (LLMs) are increasingly applied to scientific research, yet prevailing science benchmarks probe decontextualized knowledge and overlook the iterative reasoning, hypothesis generation, and observation interpretation that drive scientific discovery. We introduce a scenario-grounded benchmark that evaluates LLMs across biology, chemistry, materials, and physics, where domain experts define research projects of genuine interest and decompose them into modular research scenarios from which vetted questions are sampled. The framework assesses models at two levels: (i) question-level accuracy on scenario-tied items and (ii) project-level performance, where models must propose testable hypotheses, design simulations or experiments, and interpret results. Applying this two-phase scientific discovery evaluation (SDE) framework to state-of-the-art LLMs reveals a consistent performance gap relative to general science benchmarks, diminishing return of scaling up model sizes and reasoning, and systematic weaknesses shared across top-tier models from different providers. Large performance variation in research scenarios leads to changing choices of the best performing model on scientific discovery projects evaluated, suggesting all current LLMs are distant to general scientific "superintelligence". Nevertheless, LLMs already demonstrate promise in a great variety of scientific discovery projects, including cases where constituent scenario scores are low, highlighting the role of guided exploration and serendipity in discovery. This SDE framework offers a reproducible benchmark for discovery-relevant evaluation of LLMs and charts practical paths to advance their development toward scientific discovery.

cs.AI↗

arXiv2025

AI4X Roadmap: Artificial Intelligence for the advancement of scientific pursuit and its future directions

Artificial intelligence and machine learning are reshaping how we approach scientific discovery, not by replacing established methods but by extending what researchers can probe, predict, and design. In this roadmap we provide a forward-looking view of AI-enabled science across biology, chemistry, climate science, mathematics, materials science, physics, self-driving laboratories and unconventional computing. Several shared themes emerge: the need for diverse and trustworthy data, transferable electronic-structure and interatomic models, AI systems integrated into end-to-end scientific workflows that connect simulations to experiments and generative systems grounded in synthesisability rather than purely idealised phases. Across domains, we highlight how large foundation models, active learning and self-driving laboratories can close loops between prediction and validation while maintaining reproducibility and physical interpretability. Taken together, these perspectives outline where AI-enabled science stands today, identify bottlenecks in data, methods and infrastructure, and chart concrete directions for building AI systems that are not only more powerful but also more transparent and capable of accelerating discovery in complex real-world environments.

physics.soc-ph↗

arXiv2025

HORM: A Large Scale Molecular Hessian Database for Optimizing Reactive Machine Learning Interatomic Potentials

Transition state (TS) characterization is central to computational reaction modeling, yet conventional approaches depend on expensive density functional theory (DFT) calculations, limiting their scalability. Machine learning interatomic potentials (MLIPs) have emerged as a promising approach to accelerate TS searches by approximating quantum-level accuracy at a fraction of the cost. However, most MLIPs are primarily designed for energy and force prediction, thus their capacity to accurately estimate Hessians, which are crucial for TS optimization, remains constrained by limited training data and inadequate learning strategies. This work introduces the Hessian dataset for Optimizing Reactive MLIP (HORM), the largest quantum chemistry Hessian database dedicated to reactive systems, comprising 1.84 million Hessian matrices computed at the $\omega$B97x/6-31G(d) level of theory. To effectively leverage this dataset, we adopt a Hessian-informed training strategy that incorporates stochastic row sampling, which addresses the dramatically increased cost and complexity of incorporating second-order information into MLIPs. Various MLIP architectures and force prediction schemes trained on HORM demonstrate up to 63% reduction in the Hessian mean absolute error and up to 200 times increase in TS search compared to models trained without Hessian information. These results highlight how HORM addresses critical data and methodological gaps, enabling the development of more accurate and robust reactive MLIPs for large-scale reaction network exploration.

physics.chem-ph↗

arXiv2025

Building-Block Aware Generative Modeling for 3D Crystals of Metal Organic Frameworks

Metal-organic frameworks (MOFs) marry inorganic nodes, organic edges, and topological nets into programmable porous crystals, yet their astronomical design space defies brute-force synthesis. Generative modeling holds ultimate promise, but existing models either recycle known building blocks or are restricted to small unit cells. We introduce Building-Block-Aware MOF Diffusion (BBA MOF Diffusion), an SE(3)-equivariant diffusion model that learns 3D all-atom representations of individual building blocks, encoding crystallographic topological nets explicitly. Trained on the CoRE-MOF database, BBA MOF Diffusion readily samples MOFs with unit cells containing 1000 atoms with great geometric validity, novelty, and diversity mirroring experimental databases. Its native building-block representation produces unprecedented metal nodes and organic edges, expanding accessible chemical space by orders of magnitude. One high-scoring [Zn(1,4-TDC)(EtOH)2] MOF predicted by the model was synthesized, where powder X-ray diffraction, thermogravimetric analysis, and N2 sorption confirm its structural fidelity. BBA-Diff thus furnishes a practical pathway to synthesizable and high-performing MOFs.

physics.chem-ph↗

arXiv2025

AlphaNet: Scaling Up Local-frame-based Atomistic Interatomic Potential

Molecular dynamics simulations demand an unprecedented combination of accuracy and scalability to tackle grand challenges in catalysis and materials design. To bridge this gap, we present AlphaNet, a local-frame-based equivariant model that simultaneously improves computational efficiency and predictive precision for interatomic interactions. By constructing equivariant local frames with learnable geometric transitions, AlphaNet encodes atomic environments with enhanced representational capacity, achieving state-of-the-art accuracy in energy and force predictions. Extensive benchmarks on large-scale datasets spanning molecular reactions, crystal stability, and surface catalysis (Matbench Discovery and OC2M) demonstrate its superior performance over existing neural network interatomic potentials while ensuring scalability across diverse system sizes with varying types of interatomic interactions. The synergy of accuracy, efficiency, and transferability positions AlphaNet as a transformative tool for modeling multiscale phenomena, decoding dynamics in catalysis and functional interfaces, with direct implications for accelerating the discovery of complex molecular systems and functional materials.

cs.LG↗

arXiv2024

Generative Design of Functional Metal Complexes Utilizing the Internal Knowledge of Large Language Models

Designing functional transition metal complexes (TMCs) faces challenges due to the vast search space of metals and ligands, requiring efficient optimization strategies. Traditional genetic algorithms (GAs) are commonly used, employing random mutations and crossovers driven by explicit mathematical objectives to explore this space. Transferring knowledge between different GA tasks, however, is difficult. We integrate large language models (LLMs) into the evolutionary optimization framework (LLM-EO) and apply it in both single- and multi-objective optimization for TMCs. We find that LLM-EO surpasses traditional GAs by leveraging the chemical knowledge of LLMs gained during their extensive pretraining. Remarkably, without supervised fine-tuning, LLMs utilize the full historical data from optimization processes, outperforming those focusing only on top-performing TMCs. LLM-EO successfully identifies eight of the top-20 TMCs with the largest HOMO-LUMO gaps by proposing only 200 candidates out of a 1.37 million TMCs space. Through prompt engineering using natural language, LLM-EO introduces unparalleled flexibility into multi-objective optimizations, thereby circumventing the necessity for intricate mathematical formulations. As generative models, LLMs can suggest new ligands and TMCs with unique properties by merging both internal knowledge and external chemistry data, thus combining the benefits of efficient optimization and molecular generation. With increasing potential of LLMs as pretrained foundational models and new post-training inference strategies, we foresee broad applications of LLM-based evolutionary optimization in chemistry and materials design.

physics.chem-ph↗

arXiv2024

The Critical Metallization of Hydrogen in Pressurized LaBeH8 Hydride

Behaviours of hydrogen, such as fluidity and metallicity, are crucial for our understanding of planetary interiors and the emerging field of high-temperature superconducting hydrides. These behaviours were discovered in complex phase diagrams of hydrogen and hydrides, however, the transition mechanism of behaviours driven by temperature, pressure and chemical compression remain unclear, particularly in the processes of metallization. Until now, a comprehensive theoretical framework to quantify atomization and metallization of hydrogen in phase diagram of hydrides has been lacking. In this study, we address this gap by combining molecular dynamics and electronic structure analysis to propose a theoretical framework, which clarify the content and properties of atomic hydrogen under various temperature and pressure conditions and chemical compression exerted by non-hydrogen elements in hydrides. Applying this framework to the superconducting hydride LaBeH8, we identify three general hydrogen orderings within its phase diagram: molecular, sublattice and warm hydrogens. During the phase transition from molecule to sublattice, hydrogen exhibits different properties from three general hydrogen orderings, such as fast superionicity, metallicity and unusual atomic content response to temperature. These abnormal behaviours were defined as the critical metallization of hydrogen, which not only suggests a potential synthesis route for the metastable phase but also provides valuable insights into the complex synthetic products of superconducting hydrides.

cond-mat.mtrl-sci↗

arXiv2024

React-OT: Optimal Transport for Generating Transition State in Chemical Reactions

Transition states (TSs) are transient structures that are key in understanding reaction mechanisms and designing catalysts but challenging to be captured in experiments. Alternatively, many optimization algorithms have been developed to search for TSs computationally. Yet the cost of these algorithms driven by quantum chemistry methods (usually density functional theory) is still high, posing challenges for their applications in building large reaction networks for reaction exploration. Here we developed React-OT, an optimal transport approach for generating unique TS structures from reactants and products. React-OT generates highly accurate TS structures with a median structural root mean square deviation (RMSD) of 0.053{\AA} and median barrier height error of 1.06 kcal/mol requiring only 0.4 second per reaction. The RMSD and barrier height error is further improved by roughly 25\% through pretraining React-OT on a large reaction dataset obtained with a lower level of theory, GFN2-xTB. We envision that the remarkable accuracy and rapid inference of React-OT will be highly useful when integrated with the current high-throughput TS search workflow. This integration will facilitate the exploration of chemical reactions with unknown mechanisms.

physics.chem-ph↗

arXiv2023

Accurate transition state generation with an object-aware equivariant elementary reaction diffusion model

Transition state (TS) search is key in chemistry for elucidating reaction mechanisms and exploring reaction networks. The search for accurate 3D TS structures, however, requires numerous computationally intensive quantum chemistry calculations due to the complexity of potential energy surfaces. Here, we developed an object-aware SE(3) equivariant diffusion model that satisfies all physical symmetries and constraints for generating sets of structures - reactant, TS, and product - in an elementary reaction. Provided reactant and product, this model generates a TS structure in seconds instead of hours required when performing quantum chemistry-based optimizations. The generated TS structures achieve a median of 0.08 Å root mean square deviation compared to the true TS. With a confidence scoring model for uncertainty quantification, we approach an accuracy required for reaction rate estimation (2.6 kcal/mol) by only performing quantum chemistry-based optimizations on 14\% of the most challenging reactions. We envision the proposed approach useful in constructing large reaction networks with unknown mechanisms.

physics.chem-ph↗

arXiv2022

The 3d Transition Metal Single Atom Catalysis for Prominent Adsorption Performance Towards Cr(VI) : A First Principle Study

The reduction reaction of turning Cr(VI) into Cr(III) by appropriate oxidants together with nanoscale catalysts in contaminated soil and water received significant amount of attention for its environmental benefits. Single-atom catalysts (SACs), as an emergent new type of catalysts, show great potential for simultaneous adsorption for the Cr(VI) removal. In this work, we investigated the efficiency of 3d transitional metal (from Sc to Zn) SACs in adsorption for the Cr(VI) removal via a theoretical approach. DFT calculations were used to measure the structural and energetic of Cr(VI) (H2CrO4 and Cr2O72-) adsorption behavior on the SACs systems. The Ti-N-C has a good performance for the H2CrO4 and Cr2O72- removal and has important environmental protection significance for water purification. In addition, our results show that the binding energy of the SACs systems for H2CrO4 adsorption is found to be much less than that for Cr2O72- adsorption, indicating that reduction of Cr(VI) in Cr2O72- is energetically favorable than that of Cr(VI) in H2CrO4.

physics.chem-ph↗

arXiv2021

Noise induced new quasi-period and periods switching

We employ a typical genetic circuit model to explore how noise can influence the dynamic structure. With the increase of a key interactive parameter, the model will deterministically go through two bifurcations and three dynamic structure regions. We find that a new quasi-periodic component, which is not allowed by deterministic dynamics, will be generated by noise inducing in the first two regions, and this quasi-period will be more and more stable along with the noise increasing. Especially, in the second region, the quasi-period will compete with a stable limit cycle and perform a new transient rhythm. Furthermore, we ascertain the entropy production rate (EPR) and the heat dissipation rate (HDR), and discover a minimal value with elucidating theoretically. In the end, we unveil the mechanism of the quasi-periods forming, and show a practical biological instance. We expect that this work is helpful to solve some biological or ecological problems, such as genetic origin of periodical cicadas and population dynamics with fluctuation.

physics.bio-ph↗

arXiv2020

Ternary Hypervalent Silicon Hydrides via Lithium at High Pressure

Hydrogen is rarely observed as ligand in hypervalent species, however, we find that high-pressure hydrogenation may stabilise hypervalent hydrogen-rich materials. Focussing on ternary silicon hydrides via lithium doping, we find anions composed of hypervalent silicon with H ligands formed under high pressure. Our results reveal two new hypervalent anions: layered-SiH$_{5}^{-}$ and tricapped trigonal prismatic SiH$_{6}^{2-}$. These differ from octahedral SiH$_{6}^{2-}$ described in earlier studies. In addition, there are further hydrogen-rich structures Li$_{3}$SiH$_{10}$ and Li$_{2}$SiH$_{6+δ}$ which may be stabilised at high pressure. Our work provides pointers to future investigations on hydrogen-rich materials.

cond-mat.mtrl-sci↗