arXiv subjects

Zhaolin Hu

Publications and source records attributed to Zhaolin Hu.

5 recordsLinked to original sources

arXiv2026

Large language model agents accelerate inverse design of metal-organic frameworks for gas separation

Metal-organic frameworks (MOFs) offer a highly modular platform for adsorptive gas separation, yet their vast reticular design space makes inverse design difficult under simultaneous constraints of chemical validity, separation performance, and structural diversity. Here, we present LEMO Agent, a large-language-model agent framework for closed-loop inverse design of gas-separation MOFs in MOFid space. LEMO Agent couples language-based candidate generation with MOFid standardization, explicit validity checking, Transformer-based property prediction, structured design memory, and multi-island exploration. Through iterative generate--validate--evaluate--remember cycles, the agent uses feedback from both successful and failed candidates to guide chemically constrained search across linker, metal, and topology choices. We evaluate LEMO Agent on CH$_4$/N$_2$ and CO$_2$/N$_2$ separation tasks. Compared with representative generative, optimization, and agentic baselines, LEMO Agent enriches high-performing candidates, improves predicted separation performance, and maintains broad chemical and topological diversity. Selected candidates are further reconstructed, evaluated by GCMC simulations, and passed through an experimental down-selection workflow based on chemical feasibility and ligand purchasability, leading to initial wet-lab synthesis and SEM characterization. These results demonstrate that large language model agents can serve as interpretable and scalable design engines for accelerating MOF discovery beyond conventional fixed-library screening.

cs.AI↗

arXiv2026

OSCAgent: Accelerating the Discovery of Organic Solar Cells with LLM Agents

Organic solar cells (OSCs) hold great promise for sustainable energy, but discovering high-performance materials is time-consuming and costly. Existing molecular generation methods can aid the design of OSC molecules, but they are mostly confined to optimizing known backbones and lack effective use of domain-specific chemical knowledge, often leading to unrealistic candidates. In this paper, we introduce OSCAgent, a multi-agent framework for OSC molecular discovery that unifies retrieval-augmented design, molecular generation, and systematic evaluation into a continuously improving pipeline, without requiring additional human intervention. OSCAgent comprises three collaborative agents. The Planner retrieves knowledge from literature-curated molecules and prior candidates to guide design directions. The Generator proposes new OSC acceptors aligned with these plans. The Experimenter performs comprehensive evaluation of candidate molecules and provides feedback for refinement. Experiments show that OSCAgent produces chemically valid, synthetically accessible OSC molecules and achieves superior predicted performance compared to both traditional and large language model (LLM)-only baselines. Representative results demonstrate that some candidates achieve predicted efficiencies approaching 18\%. The code will be publicly available.

cs.CE↗

arXiv2025

Some Studies on Stochastic Optimization based Quantitative Risk Management

Risk management often plays an important role in decision making under uncertainty. In quantitative risk management, assessing and optimizing risk metrics requires efficient computing techniques and reliable theoretical guarantees. In this paper, we introduce several topics on quantitative risk management and review some of the recent studies and advancements on the topics. We consider several risk metrics and study decision models that involve the metrics, with a main focus on the related computing techniques and theoretical properties. We show that stochastic optimization, as a powerful tool, can be leveraged to effectively address these problems.

math.OC↗

arXiv2025

GraphTARIF: Linear Graph Transformer with Augmented Rank and Improved Focus

Linear attention mechanisms have emerged as efficient alternatives to full self-attention in Graph Transformers, offering linear time complexity. However, existing linear attention models often suffer from a significant drop in expressiveness due to low-rank projection structures and overly uniform attention distributions. We theoretically prove that these properties reduce the class separability of node representations, limiting the model's classification ability. To address this, we propose a novel hybrid framework that enhances both the rank and focus of attention. Specifically, we enhance linear attention by attaching a gated local graph network branch to the value matrix, thereby increasing the rank of the resulting attention map. Furthermore, to alleviate the excessive smoothing effect inherent in linear attention, we introduce a learnable log-power function into the attention scores to reduce entropy and sharpen focus. We theoretically show that this function decreases entropy in the attention distribution, enhancing the separability of learned embeddings. Extensive experiments on both homophilic and heterophilic graph benchmarks demonstrate that our method achieves competitive performance while preserving the scalability of linear attention.

cs.CV↗

arXiv2023

Chance Constrained Program with Quadratic Randomness: A Unified Approach Based on Gaussian Mixture Distribution

This paper investigates the stochastic program with the chance constraint on a quadratic form of random variables following multivariate Gaussian mixture distribution (GMD). Under some mild conditions, it is proved that the asymptotic distribution of this kind of quadratic randomness is a univariate GMD. This finding helps to translate the chance constrained program into a more tractable one, based on which an effective branch-and-bound algorithm that takes advantage of the special structure of the problem is introduced to search the global optimal solution. Furthermore, it is shown that the error resulting from approximating the quadratic randomness with its associated asymptotic distribution can be reduced by restricting the condition numbers of covariance matrices of the multivariate GMD's components. In addition, some numerical simulations are also carried out to verify the effectiveness of this flexible and unified approach.

math.OC↗