arXiv subjects

Ryohto Sawada

Publications and source records attributed to Ryohto Sawada.

9 recordsLinked to original sources

arXiv2025

PARC: An Autonomous Self-Reflective Coding Agent for Robust Execution of Long-Horizon Tasks

We introduce PARC, a coding agent for the autonomous and robust execution of long-horizon computational tasks. PARC is built on a hierarchical multi-agent architecture incorporating task planning, execution, and a mechanism that evaluates its own actions and their outcomes from an independent context and provides feedback, namely self-assessment and self-feedback. This design enables PARC to detect and correct high-level strategic errors and sustain progress without human intervention. We evaluate PARC across computational science and data science tasks. In materials science, it autonomously reproduces key results from studies on lithium-ion conduction and alloy segregation. In particular, it coordinates dozens of parallel simulation tasks, each requiring roughly 43 hours of computation, managing orchestration, monitoring, and error correction end-to-end. In Kaggle-based experiments, starting from minimal natural-language instructions, PARC conducts data analysis and implements search strategies, producing solutions competitive with human-engineered baselines. These results highlight the potential of integrating a hierarchical multi-agent system with self-assessment and self-feedback to enable AI systems capable of independent, large-scale scientific and analytical work.

cs.AI↗

arXiv2022

Towards Universal Neural Network Potential for Material Discovery Applicable to Arbitrary Combination of 45 Elements

Computational material discovery is under intense study owing to its ability to explore the vast space of chemical systems. Neural network potentials (NNPs) have been shown to be particularly effective in conducting atomistic simulations for such purposes. However, existing NNPs are generally designed for narrow target materials, making them unsuitable for broader applications in material discovery. To overcome this issue, we have developed a universal NNP called PreFerred Potential (PFP), which is able to handle any combination of 45 elements. Particular emphasis is placed on the datasets, which include a diverse set of virtual structures used to attain the universality. We demonstrated the applicability of PFP in selected domains: lithium diffusion in LiFeSO${}_4$F, molecular adsorption in metal-organic frameworks, an order-disorder transition of Cu-Au alloys, and material discovery for a Fischer-Tropsch catalyst. They showcase the power of PFP, and this technology provides a highly useful tool for material discovery.

cond-mat.mtrl-sci↗

arXiv2020

Data Transfer Approaches to Improve Seq-to-Seq Retrosynthesis

Retrosynthesis is a problem to infer reactant compounds to synthesize a given product compound through chemical reactions. Recent studies on retrosynthesis focus on proposing more sophisticated prediction models, but the dataset to feed the models also plays an essential role in achieving the best generalizing models. Generally, a dataset that is best suited for a specific task tends to be small. In such a case, it is the standard solution to transfer knowledge from a large or clean dataset in the same domain. In this paper, we conduct a systematic and intensive examination of data transfer approaches on end-to-end generative models, in application to retrosynthesis. Experimental results show that typical data transfer methods can improve test prediction scores of an off-the-shelf Transformer baseline model. Especially, the pre-training plus fine-tuning approach boosts the accuracy scores of the baseline, achieving the new state-of-the-art. In addition, we conduct a manual inspection for the erroneous prediction results. The inspection shows that the pre-training plus fine-tuning models can generate chemically appropriate or sensible proposals in almost all cases.

cs.LG↗

arXiv2019

Extractive Summarization via Weighted Dissimilarity and Importance Aligned Key Iterative Algorithm

We present importance aligned key iterative algorithm for extractive summarization that is faster than conventional algorithms keeping its accuracy. The computational complexity of our algorithm is O($SNlogN$) to summarize original $N$ sentences into final $S$ sentences. Our algorithm maximizes the weighted dissimilarity defined by the product of importance and cosine dissimilarity so that the summary represents the document and at the same time the sentences of the summary are not similar to each other. The weighted dissimilarity is heuristically maximized by iterative greedy search and binary search to the sentences ordered by importance. We finally show a benchmark score based on summarization of customer reviews of products, which highlights the quality of our algorithm comparable to human and existing algorithms. We provide the source code of our algorithm on github https://github.com/qhapaq-49/imakita .

cs.CL↗

arXiv2019

Model-Free Cluster Analysis of Physical Property Data using Information Maximizing Self-Argument Training

We present the semi-supervised IMSAT, a versatile classification method that works without labeled data and can be tuned by little additional information. We demonstrate how semi-supervised IMSAT can classify XRD patterns and thermoelectric hysteresis curves in the same way even though their shape and dimensions are different. Our algorithm will accelerate automation of big data collection and open a way to study artificial intelligent driven material development.

physics.comp-ph↗

arXiv2018

Boosting Material Modeling Using Game Tree Search

We demonstrate a heuristic optimization algorithm based on the game tree search for multi-component materials design. The algorithm searches for the largest spin polarization of seven-component Heusler alloys. The algorithm can find the peaks quickly and is more robust against local optima than Bayesian optimization approaches using the expected improvement or upper confidence bound approaches. We also investigate Heusler alloys including anti-site disorder and show that [Fe$_{0.9}$Co$_{0.1}$]$_{2}$Cr$_{0.95}$Mn$_{0.05}$Si$_{0.3}$Ge$_{0.7}$ has the potential to be a high spin polarized material with robustness against anti-site disorder.

physics.comp-ph↗

arXiv2018

Machine-learning guided discovery of a high-performance spin-driven thermoelectric material

Thermoelectric conversion using Seebeck effect for generation of electricity is becoming an indispensable technology for energy harvesting and smart thermal management. Recently, the spin-driven thermoelectric effects (STEs), which employ emerging phenomena such as the spin-Seebeck effect (SSE) and the anomalous Nernst effect (ANE), have garnered much attention as a promising path towards low cost and versatile thermoelectric technology with easily scalable manufacturing. However, progress in development of STE devices is hindered by the lack of understanding of the mechanism and materials parameters that govern the STEs. To address this problem, we enlist machine learning modeling to establish the key physical parameters controlling SSE. Guided by these models, we have carried out a high-throughput experiment which led to the identification of a novel STE material with a thermopower an order of magnitude larger than that of the current generation STE devices.

cond-mat.mtrl-sci↗

arXiv2016

Implementation of the multiconfiguration time-dependent Hatree-Fock method for general molecules on a multi-resolution Cartesian grid

We report a three-dimensional numerical implementation of multiconfiguration time-dependent Hartree-Fock (MCTDHF) based on a multi-resolution Cartesian grid, with no need to assume any symmetry of molecular structure. We successfully compute high-harmonic generation (HHG) of H2 and H2O. The present implementation will open a way to the first-principle theoretical study of intense-field and attosecond-pulse induced ultrafast phenomena in general molecules.

physics.comp-ph↗

arXiv2014

Analysis of strong-field enhanced ionization of molecules using Bohmian trajectories

We theoretically investigate the mechanism of enhanced ionization in two-electron molecules by analyzing Bohmian trajectories for a one-dimensional H2 in an intense laser field. We identify both types of ionizing trajectories corresponding to the ejection from the up-field and down-field cores. The trajectories of the two electrons are correlated with each other in the former while correlation is negligible in the latter. The contributions from the two ionization types, though depending on laser intensity and internuclear distance, are comparable to each other.

quant-ph↗