Scheduled Maintenance Notice
Please note that Researcher Profiles will be undergoing scheduled maintenance on Wednesday 7th Oct, from 8:00am to 9:00am. During this time, the Researcher Profiles system will be unavailable. We apologise for any inconvenience and appreciate your understanding.
Select Publications
By Mr Tong Xie
Preprints
, 2026, AtomWorld: A Benchmark for Evaluating Spatial Reasoning in Large Language Models on Crystalline Materials, http://dx.doi.org/10.48550/arxiv.2510.04704
, 2026, MiST: Understanding the Role of Mid-Stage Scientific Training in Developing Chemical Reasoning Models, http://dx.doi.org/10.48550/arxiv.2512.21231
, 2025, A Survey of Scientific Large Language Models: From Data Foundations to Agent Frontiers, https://arxiv.org/abs/2508.21148v2
, 2025, DrugMCTS: a drug repurposing framework combining multi-agent, RAG and Monte Carlo Tree Search, http://dx.doi.org/10.48550/arxiv.2507.07426
, 2025, Position: Intelligent Science Laboratory Requires the Integration of Cognitive and Embodied AI, http://dx.doi.org/10.48550/arxiv.2506.19613
, 2025, CheMatAgent: Enhancing LLMs for Chemistry and Materials Science through Tree-Search Based Tool Learning, https://arxiv.org/abs/2506.07551v2
, 2025, DARWIN 1.5: Large Language Models as Materials Science Adapted Learners, http://dx.doi.org/10.48550/arxiv.2412.11970
, 2025, Construction and Application of Materials Knowledge Graph in Multidisciplinary Materials Science via Large Language Model, http://dx.doi.org/10.48550/arxiv.2404.03080
, 2024, ByteScience: Bridging Unstructured Scientific Literature and Structured Data with Auto Fine-tuned Large Language Model in Token Granularity, http://dx.doi.org/10.48550/arxiv.2411.12000
, 2024, LLaMA-Berry: Pairwise Optimization for O1-like Olympiad-Level Mathematical Reasoning, http://dx.doi.org/10.48550/arxiv.2410.02884
, 2024, From Tokens to Materials: Leveraging Language Models for Scientific Discovery, http://dx.doi.org/10.48550/arxiv.2410.16165
, 2024, SciQAG: A Framework for Auto-Generated Science Question Answering Dataset with Fine-grained Evaluation, http://dx.doi.org/10.48550/arxiv.2405.09939
, 2023, DARWIN Series: Domain Specific Large Language Models for Natural Science, http://dx.doi.org/10.48550/arxiv.2308.13565
, 2023, Large Language Models as Master Key: Unlocking the Secrets of Materials Science with GPT, http://dx.doi.org/10.48550/arxiv.2304.02213
, 2022, Interdisciplinary Discovery of Nanomaterials Based on Convolutional Neural Networks, http://dx.doi.org/10.48550/arxiv.2212.02805
, Large Language Models as Materials Science Adapted Learners, http://dx.doi.org/10.21203/rs.3.rs-6752901/v1