Applied Large Language Models for Science, Engineering, and Mathematics: Reasoning, Reliability and Efficient Systems

Dear Colleagues,

Large language models are now part of everyday computational work—writing and reviewing code, steering simulations, reading lab notes, and assisting with data analysis. In practice, teams still face brittle reasoning, gaps in recall for domain facts, occasional hallucinations, and hard limits on latency and cost.
This Special Issue welcomes papers that make LLMs dependable and efficient in real workflows across science, engineering, and applied mathematics. We are interested in methods and systems that improve reasoning, tighten factual grounding, automate or optimize prompting, and reduce latency and cost at production scale while preserving quality. Submissions should connect clearly to concrete use cases and demonstrate end-to-end performance, safety, and resource efficiency with transparent metrics.

Topics of interest:

• Reasoning and verification: Tool/program-augmented reasoning; self-checking and calibration; constrained decoding; protocol and safety checks for agents; and formal methods where appropriate.
• Grounding and recall: Retrieval with domain sources (databases, ontologies, knowledge graphs); citation faithfulness; and traceable and auditable explanations.
• Auto-prompting and data: Prompt discovery/tuning, test-time selection and routing, synthetic data and weak supervision, and RLHF for domain adaptation.
• System efficiency: Distillation; PEFT/LoRA; quantization; MoE; KV-cache and speculative decoding; batching/scheduling; memory management; and cloud/edge trade-offs—all aimed at latency/cost optimization with stable quality.
• Applications in computation: Computational biology/chemistry, engineering/CFD, optimization and scientific computing, symbolic math, robotics/lab automation, and computational social science.
• Evaluation and benchmarks: Task-completion and auditability metrics; online/offline evaluation; drift monitoring; negative results; and failure analyses are welcome.

Dr. Jiahong Chen
Dr. Pengbin Feng
Prof. Dr. Xuhui Peng
Dr. Zhilin Zhang
Dr. Zhengyang Lu
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 250 words) can be sent to the Editorial Office for assessment.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Computation is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 1800 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.