The paper introduces Re4, a scientific computing agent that employs a four-step logical chain—rewriting, resolution, review, and revision—using three large language models: a Consultant, a Programmer, and a Reviewer. The Consultant rewrites problem descriptions by linking them to domain knowledge, the Programmer generates and runs code, and the Reviewer iteratively refines the code through self-debugging. Experiments on PDEs, fluid dynamics, ill‑conditioned linear systems, and data‑driven physics show that this collaborative framework markedly improves bug‑free code generation and execution success rates across several LLMs.
arXiv:2608. 03600v1 Announce Type: new Abstract: Partial differential equations (PDEs) become actionable in science and engineering not as isolated formulae, but as executable workflows that connect modelling assumptions, governing equations, numerical solvers, diagnostics, and decisions.
arXiv:2606. 10752v1 Announce Type: new Abstract: Numerical solvers for partial differential equations (PDEs) are core computational tools in science and engineering.
arXiv:2607. 14178v1 Announce Type: new Abstract: Recent advances in Large Language Models have fueled autonomous AI agents capable of tackling complex scientific tasks, yet existing automated research systems remain predominantly focused on empirically driven domains with quantitative benchmarks, leaving theory-driven discovery, particularly in mathematically grounded disciplines requiring rigorous proofs and synthesis of domain knowledge, largely underexplored.
SCICONVBENCH is a benchmark designed to evaluate large language models (LLMs) on multi‑turn clarification tasks in computational science. It focuses on two key abilities: eliciting missing information (disambiguation) and resolving contradictory requests (inconsistency resolution) across four domains—fluid mechanics, solid mechanics, materials science, and partial differential equations. The benchmark pairs a structured task ontology with a rubric‑based evaluation framework, measuring LLM performance in clarification behavior, conversational grounding, and final‑specification fidelity, and reveals that even top models only resolve about 52.7% of disambiguation cases in fluid mechanics while often making ungrounded assumptions.
arXiv:2606. 31229v1 Announce Type: new Abstract: Ideation plays a pivotal role in scientific discovery.
SciWalker is a framework that automatically synthesizes scientific coding problems by sampling operator chains from scientific library interfaces and using execution feedback to refine generated problem statements, solutions, and tests. It produces 8,178 high‑quality problems across five scientific domains and 32 subdomains, and training a large language model with these problems improves its scientific coding accuracy by nearly 10 percentage points. The approach combines structured workflow composition with verification and quality review to enable scalable, scientifically grounded task generation.
arXiv:2607. 29549v1 Announce Type: new Abstract: Large language models have demonstrated strong mathematical problem-solving capabilities, yet reliably verifying their candidate answers remains challenging.
arXiv:2607. 24459v1 Announce Type: new Abstract: Large language models increasingly solve scientific-computing tasks, but executable feedback from one problem rarely becomes durable capability on subsequent problems.
arXiv:2608. 09072v1 Announce Type: cross Abstract: Large language model-powered coding agents are increasingly used to modify existing code repositories, for example, by adding features or fixing bugs.
arXiv:2608. 19799v1 Announce Type: new Abstract: Software increasingly functions as part of the scientific instrument itself, making failures in scientific code capable of compromising not only program behavior but also the evidence underlying scientific conclusions.
E2E-SWE is a benchmark that tests large language models’ ability to create complete, functional software repositories from scratch. It includes 186 tasks across 11 programming languages, each requiring an agent to build an installable project based solely on a natural‑language specification and an empty workspace, while passing a hidden test suite. The benchmark was crafted by software engineers and LLMs, then refined through iterative verification by autonomous agents to ensure clarity and solvability.
arXiv:2512. 03476v3 Announce Type: replace-cross Abstract: Progress in computational science depends on complex numerical workflows that must faithfully encode physical laws, yet translating conceptual insight into reliable code remains a major bottleneck.