paper-with-me

Papers

AInsteinBench: Benchmarking Coding Agents on Scientific Repositories

2025-12-24 · Titouan Duston, Shuo Xin, Yang Sun, Daoguang Zan, Aoyan Li, Shulin Xin, Kai Shen, Yixiao Chen, Qiming Sun, Ge Zhang, Jiashuo Liu, Huan Zhou, Jingkai Liu, Zhichen Pu, Yuanheng Wang, Bo-Xuan Ge, Xin Tong, Fei Ye, Zhi-Chao Zhao, Wen-Biao Han, Zhoujian Cao, Yueran Zhao, Weiluo Ren, Qingshen Long, Yuxiao Liu, Anni Huang, Yidi Du, Yuanyuan Rong, Jiahao Peng arxiv

We introduce AInsteinBench, a large-scale benchmark for evaluating whether large language model (LLM) agents can operate as scientific computing development agents within real research software ecosystems. Unlike existing scientific reasoning benchmarks which focus on conceptual knowledge, or software engineering benchmarks that emphasize generic feature implementation and issue resolving, AInsteinBench evaluates models in end-to-end scientific development settings grounded in production-grade scientific repositories. The benchmark consists of tasks derived from maintainer-authored pull requests across six widely used scientific codebases, spanning quantum chemistry, quantum computing, molecular dynamics, numerical relativity, fluid dynamics, and cheminformatics. All benchmark tasks are carefully curated through multi-stage filtering and expert review to ensure scientific challenge, adequate test coverage, and well-calibrated difficulty. By leveraging evaluation in executable environments, scientifically meaningful failure modes, and test-driven verification, AInsteinBench measures a model's ability to move beyond surface-level code generation toward the core competencies required for computational scientific research.

📄 PDF Abstract BibTeX arXiv:2512.21373

Code (0)

등록된 구현이 없습니다.

Tasks

Code Generation

Similar Papers 제목 키워드 기반

CodeDistiller: Automatically Generating Code Libraries for Scientific Coding Agents

2025-11-30 · Peter Jansen, Samiah Hassan, Pragnya Narasimha arxiv

Automated Scientific Discovery (ASD) systems can help automatically generate and run code-based experiments, but their capabilities are limited by the code they can reliably generate from parametric knowledge alone. As a…

ResearchEnvBench: Benchmarking Agents on Environment Synthesis for Research Code Execution

2026-03-06 · Yubang Wang, Chenxi Zhang, Bowen Chen, Zezheng Huai 외 arxiv

Autonomous agents are increasingly expected to support scientific research, and recent benchmarks report progress in code repair and autonomous experimentation. However, these evaluations typically assume a pre-configure…

Code Repair

SWE-Explore: Benchmarking How Coding Agents Explore Repositories

2026-06-05 · Shaoqiu Zhang, Yuhang Wang, Jialiang Liang, Yuling Shi 외 arxiv

Repository-level coding benchmarks such as SWE-bench have driven a rapid surge in the capabilities of coding agents. Yet they usually treat coding tasks as a holistic, binary prediction problem (e.g., resolved or unresol…

SWE-bench Science: Can Coding Agents Resolve Engineering Tasks in Science?

2026-08-20 · Zhipeng Xu, Jiahao Lu, Yining Zheng, Yuxin Wang 외 arxiv

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. Y…

ProjDevBench: Benchmarking AI Coding Agents on End-to-End Project Development

2026-02-02 · Pengrui Lu, Shiqi Zhang, Yunzhong Hou, Lyumanshan Ye 외 arxiv

Recent coding agents can generate complete codebases from simple prompts, yet existing evaluations focus on issue-level bug fixing and lag behind end-to-end development. We introduce ProjDevBench, an end-to-end benchmark…