让科研自动化工具能自我验证执行与引用，提升可靠性。
AutoResearch: An Execution-Grounded Multi-Agent Framework for Reliable Research Workflow Automation
- 用沙盒环境运行代码并自动修复错误，确保实验可复现。
- 验证引用来源是否支持论点，避免虚假声明。
- 适合需要高可靠性的科研自动化场景，如论文撰写辅助。
自动化研究代理在生成代码、检索文献和撰写科学成果方面日益普及，但常无法验证生成的实验是否正确执行，或引用的文献是否支持所作陈述。本文提出 AutoResearch，一个以执行结果为依据的多智能体框架，用于可靠的科研工作流自动化。该系统结合了沙盒化 Python/PyTorch 执行、迭代式代码修复、引用验证、论点支持审计、决策控制以及结构化 \\(\LaTeX{}\\) 文档生成。系统将运行时错误、引用验证失败及评审代理反馈作为筛选生成科研成果的实际信号。在 HumanEval、MBPP、SciCode 子集、引用验证任务、论点支持审计以及小型端到端工作流压力测试中，相较于直接可比基线，AutoResearch 提升了执行成功率、引用有效性、局部论点支持度和工作流完成率。代码导向的智能体单独报告作为部分对比。AutoResearch 定位为面向可靠性的科研助手，而非完全自主科学家或独立的论文级基准。源代码：https://github.com/raja21068/AutoResearch
原文摘要 · Abstract (English)
Automated research agents increasingly generate code, retrieve literature, and draft scientific artifacts, but they often fail to verify whether generated experiments execute correctly or whether cited sources support generated claims. We present AutoResearch, an execution-grounded multi-agent framework for reliable research workflow automation. AutoResearch couples sandboxed Python/PyTorch execution, iterative code repair, citation verification, claim-support auditing, decision control, and structured \LaTeX{} artifact generation. The system treats runtime errors, citation-verification failures, and review-agent feedback as practical filtering signals for generated research artifacts. In controlled evaluations on HumanEval, MBPP, a SciCode subset, citation-validation tasks, claim-support auditing, and small end-to-end workflow stress tests, AutoResearch improves execution success, citation validity, local claim support, and workflow completion relative to directly comparable baselines. Code-oriented agents are reported separately as partial comparisons. AutoResearch is intended as a reliability-oriented research assistant, not as a fully autonomous scientist or a standalone manuscript-quality benchmark. Source Code: https://github.com/raja21068/AutoResearch
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。