研究人员开发了 HERMES，一个旨在提高大型语言模型 (LLM) 在复杂软件工程任务中性能的工程化框架。HERMES 利用模块化、可执行的“开发基元”，将存储库组件转化为能够进行自然语言推理和自我修改的活动代理。实验表明，HERMES 的性能平均比基线框架高出 12.4%，即使使用较小的 Qwen3-8B 模型，其性能也接近 GPT-5.6 Sol 配置，同时降低了推理成本。 AI
影响 该框架有望显著提高 LLM 驱动的软件开发的可靠性和效率，可能降低成本并加速工作流程。
排序理由 该集群包含一篇详细介绍使用 LLM 进行软件工程的新框架和方法的论文。
在 Hugging Face Daily Papers 阅读 →
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
完整方法见我们的编辑标准。
arXiv:2610.07832v1 Announce Type: cross Abstract: Large language models (LLMs) equipped with terminal access have demonstrated strong capabilities in automating software engineering tasks. However, existing agents remain brittle on long-horizon workflows, where they must repeated…
Large language models (LLMs) equipped with terminal access have demonstrated strong capabilities in automating software engineering tasks. However, existing agents remain brittle on long-horizon workflows, where they must repeatedly reconstruct program state scattered across sour…
Large language models (LLMs) equipped with terminal access have demonstrated strong capabilities in automating software engineering tasks. However, existing agents remain brittle on long-horizon workflows, where they must repeatedly reconstruct program state scattered across sour…