最新研究揭示LLM生成代码在真实仓库中的质量与注释模式，为开发者提供实用参考。
arXiv:2607.01867v1 Announce Type: cross Abstract: The use of LLMs in software development has become increasingly widespread on tasks such as code gen…
一篇实证研究，揭示大语言模型在生成代码时对自己安全性的认知偏差，关乎代码安全可靠性。
arXiv:2606.31159v1 Announce Type: cross Abstract: Large Language Models (LLMs) are rapidly transforming software development, yet their use in securit…
LLM能否精准模拟人类文化品味？论文揭示其作为调查代理的“拟人”局限与刻板杂食性。
arXiv:2606.30085v1 Announce Type: new Abstract: Large-language models have proven to be remarkable if inconsistent parrots of public attitudes and opi…
AI对在线劳动力市场的实证研究，揭示生成式技术如何重塑工作模式与就业生态。
arXiv:2308.05201v4 Announce Type: replace Abstract: Large Language Model (LLM)-based generative AI systems are general-purpose tools capable of augmen…
开源LLM在结构化输出约束下，工具调用能力被抑制的实证研究，揭示“约束税”现象。
arXiv:2606.25605v1 Announce Type: new Abstract: Tool Calling and Structured Output are two core capabilities of modern Agent systems, yet their intera…
多智能体LLM系统提示何时优化才有效？这篇论文用系统性实验给出了答案，值得AI从业者关注。
arXiv:2606.23664v1 Announce Type: new Abstract: Multi-agent systems (MAS) offer a scalable path forward for agentic AI, comprising multiple LLM-based …
揭秘LLM智能体技能如何无意间泄露你的登录凭证，基于实证研究的新发现。
arXiv:2604.03070v2 Announce Type: replace-cross Abstract: Large Language Model (LLM) agents increasingly rely on third-party skills that operate withi…
大模型能否辨别域名背后是品牌官方还是钓鱼陷阱？这项实证研究揭示了LLM的归因推理能力。
arXiv:2606.20868v1 Announce Type: cross Abstract: When a new domain resembling a popular brand appears, defenders face a fundamental ambiguity: it may…
华为Ascend NPU上OpenPangu量化的实证研究，揭秘国产芯片AI模型部署关键优化。
arXiv:2606.21257v1 Announce Type: cross Abstract: OpenPangu models are attractive targets for private and domestic large-language-model deployment, ye…
实证检验后训练策略能否让大语言模型胜任医疗ICD编码任务，揭示生成式编码的潜力与当前局限。
arXiv:2606.13940v1 Announce Type: new Abstract: Automated International Classification of Diseases (ICD) coding is a core medical-coding task for bill…
DeepSeek-R1的"啊哈时刻"背后，是真正的推理还是高级模仿？本文通过全面实证对比，解剖人类与LLM的数学推理差异。
arXiv:2606.07410v1 Announce Type: cross Abstract: The emergence of "Aha moments" in large language models, particularly DeepSeek-R1-0120, has raised t…
AI能否挑战经济学经典理论？利用知识截止点后的新数据，实证检验大模型的经济学论证能力。
arXiv:2606.05383v1 Announce Type: cross Abstract: Can artificial intelligence (AI) refute economic theory? I document experiments in which I asked sev…
专业译者能否看穿AI翻译？一项严谨实验揭示人机文本识别真相，结果或颠覆行业认知。
arXiv:2601.15828v4 Announce Type: replace-cross Abstract: This study investigates whether professional translators without prior specialized training …
一篇洞察AI情感依赖的实证论文，揭示日常AI互动如何无意识重塑人际关系，挑战主流认知
arXiv:2606.04150v1 Announce Type: new Abstract: Public discourse and emerging policy typically assume that AI emotional support is a deliberate act: a…
分子文本表示如何影响大语言模型性能？这项实证研究揭示关键发现，为化学与AI交叉领域提供新思路。
arXiv:2606.03057v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used for molecular tasks, but it remains unclear which…
成对损失估计用更少样本实现高效优化，采样技巧让机器学习实证更省力！
arXiv:2606.02345v1 Announce Type: cross Abstract: Many machine learning problems, including similarity learning, ranking, and clustering, rely on empi…
评估算法选择模型在真实场景中的泛化能力，揭示理论与实际性能差距的关键研究
arXiv:2606.02016v1 Announce Type: new Abstract: Algorithm Selection (AS) aims to automatically identify the most suitable optimization algorithm for a…
工业任务中，LLM对话式与图形化决策支持谁更优？实证对比揭示两者并非替代关系，各有适用场景。
arXiv:2605.31287v1 Announce Type: cross Abstract: Managers in manufacturing settings rely on digital interfaces to interpret operational data for deci…
400次重复实验揭示：大模型做黑客竟如此「不稳定」？首个LLM渗透测试一致性量化研究。
arXiv:2605.30096v1 Announce Type: cross Abstract: Large language models (LLMs) can autonomously conduct multi-stage cyber attacks, but the consistency…
对LLM网络代理中不同规划表示方法进行实证对比，揭示规划形式如何影响任务表现的核心发现
arXiv:2605.29927v1 Announce Type: cross Abstract: Despite recent advances, LLM-based web agents still struggle with limited exploration, omission of c…