探索自精炼流程中非对称容量分配策略，揭秘资源优化与推理效率的关键突破。
arXiv:2608.21345v1 Announce Type: new Abstract: Self-refinement, typically structured as generation, critique, and revision, is a widely adopted parad…
揭秘LLM裁判在推荐解释中的全生命周期，从训练到部署的工程实践与挑战一网打尽。
arXiv:2608.18300v1 Announce Type: new Abstract: LLM-as-a-Judge, which leverages a large language model to evaluate natural language generated by anoth…
AI自我进化的边界在哪？这篇论文直面“AI设计AI”是创新还是模仿的终极拷问。
arXiv:2608.17471v1 Announce Type: new Abstract: Recent advances in LLM agents have made them increasingly capable of designing methods for complex AI …
从语义不确定性切入，为层级多智能体协作提供全新编排思路，适合关注大模型Agent与系统优化的读者。
arXiv:2608.14707v1 Announce Type: new Abstract: As large language model (LLM)-based multi-agent systems become increasingly capable, coordinating agen…
本文精选了美团技术团队被 KDD 2026 收录的 8 篇论文进行分享，这些论文覆盖了推荐大模型、生成与奖励建模框架、智能体搜索、Transformer 框架、元泛化框架等技术领域。
直达arXiv论文页，帮你快速获取AI艺术检测器鲁棒性研究的最新成果。
arXiv:2608.11643v1 Announce Type: cross Abstract: Text-to-image generative models have advanced rapidly, with modern Diffusion Transformer architectur…
别再笼统说“AI语言”了，这篇论文用语料库方法论证大模型输出其实带有个人语言习惯特征，视角新颖。
arXiv:2608.06589v1 Announce Type: cross Abstract: While large language model outputs are frequently analysed as a collective super variety termed "AI …
聚焦自主AI代理用于进攻性安全的伦理边界，安全自动化时代不可错过的思辨指南
arXiv:2607.20255v2 Announce Type: replace-cross Abstract: LLM-driven autonomous agents are reshaping offensive security. Unlike traditional penetratio…
因果发现也能讲人话？GENESIS提出可解释方法，给复杂因果推断配上一份清晰说明书，值得研究因果推理的读者细品。
arXiv:2608.03868v1 Announce Type: new Abstract: Causal Discovery (CD) from observational data faces two fundamental challenges. First, purely statisti…
多模态大模型时代，显著目标检测迎来复兴契机，这篇论文带你重新审视经典任务的未来方向。
arXiv:2607.29222v1 Announce Type: new Abstract: The zero-shot capabilities of multimodal large language models (MLLMs) are pushing salient object dete…
arXiv最新论文，在推理时动态引导指令层次结构，有效提升大模型对复杂指令的遵循能力。
arXiv:2607.26228v1 Announce Type: new Abstract: Instruction hierarchies are a core safety assumption of language model deployment: higher priority inp…
通过人机协同构建语料库，用大模型简化科学摘要，为AI辅助学术写作提供新方向。
arXiv:2607.25630v1 Announce Type: cross Abstract: Interdisciplinary research is accelerating, yet scientific papers remain difficult to understand out…
同一问题给出不同答案？这篇论文教你如何全面评估大模型可靠性，而不只看准确率。
arXiv:2607.22554v1 Announce Type: cross Abstract: Large language models (LLMs) often achieve strong accuracy on benchmarks, yet it remains unclear how…
访问 arXiv 论文页面，获取“从文本证据设计服务系统”的前沿研究，适合科研与工程实践
arXiv:2603.10400v2 Announce Type: replace Abstract: Designing service systems requires selecting among alternative configurations -- choosing the best…
解读LLM安全新漏洞：不完整提示即可绕过模型防护，ACL 2026前沿研究揭示越狱攻击新范式。
arXiv:2607.20473v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly released as open-weight models with safeguards against h…
研究揭示AI助手可能过度干预人类决策，引发对智能辅助边界的深度思考。
arXiv:2607.21306v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used as tutors and thought partners, helping users rea…
揭示2026年全球认知基础设施中的算法单一文化现象，一场悄然发生的协调奇迹如何塑造AI生成的内容世界。
On the morning of 9 April 2026, a small miracle of coordination is unfolding in the cognitive infrastructure of the planet. A graduate student in Hyde…
15页论文提出约束锚定推理痕迹方法，为AI推理提供新视角，ACM MM 2026收录。
arXiv:2607.16727v1 Announce Type: new Abstract: Autoregressive multimodal large language models (MLLMs) suffer from error snowballing: a single incorr…
深度解析AI原生企业的定义、组织架构与商业模式变革，为理解AI驱动的新型企业形态提供学术框架。
Article URL: https://download.ssrn.com/2026/6/9/6905079.pdf?response-content-disposition=inline&X-Amz-Security-Token=IQoJb3JpZ2luX2VjENT%2F%2F%2F%…
从学术视角深度剖析Qubes OS的分区隔离安全架构，展示其安全度量与公开记录中的独特价值
arXiv:2607.14587v1 Announce Type: cross Abstract: Qubes OS is a revealing case for security measurement because its architecture makes component bound…