扩散语言模型的自蒸馏新方法登上ACL 2026，生成效率与质量或迎来新突破。
arXiv:2608.22898v1 Announce Type: new Abstract: Diffusion language models (DLMs) alleviate the inherent latency bottleneck of autoregressive (AR) larg…
AI道德评估只测了一半？新研究揭示当前评测盲区，搞AI对齐的都该看看
arXiv:2608.14566v1 Announce Type: new Abstract: Recent work on evaluating the moral competence of large language models (LLMs) has focused primarily o…
纯Go重写RustDesk通信协议，逆向细节与加密管线全拆解，硬核技术分享。
RustDesk's public server now requires login, and the only official client is a desktop GUI. If you wanted to script a remote machine, pull a file, or …
ACL 2026录用，开创性提出前缀感知的局部熵最大化方法，高效实现大模型精准遗忘而不牺牲整体性能。
arXiv:2601.03190v4 Announce Type: replace Abstract: Machine unlearning aims to forget sensitive knowledge from Large Language Models (LLMs) while main…
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…
Oracle可能要为150亿美元数据中心买单70亿美元电力担保，抗议浪潮接踵而至，AI扩张遭遇“反噬”风险。
IT之家 7 月 22 日消息，参考《金融时报》近日报道，威斯康星州公共服务委员会表示将不会为 Oracle（甲骨文）提供豁免，这意味着 Oracle 可能需要为在当地建设的 150 亿美元数据中心园区提供 70 亿美元电力基建担保 ，每年产生 1 亿美元的额外成本。 威斯康星州 Port Wash…
提出公平oracle量化LLM agent“知道却做不到”的认知鸿沟，揭示感知与行动差距根源，值得关注长期决策评估的研究者深读。
arXiv:2607.13618v1 Announce Type: new Abstract: LLM agents are increasingly evaluated on multi-week decision tasks in which the state that drives cost…
智能体不再依赖自然语言，直接在潜在空间高效沟通，突破传统交互瓶颈。
arXiv:2511.09149v5 Announce Type: replace-cross Abstract: While natural language is the de facto communication medium for LLM-based agents, it present…
用MDL引导规则学习，让语言代理更会挑工具、用工具，ACL 2026长文带你秒懂核心机制。
arXiv:2601.00086v3 Announce Type: replace Abstract: Large language models (LLMs) often struggle to use tools reliably in domain-specific settings, whe…
企业AI不是万能接口，不同岗位需要量身定制的交互方式
Presented by Oracle NetSuite Every major technology transition produces a set of assumptions about where the market is headed. The assumptions are oft…
阿里摘得ACL 2026最佳资源论文奖，以Agent评测新范式突破AI前沿，国内独一份。
用进化算法迭代精炼价值，提升大模型解码质量，被ACL 2026接收的前沿研究。
arXiv:2503.02368v4 Announce Type: replace-cross Abstract: While guided decoding, especially value-guided methods, has emerged as a cost-effective alte…
长文本RAG面临虚假信息污染威胁，MIRAGE框架提出新防御策略，为生成可信长答案提供安全屏障。
arXiv:2607.05069v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) improves factuality by grounding LLMs in external evidence, but r…
新方法STAPO：选择性轨迹感知策略优化，提升LLM智能体训练效率与性能
arXiv:2607.04963v1 Announce Type: new Abstract: Reinforcement Learning (RL) is the dominant paradigm for training Large Language Model (LLM) agents on…
引入约束感知强化学习，让LLM规划不再“天马行空”，ACL 2026最新研究。
arXiv:2607.04854v1 Announce Type: new Abstract: Despite their strong reasoning capabilities and extensive world knowledge, Large Language Models (LLMs…
评估针对大模型的心理引导技术效果与可信度，为安全可控的AI应用提供新视角。
arXiv:2510.04484v2 Announce Type: replace-cross Abstract: The ability to control LLMs' emulated emotional states and personality traits is an essentia…
美团履约团队ACL 2026前沿技术，揭秘GeoRA与UserLM-R1如何用连续概率流革新推理模型。
美团业务研发平台/履约 AI 算法团队，聚焦构建大模型为基础的 Agent 技术体系，用 AI 赋能美团履约业务， 构建 Agent 自进化的运营系统。在大模型 CPT、Post-training、Agentic RL 以及多模态理解等核心前沿方向持续深耕，已在 ACL、EMNLP 等AI领域的国际…
高性能跨平台 RDF 1.2 工具包，支持 SPARQL、SHACL、ShEx 并通过 W3C 测试套件，语义网开发利器
Article URL: https://github.com/Blackcat-Informatics/purrdf/ Comments URL: https://news.ycombinator.com/item?id=48766069 Points: 1 # Comments: 1
自动化生成可定制Web环境，为GUI Agent训练提供无限规模、高保真交互场景。
arXiv:2601.04126v3 Announce Type: replace-cross Abstract: GUI agents that interact with graphical interfaces on behalf of users represent a promising …
首个评估大模型逻辑谬误鲁棒性的基准，揭示LLM在诡辩面前的漏洞，被ACL 2026收录。
arXiv:2606.31039v1 Announce Type: new Abstract: Large Language Models (LLMs) exhibit strong semantic capabilities, yet their resilience to manipulativ…