给每个大模型回复加盖“收据”，一个开源AI网关，让AI输出变得可验证、可溯源。
Article URL: https://github.com/AxioRank/gateway/tree/main Comments URL: https://news.ycombinator.com/item?id=48880034 Points: 1 # Comments: 0
用图论框架量化大模型逻辑推理的可信度，为评估LLM可靠性提供新方法。
arXiv:2607.08017v1 Announce Type: new Abstract: Large-Language Models (LLMs) can be prone to flawed and unfaithful reasoning that decoding strategies …
用模块化预训练实现AI能力访问控制，破解双重用途困境，确保可靠部署。
arXiv:2607.08077v1 Announce Type: new Abstract: AI developers face a dual-use dilemma. An AI capability that helps one user cure a disease can help an…
Go 开发者探讨 ORM 新期望：如何平衡 SQL 控制权与查询简化？
I have been working on a Go ORM and I am trying to understand what experienced Go developers actually want from an ORM. The main problems I see: - los…
企业AI治理新范式：AGL-1将治理层作为控制平面，打造可信企业智能。
arXiv:2607.03516v1 Announce Type: cross Abstract: Enterprise artificial intelligence is moving from isolated experimentation toward operational depend…
深度探讨LLM代理在医疗场景中的可信赖性问题，为AI医疗安全提供关键研究视角。
arXiv:2607.05055v1 Announce Type: new Abstract: Healthcare appointment scheduling remains a persistent operational bottleneck, driven by manual coordi…
融合轨迹感知与证据生态，让LLM搜索代理更可信、更高效
arXiv:2605.12887v2 Announce Type: replace-cross Abstract: Web-enabled LLM agents are changing how online information influences search outcomes. Exist…
提出认证推测执行框架，用形式化证明保障不可信AI智能体在运行时的安全性，兼顾效率与可证明保证
arXiv:2606.31023v1 Announce Type: cross Abstract: Hard-constrained sequential decision systems have no certified way to spend the test-time compute of…
无需训练即可检测大模型真实性，稀疏MLP值向量方法为可信AI提供新思路。
arXiv:2509.17932v2 Announce Type: replace Abstract: Large language models (LLMs) are prone to generating factually incorrect content, motivating metho…
探讨LLM在高效学习中的可信度矛盾，引发现实思考。
Reading some threads here on HN recently, people suggest LLMs give out untrustworthy data. That makes me think they are not a good source to understan…
美国新规限制最先进大模型向“可信方”发布，是否会让市场萎缩、拖慢研发进程？值得关注的政策信号。
Sorry, I just realized, and I ask for your opinion: if now the policy of the administration at the USA is to mandate a staggered, conditional, restric…
新基准CORTEX专为3D胸部CT的多模态大语言模型设计，强调结构化推理而非仅看最终答案，让诊断结果可溯源至证据，提升可信度。
arXiv:2606.27264v1 Announce Type: new Abstract: Reasoning in multimodal large language models (MLLMs) has shown strong promise in medical imaging. How…
工信部联合产业联盟发布AI眼镜自律公约，明确禁止超范围收集个人信息，强调数据本地化处理，为智能眼镜行业树立隐私安全标杆。
IT之家 6 月 26 日消息，中国信通院 6 月 25 日宣布，在工业和信息化部信息通信管理局的指导下，中国信息通信研究院 泰尔终端实验室 联合深圳市 AI 眼镜产业联盟研究起草了《AI 眼镜可信视界自律公约》（以下简称《公约》），得到产业链上下游企业的积极响应。 2026 年 6 月 17 日，…
编程代理的“虚假成功”比失败更危险——即使通过测试，也可能完全偏离意图，威胁生产环境信任度。
arXiv:2603.25764v3 Announce Type: replace-cross Abstract: As coding agents move into production workflows, teams need to know not only whether an agen…
HN上的生产力提升去哪了？一位用户观察到AI普及后社区内容质量和可信度并未提高，引发对技术变革实际影响的反思。
At best, average credibility across HN from what I can see has remained roughly the same, though it realistically went down a bit compared to 3 years …
针对MCP-based LLM智能体的来源感知事实性验证新方法，专治AI幻觉，提升输出可信度。
arXiv:2606.18037v1 Announce Type: new Abstract: Tool-using LLM agents increasingly use the Model Context Protocol (MCP) to answer from heterogeneous e…
一句话打造可靠、受管控且值得信赖的数据智能体，值得了解。
Build grounded, governed, trustworthy data agents Discussion | Link
解决LLM生成报告的数字错误和幻觉问题，让你的AI内容在老板和SEC面前更可信。
As a graudate student who just working as management & IR, I use LLM to do daily jobs , including weekly briefing and But AI generated report looks to…
LLM API路由器的代理会泄露过多信息？这项研究用TEE可信执行环境来密封路由器，为推理服务提供安全背书。
arXiv:2606.16358v1 Announce Type: cross Abstract: Agents increasingly access large language models (LLMs) through API routers. A router terminates the…
大模型数据智能体验证难题新解，VeriGraph用图结构提升分析可信度。
arXiv:2606.16603v1 Announce Type: cross Abstract: LLM-based agents have demonstrated strong capabilities in data-intensive analytical tasks, yet their…