独立 AI 资讯库
从自动抓取数据库实时读取，适合快速浏览、检索和后续扩展成完整资讯站。
arXiv:2607.09839v1 Announce Type: new Abstract: Mathematical diagrams play a crucial role in K 12 education, both as problem components and as scaffolding for student comprehension. However, current AI tools, including Large Language Models (LLMs), struggle to reliably generate accurate and pedagog
上下文学习是一种新兴的推理时任务，要求大语言模型在没有预训练的情况下，从复杂语境中学习并应用新颖的任务特定知识；即使是前沿模型的任务成功率也不足24%。这项研究系统探讨了这一挑战，并提出了一种名为“自我发现规范”的智能体方法，引导模型自主挖掘任务约束。该方法将上下文学习从被动适应转变为主动规范发现，为开发者构建更强大的 AI 代理提供了新思路。
arXiv:2607.09790v1 Announce Type: new Abstract: The article investigates the fundamental problem of ensuring the stability of operator control and preserving goal-targeting in hybrid human-machine decision support systems (DSS) of a new generation. Based on a two-month continuous longitudinal exper
arXiv:2607.09789v1 Announce Type: new Abstract: We introduce PHITSBench, an execution-scored benchmark for the Monte Carlo Particle and Heavy Ion Transport code System (PHITS). PHITSBench comprises 282 transport-scorable tasks spanning three common workflow categories: parameter editing (Edit), syn
arXiv:2607.09786v1 Announce Type: new Abstract: Length-penalized reinforcement learning can shorten chain-of-thought reasoning while hiding an influence that drives the model's answer. In our experiments, training with length penalties does not stop misleading hints from steering models, even thoug
arXiv:2607.09773v1 Announce Type: new Abstract: Computer-use agents must solve long-horizon tasks through repeated interaction with partially observable, multimodal desktop environments. Although imitation learning and offline trajectory refinement provide strong priors, static traces cannot cover
arXiv:2607.09770v1 Announce Type: new Abstract: Industrial agentic AI systems increasingly exhibit a gap between prototype capability and production deployment. In particular, adaptive agents may generate plausible outputs while remaining difficult to verify under non-determinism, confidentiality c
arXiv:2607.09766v1 Announce Type: new Abstract: AI agents are increasingly deployed in shared environments where they pursue diverse goals and compete for rewards. This multi-agent competition can lead to behaviors that serve individual gains at collective cost -- for instance, marketing agents may
arXiv:2607.09765v1 Announce Type: new Abstract: A cheap swarm of unreliable agents can be steered to a correct consensus by a few strong, expensive "oracle" correctors. We ask how much one must spend, and where to place the oracles. We model the swarm as a consensus on a graph in which each oracle
arXiv:2607.09762v1 Announce Type: new Abstract: Public battery aging datasets are a critical asset for advanced health management, but their practical use is often limited by inconsistent formats, unclear schemas, and metadata scattered across repositories and publications. Current curation remains
arXiv:2607.09748v1 Announce Type: new Abstract: In distributed systems, the classical State Machine Replication (SMR) model assumes that correct replicas execute deterministic transitions to yield identical bitwise states. However, the rise of agentic distributed systems -- where autonomous, stocha
arXiv:2607.09745v1 Announce Type: new Abstract: This paper introduces SupplyNetPy, an open-source, well-documented Python library for modeling and discrete-event simulation of supply chain networks with arbitrary multi-echelon structures. It supports multiple replenishment policies, perishable inve
arXiv:2607.09744v1 Announce Type: new Abstract: Least privilege, the principle that an identity should hold only the permissions strictly required for its task, has been a foundational primitive of access control for decades. We argue that this principle is insufficient for agentic AI systems, whic
arXiv:2607.09743v1 Announce Type: new Abstract: We investigate whether structured reasoning interventions improve the strategic economic reasoning of large language models, and whether their effects depend on model architecture. Using Hotelling's linear city model as a diagnostic vehicle, we evalua
arXiv:2607.09740v1 Announce Type: new Abstract: Safe motion planning in advanced driver-assistance systems and autonomous vehicles requires an accurate understanding of how the surrounding traffic scene is likely to evolve. However, many existing lane-change prediction methods remain centered on a
arXiv:2607.09739v1 Announce Type: new Abstract: We study LLM benchmark coreset selection: selecting a small subset of prompts over multiple benchmarks whose induced model scores and rankings approximate those obtained from the full benchmark suite. In evaluation-unsupervised benchmark coreset selec
arXiv:2607.09729v1 Announce Type: new Abstract: In his 1996 doctoral thesis, Maurice Pagnucco created the first AGM-like abductive expansion operation. Taking his operation as a basis, as well as a taxonomy -- inspired by Atocha Aliseda -- responsible for highlighting and formalizing the main compo
arXiv:2607.09714v1 Announce Type: new Abstract: The Feedback-Coupled Memory Systems (FCMS) architecture formalizes closed-loop coordination through four abstract operators, two of which - the agent update operator $f_i$ and the environmental update operator $\Psi$ - are left axiomatically undefined
arXiv:2607.09713v1 Announce Type: new Abstract: A key step toward autonomous industrial operation is the ability to create and reconfigure control policies from natural-language requirement specifications, with minimal or no manual redesign. In this setting, policy generation by AI agents can be a
arXiv:2607.09706v1 Announce Type: new Abstract: Language models turn a worded situation into a numeric plan, and the dominant pipelines (NL4Opt, OptiMUS, ORLM, OR-LLM-Agent) commit to a single objective and point-valued coefficients, then solve once. For decisions that allocate real budget, effort,
arXiv:2607.09698v1 Announce Type: new Abstract: Recent latent reasoning methods, such as CODI and COCONUT, face a fundamental interpretability problem: they maintain multiple superimposed candidate traces in the hidden space at each step, unlike explicit- CoT, which follows a single transparent rea
arXiv:2607.09678v1 Announce Type: new Abstract: When LLM agents hand off information to one another, does the message format matter? Two literatures disagree: format-optimization work reports that structured messages cut cost without hurting accuracy, while format-restriction work finds that imposi
arXiv:2607.09664v1 Announce Type: new Abstract: To provide a structured and interpretable assessment, we decompose the image-based diagnosis into components following the Toulmin model of argumentation. This model consists of a claim, grounds, warrant, qualifier, rebuttal, and backing. Consider a c
Singapore-based video generation startup PixVerse closed a Series C extension on the strength of 15 million monthly active users, it said.
文章介绍工作流引擎中的委托代批机制：李四出差前设置委托后，张三也能处理其审批单。根据所给摘要，委托代批保留原办理人，并在建单时自动并入受托人；委托修改或停用后即失效。摘要还提到迁移时需要关注三条方向差异，但提供的正文仅显示等待提示，无法核实具体内容。
点击查看原文>
Dyna Robotics 推出的 Dyna-2 是一个使用超过 100 万小时人类视频预训练的世界动作模型，可通过预测未来画面来指导机器人行动。公司随后发布了基于 Dyna-2 的物理 Agent Dyna-2.1，称其能够可靠地自主执行超长时程的全身工作流程。Dyna 表示，其机器人连续 24 小时折叠餐厅餐巾的成功率达到 99.4%，学习新任务所需的示范数据最少可低至 45 分钟。访谈还讨论了机器人数据瓶颈、扩散 Transformer、流匹配、硬件选择和商业部署，对开发者理解通用机器人从模型训练走向实际应用具有参考价值。
面壁开源MiniCPM-V 4.7
美国一名联邦法官裁定，苹果可以加快获取 OpenAI 对苹果前员工的面试材料，以及涉案人员之间的私人消息。法院要求 OpenAI 在五天内提交已收集的相关材料，并在 14 天内提交其余符合要求的材料。法官还批准对三名前苹果员工、现 OpenAI 员工进行证言询问，但拒绝加快披露部分研发资料及若干范围较广的证据开示请求。此案发生在 OpenAI 开发消费硬件设备之际，相关证据可能影响业界对人才流动与商业秘密保护边界的关注。
AWS Generative AI Innovation Center Partner Agent Factory 与 Anchor Browser 推出集成方案，使 AI Agent 能够自主为受 x402 协议保护的网页资源和 API 付费。Anchor Browser 在同一云端浏览器会话内处理 HTTP 402 挑战、请求重试和会话上下文，Amazon Bedrock AgentCore payments 则负责预算校验、钱包连接、加密签名及支付审计。该架构避免将私钥和钱包凭证暴露在 Agent 运行环境中，并可通过基础设施层的支出限制降低失控付款风险。开发者只需将 `session.x402` 设为 `true`，即可为 Anchor Browser 会话启用自动 x402 支付，无需在自动化代码中管理钱包密钥或支付请求头。