发布日期：2026-07-03
收录条目：20
1. RAG-Anything Tutorial: Build a Multimodal Retrieval Pipeline for Text, Tables, Equations, and Images in Colab
- 来源：MarkTechPost
- 发布时间：2026-07-02 21:38 UTC
- 链接：https://www.marktechpost.com/2026/07/02/rag-anything-tutorial-build-a-multimodal-retrieval-pipeline-for-text-tables-equations-and-images-in-colab/
摘要：In this tutorial, we build a RAG-Anything workflow to explore how multimodal retrieval works across text, tables, equations, and images. We prepare a Colab environment, enter our OpenAI API key at runtime, and generate a
2. Meet Alibaba’s Page Agent: A JavaScript In-Page GUI Agent That Controls Web Interfaces With Natural Language Through the DOM
- 来源：MarkTechPost
- 发布时间：2026-07-02 20:51 UTC
- 链接：https://www.marktechpost.com/2026/07/02/meet-alibabas-page-agent-a-javascript-in-page-gui-agent-that-controls-web-interfaces-with-natural-language-through-the-dom/
摘要：Alibaba's Page Agent runs as client-side JavaScript inside the webpage. It reads the live DOM as text, then clicks and types from natural-language commands. No screenshots, no multimodal model, and no backend rewrite are
3. How Amazon Bedrock catches AI-generated phishing
- 来源：AWS ML Blog
- 发布时间：2026-07-02 17:55 UTC
- 链接：https://aws.amazon.com/blogs/machine-learning/how-amazon-bedrock-catches-ai-generated-phishing/
摘要：Social engineering through phishing remains one of the most common tactics for launching cyberattacks. AI-generated phishing email messages now pose a new challenge for security teams managing email systems, significantl
4. Best practices for multi-turn reinforcement learning in Amazon SageMaker AI
- 来源：AWS ML Blog
- 发布时间：2026-07-02 17:50 UTC
- 链接：https://aws.amazon.com/blogs/machine-learning/best-practices-for-multi-turn-reinforcement-learning-in-amazon-sagemaker-ai/
摘要：In this post, we share best practices for reliable multi-turn RL training. We cover how to build a training environment you can trust, set up an external evaluation, design a reward aligned with the end task, manage what
5. OpenAI floats giving Trump administration 5 percent cut of AI boom
- 来源：The Verge AI
- 发布时间：2026-07-02 10:23 UTC
- 链接：https://www.theverge.com/ai-artificial-intelligence/960588/openai-government-5-percent-stake-trump
摘要：OpenAI has floated giving the US government a 5 percent ownership stake as a way of easing tensions with the Trump administration and blunting mounting public backlash against AI, according to the Financial Times. CEO Sa
6. The Google Health API Got a CLI: ghealth is an Open-Source Tool for Your Fitbit Air Data
- 来源：MarkTechPost
- 发布时间：2026-07-02 08:46 UTC
- 链接：https://www.marktechpost.com/2026/07/02/the-google-health-api-got-a-cli-ghealth-is-an-open-source-tool-for-your-fitbit-air-data/
摘要：The Google Health API now has an open-source CLI. ghealth is a single Go binary that exposes 40 data types as agent-ready JSON. It is a community project, not an official Google release. Here's how it works, and what to
7. Constructive Alignment: Governing Preference Dynamics in Human-AI Interaction
- 来源：arXiv cs.AI
- 发布时间：2026-07-02 04:00 UTC
- 链接：https://arxiv.org/abs/2607.00001
摘要：arXiv:2607.00001v1 Announce Type: new Abstract: Most approaches to AI alignment treat human preferences as fixed targets to be inferred and optimized. This assumption conflicts with extensive empirical evidence showing t
8. Bounded Morality: Defining the Space of Moral Computation
- 来源：arXiv cs.AI
- 发布时间：2026-07-02 04:00 UTC
- 链接：https://arxiv.org/abs/2607.00002
摘要：arXiv:2607.00002v1 Announce Type: new Abstract: Moral cognition has traditionally been modeled as adherence to fixed ethical theories--deontology, consequentialism, virtue ethics--implemented as static rules or value fun
9. The MMM Data Model -- A Normative Specification for Knowledge Interoperability in a Decentralisable Knowledge Commons
- 来源：arXiv cs.AI
- 发布时间：2026-07-02 04:00 UTC
- 链接：https://arxiv.org/abs/2607.00032
摘要：arXiv:2607.00032v1 Announce Type: new Abstract: Many information systems are built around documents: self-contained units optimised for print production and linear reading. While effective for large-scale dissemination,
10. Making Failure Safe: A Constrained, Verifiable Agent Framework for Open-Web Data Collection
- 来源：arXiv cs.AI
- 发布时间：2026-07-02 04:00 UTC
- 链接：https://arxiv.org/abs/2607.00035
摘要：arXiv:2607.00035v1 Announce Type: new Abstract: LLMs and agents can generate web scrapers from natural-language requirements, but direct generation remains unreliable because of dependency errors, broken selectors, schem
11. Solution space path planning for supporting en-route air traffic control
- 来源：arXiv cs.AI
- 发布时间：2026-07-02 04:00 UTC
- 链接：https://arxiv.org/abs/2607.00064
摘要：arXiv:2607.00064v1 Announce Type: new Abstract: As technology advances, many path-planning algorithms have been proposed for Air Traffic Management, yet their operational adoption in tactical control remains limited, rev
12. RareDxR1: Autonomous Medical Reasoning for Rare Disease Diagnosis Beyond Human Annotation
- 来源：arXiv cs.AI
- 发布时间：2026-07-02 04:00 UTC
- 链接：https://arxiv.org/abs/2607.00147
摘要：arXiv:2607.00147v1 Announce Type: new Abstract: Rare disease differential diagnosis is a critical yet arduous clinical task, requiring physicians to identify precise phenotypes from complex, unstructured patient symptoms
13. A Contextual-Bandit Oversight Game with Two-Sided Informational Asymmetry
- 来源：arXiv cs.AI
- 发布时间：2026-07-02 04:00 UTC
- 链接：https://arxiv.org/abs/2607.00155
摘要：arXiv:2607.00155v1 Announce Type: new Abstract: We study runtime human oversight of an AI agent when private information runs in both directions: the human privately knows her reward function, while the AI privately know
14. Constructing Epistemic AI Literacy: Detecting Epistemic Aims and Processes in Student-AI Co-Programming
- 来源：arXiv cs.AI
- 发布时间：2026-07-02 04:00 UTC
- 链接：https://arxiv.org/abs/2607.00211
摘要：arXiv:2607.00211v1 Announce Type: new Abstract: Epistemic thinking plays a central role in students' learning processes when applying generative artificial intelligence (GenAI), particularly in programming contexts where
15. From Signals to Structure: How Memory Architecture Drives Language Emergence in LLM Agents
- 来源：arXiv cs.AI
- 发布时间：2026-07-02 04:00 UTC
- 链接：https://arxiv.org/abs/2607.00233
摘要：arXiv:2607.00233v1 Announce Type: new Abstract: How do two agents invent a shared language from scratch? In a Lewis signaling game, a sender and receiver must coordinate on a code using only their interaction history. We
16. Seed2.0 Model Card: Towards Intelligence Frontier for Real-World Complexity
- 来源：arXiv cs.AI
- 发布时间：2026-07-02 04:00 UTC
- 链接：https://arxiv.org/abs/2607.00248
摘要：arXiv:2607.00248v1 Announce Type: new Abstract: We present Seed2.0, a model series that takes a meaningful step toward solving complex, real-world tasks. Our approach begins with identifying users' genuine needs and cons
17. Mnemosyne: Agentic Transaction Processing for Validating and Repairing AI-generated Workflows
- 来源：arXiv cs.AI
- 发布时间：2026-07-02 04:00 UTC
- 链接：https://arxiv.org/abs/2607.00269
摘要：arXiv:2607.00269v1 Announce Type: new Abstract: LLMs, solvers, and agent teams increasingly generate workflow actions, repairs, and plans, but a generated action may be syntactically valid yet stale, infeasible, conflict
18. Managed Autonomy at Runtime: Gear-Based Safety and Governance for Single- and Multi-Agent Cyber-Physical Systems
- 来源：arXiv cs.AI
- 发布时间：2026-07-02 04:00 UTC
- 链接：https://arxiv.org/abs/2607.00334
摘要：arXiv:2607.00334v1 Announce Type: new Abstract: Autonomous agents, whether LLM-driven software agents or robotic physical agents, face a common class of failure modes when operating without continuous human oversight: sa
19. Personalization as Inverse Planning: Learning Latent Design Intents for Agentic Slide Generation via Structural Denoising
- 来源：arXiv cs.AI
- 发布时间：2026-07-02 04:00 UTC
- 链接：https://arxiv.org/abs/2607.00407
摘要：arXiv:2607.00407v1 Announce Type: new Abstract: Slide design requires personalizing both deck themes and page layouts. Yet, current AI agent-based methods struggle with fine-grained, page-level design. Solely relying on
20. PHREEQC-MCQ-200: A Diagnostic Benchmark for Tool-Augmented Scientific Simulator Agents
- 来源：arXiv cs.AI
- 发布时间：2026-07-02 04:00 UTC
- 链接：https://arxiv.org/abs/2607.00436
摘要：arXiv:2607.00436v1 Announce Type: new Abstract: Large language model agents are increasingly connected to scientific software, yet it remains unclear when tool access makes scientific computation more reliable rather tha