232 stories tagged AI Agents · page 4 of 10
Researchers introduced Janus, a modular playground system that allows users to manage permissions for AI agents. It enables the implementation and evaluation of different designs for user-involved permission management, giving people more granular control over what AI tools can do on their behalf.
Researchers developed Auto-FL-Research, an AI system that automates the testing of different federated learning algorithms. This could make it much faster to improve privacy-focused AI training methods.
AI agents can develop shared languages through interaction, and the way they store memories significantly impacts their success. This discovery could improve how AI systems communicate and collaborate in the future.
Researchers propose using AI agents to audit personalization algorithms on social media. This could make it easier to study how these systems influence what we see online. The method aims to balance realism and scalability in audits.
AI agents are borrowing decades-old database techniques to become more reliable and context-aware. This could make digital assistants far more useful for complex, multi-step tasks. The article explores how methods refined over 50 years are being adapted to improve AI performance.
AI agents often assume users know exactly what they want. New research suggests these tools should help people learn and form preferences instead. This could make AI assistants much more helpful for everyday tasks.
OpenAI has launched a new feature that allows users to create custom AI agents without coding. This could make advanced AI tools accessible to everyone, not just programmers.
Anthropic has released Claude Sonnet 5, a more affordable AI model with stronger agentic capabilities. It's positioned as a cheaper alternative to top-tier models like Opus, GPT-5.5, and Gemini Pro.
Researchers have developed a new way for AI to simulate future outcomes, making it better at long-term planning. This could help AI agents make decisions more like humans do, by imagining different scenarios before acting.
Notion is closing its email app, a product influenced by the Skiff acquisition, and is instead going all in on AI agents that handle inboxes. This shift reflects how AI agents are transforming everyday tasks like managing emails, moving beyond simple automations to directly running your inbox.
Researchers developed an AI-powered pipeline to compare governance structures of decentralized and corporate AI protocols. The system analyzes over 4,300 governance discussions to uncover power dynamics in AI agent interoperability standards.
Researchers evaluated AI agents on complex energy market tasks, including live data retrieval, regulatory knowledge, and multi-step quantitative reasoning. The study fills a critical gap, with 243 expert-designed tasks showing how tool-augmented LLMs could make energy systems more efficient and responsive.
Researchers introduced TrustMem, a framework designed to improve long-term memory in AI agents. It addresses the problem of AI systems forgetting important information or generating hallucinated content that becomes permanently stored. This could make AI assistants more reliable over extended interactions.
Tabularis is a new open-source desktop app that lets you manage databases with SQL. It also supports AI agents, making database management easier for non-experts. This could change how people interact with databases, especially for those who aren't familiar with SQL.
AI agents often make mistakes that snowball over time, especially in tasks like persuasion. Researchers found a key reason—semantic leakage in standard RAG—and developed a method called Taxonomic Strategy Retrieval to prevent these compounding errors.
A new practitioner's reference, 'The Hitchhiker's Guide to Agentic AI,' covers the full stack of building autonomous AI systems—from transformer architecture and GPU systems to fine-tuning, model compression, and production deployment.
OpenAI's research shows AI agents can now handle longer, more complex tasks, making many jobs more efficient. This could change how we work across various industries.
MoEngage has acquired an AI startup to deploy millions of AI agents, each assigned to an individual customer, aiming to revolutionize personalized marketing. This could make customer interactions more tailored and efficient for businesses and consumers alike.
A new research paper introduces a reference architecture for 'agent skills' — reusable, externalized behavioral knowledge that LLM agents can discover, activate, and interpret at runtime. The framework formalizes how skills are bound to context and authority, interpreted by stochastic agents, and recorded as run evidence.
TechCrunch reports that AI agents are evolving to work in continuous 'loops', a step beyond current agentic AI. These agents can now operate endlessly in the background, handling tasks without constant human oversight. Think of it like a team of digital assistants that never sleep, constantly refining their work. For everyday people, this means more automation in daily tasks. Imagine an AI that not only books your flights but also adjusts them based on real-time weather, price changes, and your schedule—all without you lifting a finger. However, it also raises questions about privacy and control over our digital lives.
Lelu is an open-source tool designed to detect and prevent manipulation of AI agents in real-time. It's a significant step forward in ensuring the security and reliability of AI systems.
Hugging Face introduced a new open-source standard called Agentic Resource Discovery that enables AI agents to autonomously discover and connect to external tools, APIs, and data sources on the fly. While it is related to search, its primary focus is on expanding agent capabilities through dynamic resource discovery, not just web search.
Scientists have developed a framework to control AI agents that can act independently. This could help prevent security and privacy risks as these systems become more common.
Hugging Face introduced a new tool to test how well open-source AI models perform as agents. This helps developers compare models without needing complex setups.