192 stories tagged AI Agents · page 5 of 8
Researchers introduced AgentAtlas, a new benchmark for evaluating AI agents. It moves beyond simple accuracy scores to assess agents' performance across multiple dimensions, like safety and consistency.
Nvidia's CEO Jensen Huang announced a new $200 billion market for AI agent CPUs. This shift could make Nvidia a key player in the future of AI-driven automation.
AI agents working together can solve complex problems better than single agents, but this collaboration introduces new security risks. Researchers warn that trust must be built into these networks from the start, not added later.
Researchers created a new test to measure how well AI agents balance user privacy with task performance. POLAR-Bench evaluates AI's ability to protect sensitive data while still getting the job done.
A group of developers has proposed ANML, a markup language designed for AI agents to work together. It could make it easier for different AI systems to collaborate on tasks.
Google's AI assistants have struggled to deliver on the promise of a truly helpful personal assistant. Open-source platforms like OpenClaw are now leading the way in making AI agents more useful. This shift is reshaping the industry and user expectations.
Researchers have identified a new type of AI failure called 'accidental meltdowns', where helpful AI agents behave dangerously when encountering everyday errors. This happens even without any hacking or bad inputs, just normal glitches online.
Researchers introduced SkillSmith, a new AI framework that makes AI agents more efficient by reducing redundant tasks. This could lead to faster, more reliable AI assistants for everyday use.
Researchers have developed a system to make AI agents safer by verifying their actions before execution. This could prevent AI agents from making harmful or unauthorized decisions in critical systems.
Researchers developed a method called ICRL to help AI models learn from their own critiques. This could make AI assistants like ChatGPT or Claude much more reliable over time. The key is that the models internalize feedback, not just follow temporary instructions.
Google unveiled Gemini 3.5 Flash, an AI model that can autonomously build software and execute complex tasks. This shift from chatbots to AI agents could revolutionize how we use technology daily.
OpenAI has reorganized its leadership to prioritize AI agents, a type of AI that can perform tasks autonomously. This shift aims to streamline product development and compete more effectively in the AI market.
Researchers proposed a two-dimensional system to categorize AI agents. It considers both how they process information and what tasks they perform, helping designers build better tools. This could make AI systems more reliable and easier to understand.
Researchers introduced GraphBit, a new framework that improves AI agents by using a structured approach called a directed acyclic graph (DAG). This makes AI workflows more reliable and reproducible, avoiding common issues like hallucinations and infinite loops.
Researchers developed PIVOT, a system that helps AI agents improve their plans by learning from real-world failures. This could make AI assistants and robots more reliable in everyday tasks.
Medicare’s new ACCESS model will pay for AI agents that help patients between doctor visits. This could make healthcare more personal and proactive, especially for those managing chronic conditions.
OCL Nexus introduces an automated compute layer designed to simplify running AI agents. This could make AI tools more accessible and efficient for everyday users.
Researchers have developed SkillLens, a system that organizes AI skills in layers to make them more reusable and cost-effective. This could make AI agents smarter and more adaptable for everyday tasks.
Researchers have developed a new way for AI agents to learn from their past experiences by tracking how memories connect to each other. This could help AI remember useful information over time, like how humans build on past knowledge.
Researchers have created a framework called Weblica to help train AI agents on real websites. This tool captures and replays web pages to create stable, interactive environments for AI learning. It could make web agents smarter and more adaptable to the constantly changing internet.
Researchers propose a unified graph representation to track AI agents' decisions, making it easier to audit their actions. This could help ensure AI systems behave as intended and follow security protocols.
Researchers have proposed a new framework to unify how AI agents remember information, bridging the gap between computer engineering and cognitive science. This could lead to smarter, more reliable AI assistants in the future.
Researchers have developed a new AI framework called PRISM that helps AI agents make better decisions by tightly connecting what they see with how they think. This could improve AI assistants that interact with the real world, like robots or smart home systems.
Researchers have created a new benchmark to test how AI agents handle information they can't access due to security restrictions. This helps ensure AI systems provide accurate responses without revealing sensitive data.