232 stories tagged AI Agents · page 6 of 10
Researchers tested AI agents on complex neuroscience tasks, finding they can automate processes that usually take experts months. This could revolutionize scientific research by making data analysis faster and more accessible.
Researchers developed OpenSkill, a system that lets AI agents learn and improve on their own in the real world. This could make AI tools more adaptable and useful without constant human input.
Researchers introduced Lean4Agent, a new method to make AI agents more reliable by using formal verification. This approach helps ensure AI agents follow correct steps in complex tasks, reducing errors in multi-step workflows.
AI agents are becoming more powerful, but their terminology can be confusing. Understanding key terms like 'harness' and 'scaffold' helps clarify how these tools work and what they can do. These concepts are crucial for both developers and users to grasp as AI agents evolve.
Researchers introduced SentinelBench, a benchmark to test AI agents' ability to monitor tasks over long periods. This could improve AI assistants that handle slow, real-world tasks like waiting for stock price changes or tracking delivery updates.
Researchers introduced Agents' Last Exam (ALE), a new benchmark to evaluate AI agents on long-horizon, economically valuable tasks with verifiable outcomes. This could help bridge the gap between AI performance in labs and real-world usefulness.
Endava is integrating AI agents like ChatGPT Enterprise and Codex into their software development process. This shift is making workflows faster and more efficient, setting a new standard for AI-native enterprises.
Hugging Face released Holo3.1, a free open-source tool that lets you run AI agents locally. This means you can use AI assistants without sending your data to the cloud.
IBM Research explains why AI agents—software that automates complex tasks—are crucial for businesses to use AI at scale. These agents could make AI more practical for everyday work.
Scientists studied how AI agents update their own tools and strategies. They found that not all AI models benefit equally from these self-improvements, even if they're good at their original tasks.
Researchers developed a method called AdaCoM to help AI agents manage information overload during long tasks. Unlike prior approaches that require retraining the agent itself, AdaCoM adapts context management strategies to each agent, making it practical for closed-source systems.
Robinhood now lets AI agents handle your trading and even make purchases with your credit card. This could make investing and shopping more hands-off but raises security concerns.
Scientists argue that AI memory systems need to evolve beyond simple databases. Current approaches lead to issues like unchecked growth and forgotten information. Long-term AI agents need more sophisticated memory structures to function effectively.
AI agents change as they work, so researchers propose new ways to measure how long they stay reliable. This could help make AI tools more dependable for everyday use.
Researchers propose the Foundation Protocol to help AI agents work together more effectively. This could enable better collaboration between autonomous systems in the future.
Researchers are using AI agents to study negotiation strategies. This could help us understand how to balance empathy and assertiveness in real-life talks. The method allows for precise, repeatable experiments that humans can't easily replicate.
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.