All 3,125 AI stories, newest first · page 45 of 131
Researchers introduced MedAgentBench-v3, a new benchmark for AI agents in healthcare. It improves on previous versions by addressing issues where agents often did nothing, making it harder to train them effectively.
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.
GrowthSpree, a B2B marketing agency, rebuilt itself as an AI-native firm and hit $1.5M in annual recurring revenue in just six months. Their approach involved integrating AI deeply into their operations, not just as a tool. This strategy proved highly successful, demonstrating the power of AI in modern business.
Researchers introduced FaithMed, a framework that trains large language models to reason faithfully using evidence-based medicine principles. It combines clinician-designed rubrics with reinforcement learning to ensure transparent, evidence-grounded medical reasoning.
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.
Researchers found that AI agents can uncover different conclusions from the same data by adopting different personas. This highlights how human biases can shape research findings, even when using identical datasets.
Researchers developed a multi-agent AI system called Agent4cs to better understand large, messy code projects. It works like a team of specialists, each handling different parts of the code, creating clearer summaries than current tools.
Researchers found that tweaking just one skill description can prevent AI routing errors in enterprise chat systems. This discovery could save companies time and money by automating the optimization process.
Researchers introduced Seed2.0, a model series designed to handle complex, real-world tasks. It focuses on long-tail knowledge and complex instruction following, making it more reliable for intricate, long-horizon tasks.
A new paper introduces a framework for understanding how AI systems can handle moral decisions. It suggests that AI ethics should consider both the scope of moral concerns and the complexity of moral reasoning.
OpenAI has introduced Genebench-Pro, a new benchmark designed to evaluate AI models on complex genetic research tasks. The benchmark tests models on real-world challenges like predicting gene expression and identifying disease-causing mutations, aiming to accelerate progress in computational biology.
Google, the New York Jobs CEO Council, and Urban Assembly hosted an AI summit to explore how AI can transform education. The event brought together 150 leaders to discuss practical applications and ethical considerations for classrooms.
Researchers developed a system to prevent safety violations in autonomous agents. It uses five gears to manage different stages of operation, ensuring stability and continuity. This could make AI-driven robots and software agents safer for real-world use.
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 have developed a new framework to study how humans can oversee AI agents when both parties have private information. This work could improve collaboration between humans and AI in real-world scenarios.
A new study challenges the idea that human preferences are fixed, showing AI systems influence what we value. Researchers propose a new approach to AI alignment that accounts for this dynamic relationship.
Researchers developed a new way to fairly compare AI models by controlling for accuracy. This helps avoid misleading conclusions when evaluating different systems.
Researchers created a test to evaluate how well AI agents can use scientific software for chemistry simulations. The benchmark, PHREEQC-MCQ-200, challenges AI to solve 200 multiple-choice questions using a geochemistry tool called PHREEQC.
Researchers created a new test to evaluate how well AI models handle mixed-language text, like Hindi or Tamil blended with English. This is common in many multilingual communities but often confusing for AI systems.
Researchers developed a method to make AI-generated database queries more accurate. This could help everyday users get better results when asking AI to pull data from complex systems.
Researchers developed a new framework to make AI-generated web scrapers more reliable. It uses structured feedback and constraints to reduce errors in data collection. This could make web scraping more accessible and accurate for everyone.
Researchers introduced Agentic Transaction Processing (ATP), a transaction model that treats AI-generated workflow actions as untrusted proposals until they pass deterministic admission under a declared constraint set. This approach ensures actions are not just syntactically correct but also feasible, conflict-free, and non-destructive of the evidence that triggered a repair.
Meta has quietly released Pocket, an experimental AI app that lets users generate and share interactive mini-games just by describing them in text. This makes game creation accessible to anyone, not just developers.
Hugging Face and Cerebras have released a new open-source model optimized for real-time voice AI, leveraging Cerebras hardware to achieve low-latency speech processing. This could make voice assistants and AI-powered call centers faster and more responsive.