264 stories tagged AI Agents · page 4 of 11
Researchers introduced FlowEvo, a training-free framework that compiles successful AI agent traces into reusable skill records, enabling agents to improve efficiency and flexibility over time without additional data or computational resources.
OneCLI is a new open-source credential gateway that sits between AI agents and the services they call, ensuring sensitive secrets like passwords and API keys are never exposed to the agent itself.
AWS has published a detailed blueprint for building production-ready AI agents using the Strands and AgentCore frameworks. The guide provides developers with practical tools and best practices to improve the reliability, performance, and real-world capability of AI agents.
OpenAI has introduced Presence, a proven enterprise AI agent platform that enables organizations to deploy trusted voice and chat agents for customer service and internal workflows, making advanced AI accessible to businesses of all sizes.
Researchers introduced SAAG (Structured Agent Assessment and Grounding), a cascaded diagnostic framework that decomposes AI agent-calling evaluation into three sequential stages: registry conformance, structural completeness, and argument grounding. This helps identify specific failure modes rather than just giving a pass/fail score.
Researchers introduced SkillCorpus, a framework to consolidate and evaluate the fragmented open-source SKILL.md ecosystem for LLM agents, aiming to improve real-world agent task performance.
Provena is an open-source library that governs the data flowing into AI agents' context windows—filling a critical gap in AI governance. The project has 7 contributors and is actively seeking more, with 11 'good first issue' labels and 17 'help wanted' issues.
The biggest challenge in AI agent development is no longer the models themselves but how to manage and use context effectively. This shift is changing how developers approach AI systems.
DoorDash has introduced dd-cli, a command-line tool that lets developers and AI agents search stores, build carts, and place orders directly from the terminal. The limited beta marks another step in creating software designed for AI agents as well as humans.
AllenAI's open-source Shippy agent introduces modular components that can be swapped independently, making AI development more accessible and scalable for developers.
A new ArXiv study shows that LLM-based AI agents lose information when communicating via plain text, suggesting they possess an internal 'world model' that exceeds textual expressibility. This finding has implications for multi-agent system design and alignment.
A study of 157 enterprises reveals that half have shipped AI agents that passed internal evaluations but failed in production. Only 5% fully trust automated evaluations, yet two-thirds are moving toward fully automated deployments without human oversight. The core issue is not test coverage but a reality-alignment gap between evaluations and real-world outcomes.
A VentureBeat Pulse Research report of 101 enterprises finds that most deployed 'AI agents' are actually simple chatbot wrappers, not true autonomous agents. Anthropic's Claude leads agent orchestration adoption due to reliable multi-step execution, while enterprises deliberately build hybrid control planes to avoid vendor lock-in. Real-time fiscal control over token burn remains rare.
A VentureBeat survey of 107 enterprises reveals that 54% have already experienced an AI agent security incident or near-miss. Despite this, most companies still let agents share credentials, only a third give each agent its own scoped identity, and just 30% isolate their highest-risk agents. The security stack is largely borrowed from model providers and hyperscalers rather than purpose-built for agents, and spending remains a thin slice of the security budget.
A new study reveals that the format of messages between AI agents significantly impacts how accurately information is preserved across multiple hops. Structured messages help maintain fidelity, but the effect depends on the type of information and the agent's tier.
Researchers created a new test called Long-Horizon-Terminal-Bench to evaluate AI agents on complex, time-consuming tasks. Unlike previous tests, it measures progress over time, not just final results.
Researchers developed a new AI planning method called GATS that reduces computational costs and improves reliability by eliminating LLM calls during inference. It could make AI assistants more efficient at complex tasks.
NVIDIA has released a massive open-source dataset designed to train AI agents. This data could accelerate the development of more capable AI assistants for everyday tasks.
AI agents are transforming banking at record speed, outpacing even the internet's adoption. The market for AI in banking is projected to reach $97B by 2027 and over $200B beyond, with the token $SERV positioned at the intersection of AI agents and banking.
Researchers discovered a new technique called 'Ghostcommit' that embeds hidden instructions in images to manipulate AI systems. This could trick AI agents into revealing sensitive information or performing unauthorized actions.
Lyzr, a startup building AI agents for businesses, used its own AI agent to successfully raise $100 million. This demonstrates the agent's capabilities in real-world applications.
Researchers found that AI agents can create reusable workflows from basic tasks, reducing errors and saving time. This could make AI assistants much more efficient at complex jobs.
Researchers introduced AgentLens, a benchmark that evaluates AI coding assistants by analyzing their entire problem-solving process. This goes beyond just checking if the code works, looking at how the AI follows instructions and recovers from mistakes.
A new study identifies recurring weaknesses in AI agents that use tools and plan tasks. These failures highlight challenges in making AI more reliable for everyday use.