264 stories tagged AI Agents · page 9 of 11
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.
A new study shows that adding more context to AI agents can sometimes hurt their performance. The research reveals that irrelevant information can sometimes work as well as or better than relevant details for certain tasks. This challenges the common assumption that more context always improves AI decision-making.
MCP Agora is a new open-source tool that allows AI agents to retain memory across different conversations. This could make AI interactions feel more natural and personal over time.
A new platform called Agent Exchange lets AI agents compete to complete your tasks through real-time bidding. It's like a marketplace where AI agents bid to do work for you, similar to how freelancers bid on projects.
Testing AI agents is tricky because they often produce different answers. Researchers are developing new methods to evaluate their performance consistently. This matters for everyone who relies on AI tools for daily tasks.
TrainForgeTester is a new open-source tool that helps you test AI agents in real-world scenarios. It focuses on catching mistakes like wrong tool calls or skipped steps, making AI agents more reliable for everyday use.
Mnemory is a new tool that lets AI agents remember information across conversations. This could make AI assistants much more useful in everyday tasks.
Stripe has updated its Link digital wallet to allow AI agents to make purchases on your behalf with your approval. This could make online shopping and subscriptions easier and more secure.
Researchers propose a new approach to optimize compute resources for GUI-interacting AI agents, reducing costs and improving efficiency. The method targets long-horizon tasks where uniform compute allocation is inefficient.
Researchers deployed 3,505 AI agents to trade real ETH, processing 7.5M inferences and $20M in volume. The study highlights the reliability of language-model agents in real-world financial markets.
Researchers introduce AGEL-Comp, a neuro-symbolic AI architecture that enhances compositional generalization in interactive agents. The framework combines a dynamic Causal Program Graph and an Inductive Logic Programming engine to improve robustness in complex environments.
Researchers introduce PExA, a novel approach to text-to-SQL generation that balances latency and performance by using parallel test cases. The method ensures semantic coverage before finalizing the SQL query.
GraphOS is an open-source tool that provides a visual interface for building, running, and debugging AI agents. It emphasizes local-first execution, making it easier to develop and troubleshoot AI workflows.
Choco leveraged OpenAI APIs to automate food distribution, significantly boosting productivity. The implementation highlights real-world AI applications in supply chain management.
Researchers introduce the Superminds Test to measure collective intelligence in large-scale agent societies. The study examines MoltBook's two million agents to determine if intelligence emerges from scale.
NVIDIA's new Nemotron 3 Nano Omni model supports long-context multimodal intelligence across documents, audio, and video. It is designed for developers to build advanced AI agents.
Researchers introduce AgentSearchBench, a benchmark to evaluate AI agent search capabilities in realistic, unconstrained environments. The benchmark addresses gaps in existing research by focusing on compositional and execution-dependent agent capabilities.
OpenAI is reportedly working on a smartphone that replaces traditional apps with AI agents. The device could enter mass production by 2028, according to an analyst.
A new paper highlights the risks of AI agents producing selectively chosen, publishable analyses that lack rigorous validation. The study calls for adversarial experiments to ensure scientific integrity.
Researchers developed an AI system that can reproduce social science findings using only paper descriptions and raw data. The method achieves deterministic, cell-level result comparisons without access to original code or outputs.
A new study reveals previously unknown attack vectors in sandboxed AI agents, challenging assumptions about their security. The findings highlight the need for enhanced isolation techniques and continuous monitoring.
Anthropic has created a test marketplace where AI agents acted as both buyers and sellers, completing real transactions. This experiment could revolutionize automated commerce and AI-driven economies.
A new arXiv paper introduces a framework to automate the creation of AI agent harnesses, potentially eliminating the need for manual design. This could revolutionize AI deployment across complex workflows.
A new wiki system allows AI agents to maintain and access knowledge in Markdown files stored in a Git repository. This approach avoids complex databases and enables portable, version-controlled knowledge sharing.