5 stories tagged Tool Use
A new benchmark called MERIT measures the marginal utility of long-term memory for tool-using LLM agents. The study finds that memory often fails to improve task performance, especially when access costs are high, challenging assumptions about AI memory in real-world applications.
LLM Colosseum is a free, browser-based game where AI models compete in real-time strategy battles. It helps developers test how well AI models can use tools, like humans using apps. You can try it today with no downloads or setup.
A new research paper introduces Evoflux, a method that helps compact AI agents create and adjust executable tool workflows during inference, rather than relying solely on pre-training data. This could make small models more reliable for MCP-style tasks.
Using tools to help AI reason doesn't always work better than just thinking things through. Researchers found that tool use can actually slow things down and cost more. This challenges the idea that tools are always the best solution for AI.
IBM Research has introduced VAKRA, a new benchmark for assessing agents' reasoning, tool use, and failure modes. The benchmark aims to provide a standardized way to evaluate agent capabilities across various tasks.