π§ Researchers introduce the Wandr Benchmark, a tool for evaluating AI agents that perform web search and information gathering tasks. The benchmark measures how well these agents can explore broadly and dive deep into topics to find relevant information.π¬ Hacker Newsπ https://research.perplexity.ai/articles/wandr-benchmark-evaluating-research-agents-that-must-search-wide-and-deep#AI #MachineLearning #tech
π§ Researchers introduce the Wandr Benchmark, a tool for evaluating AI agents that perform web search and information gat...