Wandr Benchmark: Evaluating Research Agents That Must Search Wide and Deep | Dark Hacker News

Dark Hacker News

new|best|ask|show|jobs

Built with the HackerNews API. Developed by LJT.AI

Note: The HackerNews API provides up to 500 stories per category

Wandr Benchmark: Evaluating Research Agents That Must Search Wide and Deep(research.perplexity.ai)

1 points by tagawa 39 days ago | 1 comment

Wandr Benchmark: Evaluating Research Agents That Must Search Wide and Deep | Dark Hacker News

tagawa 39 days ago |

Repo with benchmark tasks, evaluation harness, tech report:

https://github.com/perplexityai/wandr