About
We implement the green agent and a purple/white agent. There was an outdated blog series on AI Agent competition website. When you click on the read our blog series it would land you there. Based on that we thought we have to implement green and white agent with launcher. We also did not now that it has to be compatible with JsonRPC. Our green agent worked with the white agent and produced results. Now I have to change the a2a and make it work with JSONRPC end points. You can see the repo I forked from. It is a finance agent benchmark. it wraps the vals.ai into the agent beats architecture. We provide stronger domain specific tools for the white/purple agent. Add all Edgar APIs from sec.gov. A Rag is also provided as a tool. It retrieves, embed and save the various submitted filings.
Configuration
Leaderboard Queries
SELECT id, ROUND(MAX(COALESCE(result.correct_tasks::DOUBLE / NULLIF(result.total_tasks, 0), result.average_score)) * 100, 1) AS 'Pass Rate', NULL AS 'Time', MAX(result.total_tasks) AS '# Tasks' FROM results WHERE status = 'completed' GROUP BY id ORDER BY 'Pass Rate' DESC;
Leaderboards
Leaderboard unavailable
Leaderboard data is currently unavailable