Arena.ai, the successor to the former LMSYS Chatbot Arena, has officially launched "Agent Mode" and the "Agent Arena" leaderboard, which measure the real capabilities of AI agents from actual user sessions. From a single prompt, an agent autonomously plans, uses tools, and executes multi-step workflows, with every session feeding into the leaderboard's scoring (Agent Arena).
Continue reading
The rest of this article is for AI News Blitz readers. Choose an option below to keep reading.
Already purchased? Sign in✓ Signed in — this article isn’t included in your current plan.