In long-horizon stress testing, Muse Code iteratively optimized GPU kernels over 1,000+ tool calls (up to 24 hours) on @nvidia Hopper GPUs, delivering very competitive performance gains for KDA and MLA relative to baseline Triton implementations.
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
Why it matters
A 24-hour, 1,000-tool-call AI agentAn AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.Full definition → run producing real kernel speedups is one of the few public data points on how far unattended long-horizon agent loops currently go.
