Tag
FixItFlow is an automated system that generates troubleshooting guides from historical cloud incident data using large language models, achieving a 2.3x reduction in mitigation time and positive engineer feedback.
MAG introduces a benchmark and harness for multimodal web agents that both execute tasks and generate step-by-step guide text, using screenshots and grounding schemes. The work includes a GRPO training method that nearly doubles the success rate of a 9B agent.