WebDART: Dynamic Decomposition and Re-planning for Complex Web Tasks

Large-language-model (LLM) agents are becoming competent at straightforward web tasks, such as opening an item page or submitting a form, but still struggle with objectives that require long-horizon navigation, large-scale information extraction, and reasoning under constraints.We present WEBDART, a general framework that enables a single LLM to handle such complex chores.WEBDART (i) dynamically decomposes each objective into three focused subtasks-navigation, information extraction, and execution-so the model concentrates on one skill at a time, and (ii) continuously re-plans the decomposition as new webpages are revealed, taking advantage of newly discovered filters or shortcuts and avoiding redundant exploration.Evaluated on WebChore-Arena, WEBDART lifts end-to-end success rates by up to 13.7 percentage points over previous state-of-the-art agents, while matching their performance on the easier WebArena suite and completing tasks with up to 14.7 fewer navigation steps.