TraceWeaver: Language-Conditioned Action Selection for Web Agents via Coupled Rollouts and Episodic Memory
Abstract
AbstractWeb agents must choose queries, clicks, form fills, and tool calls from language instructions while preserving constraints whose consequences may appear several steps later. We study this challenge as language-conditioned delayed-constraint tracking and present TraceWeaver, which couples linear-time latent rollouts, entity-centric episodic memory, and a learned critic for budgeted action selection. Across WebShop (500 episodes), Mind2Web (1,000-task split), WebArena (812-task split), and WorkArena (165-task enterprise split), TraceWeaver shows task-success gains of +2.7 to +4.7 over baselines under a matched test-time budget. Shared-pool controls reduce the confound between selection quality and proposal quality, while a language-phenomenon analysis concentrates the gains on tasks with dense, conflicting, or delayed constraints.