Book
Open access
Nov 2026
Seeing is Deciding: Evidence-Based Parallel Probing for LLM-based Web Agents
Autonomous agents powered by Large Language Models (LLMs) can automate complex web tasks, but their reliability is limited by uncertain action outcomes: the consequence of interacting with a web element is often known only after execution. Existing sequential methods are vulnerable to error propagation after wrong deci...
Han-Xun Li, Bin Li, Jing-Tao Qi et al.
· Proceedings of the 35th ACM... · 0 citations