AI RESEARCH
Web Agents Should Adopt the Plan-Then-Execute Paradigm
arXiv CS.CL
•
ArXi:2605.14290v1 Announce Type: cross ReAct has become the default architecture across LLM agents, and many existing web agents follow this paradigm. We argue that it is the wrong default for web agents. Instead, web agents should default to plan-then-execute: commit to a task-specific program before observing runtime web content, then execute it. The reason is that web content mixes inputs from many parties. An e-commerce product page may combine a seller's listing, customer reviews and sponsored advertisements.