#artificial intelligence
May 2026
Does The Way You Plan Matter? An Empirical Study of Planning Representations for LLM Web Agents
PlanAhead is introduced, a static planner-executor framework that evaluates the impact of plan representation on agent performance and shows that both, the plan formulation and the underlying LLM generating the plan, significantly influence web-agent robustness and task success.
Alejandra Zambrano, Sara Vera Marjanovic, Imene Kerboua et al.
· arXiv.org · 1 citation