Hierarchical analysis reveals LLM web agents fail mainly at low-level execution and perceptual grounding despite better high-level plans from PDDL structures.
Proposed high-level plan
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Why Do LLM-based Web Agents Fail? A Hierarchical Planning Perspective
Hierarchical analysis reveals LLM web agents fail mainly at low-level execution and perceptual grounding despite better high-level plans from PDDL structures.