Pre-trained LLMs using recursive criticism and improvement prompting achieve state-of-the-art results on the MiniWoB++ computer task benchmark with only a handful of demonstrations and no task-specific reward function.
End-to-end goal-driven web navigation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2023 1verdicts
ACCEPT 1representative citing papers
citing papers explorer
-
Language Models can Solve Computer Tasks
Pre-trained LLMs using recursive criticism and improvement prompting achieve state-of-the-art results on the MiniWoB++ computer task benchmark with only a handful of demonstrations and no task-specific reward function.