BAGEL: Bootstrapping Agents by Guiding Exploration with Language
arxiv(2024)
摘要
Following natural language instructions by executing actions in digital
environments (e.g. web-browsers and REST APIs) is a challenging task for
language model (LM) agents. Unfortunately, LM agents often fail to generalize
to new environments without human demonstrations. This work presents BAGEL, a
method for bootstrapping LM agents without human supervision. BAGEL converts a
seed set of randomly explored trajectories or synthetic instructions, into
demonstrations, via round-trips between two noisy LM components: an LM labeler
which converts a trajectory into a synthetic instruction, and a zero-shot LM
agent which maps the synthetic instruction into a refined trajectory. By
performing these round-trips iteratively, BAGEL quickly converts the initial
distribution of trajectories towards those that are well-described by natural
language. We use BAGEL demonstrations to adapt a zero shot LM agent at test
time via in-context learning over retrieved demonstrations, and find
improvements of over 2-13
reduction in execution failures.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要