arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2409.18538cs.CL
收藏

面向目标导向交互式智能体的复杂任务综述

A Survey on Complex Tasks for Goal-Directed Interactive Agents

Saarland University(萨尔大学);Saarland Informatics Campus(萨尔兰信息学园区)

Mareike Hartmann, Alexander Koller

AI总结:

本综述旨在评估目标导向交互式智能体,系统汇编了相关复杂任务与环境,并按理解当前障碍的维度进行结构化分类,为结合任务背景评估智能体性能提供参考。

摘要:

目标导向的交互式智能体通过与环境的交互自主完成任务,可以在日常生活的各个领域协助人类。大型语言模型(LLMs)的最新进展引发了大量新的、越来越具挑战性的任务来评估此类智能体。为了正确地结合这些任务的背景来评估性能,必须了解它们给智能体带来的不同挑战。为此,本综述汇编了用于评估目标导向交互式智能体的相关任务和环境,并沿着与理解当前障碍相关的维度对其进行了结构化整理。相关资源的最新汇编可在我们的项目网站上找到:https://coli-saar.github.io/interactive-agents。

英文摘要:

Goal-directed interactive agents, which autonomously complete tasks through interactions with their environment, can assist humans in various domains of their daily lives. Recent advances in large language models (LLMs) led to a surge of new, more and more challenging tasks to evaluate such agents. To properly contextualize performance across these tasks, it is imperative to understand the different challenges they pose to agents. To this end, this survey compiles relevant tasks and environments for evaluating goal-directed interactive agents, structuring them along dimensions relevant for understanding current obstacles. An up-to-date compilation of relevant resources can be found on our project website: https://coli-saar.github.io/interactive-agents.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑