Large Language Models (LLMs) are transforming artificial intelligence,
enabling autonomous agents to perform diverse tasks across various domains.
These agents, proficient in human-like text comprehension and generation, have
the potential to revolutionize sectors from customer service to healthcare.
However, they face challenges such as multimodality, human value alignment,
hallucinations, and evaluation. Techniques like prompting, reasoning, tool
utilization, and in-context learning are being explored to enhance their
capabilities. Evaluation platforms like AgentBench, WebArena, and ToolLLM
provide robust methods for assessing these agents in complex scenarios. These
advancements are leading to the development of more resilient and capable
autonomous agents, anticipated to become integral in our digital lives,
assisting in tasks from email responses to disease diagnosis. The future of AI,
with LLMs at the forefront, is promising.

大型语言模型（LLMs）正在改变人工智能，使得自主代理能够在不同领域执行多样化任务。这些代理具备类似人类的文本理解和生成能力，有望在从客户服务到医疗保健等各个领域引发革命。然而，它们面临着诸如多模态、人类价值取向、幻觉和评估等挑战。推动、推理、工具利用和上下文学习等技术正在被探索，以增强它们的功能。像 AgentBench、WebArena 和 ToolLLM 这样的评估平台为在复杂场景中评估这些代理提供了强大的方法。这些进展正在引领更加有韧性和能力的自主代理的发展，预计它们将成为我们数字生活中不可或缺的一部分，协助我们完成从邮件回复到疾病诊断等任务。拥有 LLMs 带头的人工智能的未来充满了希望。

通过大型语言模型探索自主代理：一项综述

Exploring Autonomous Agents through the Lens of Large Language Models: A  Review

Large Language Models (LLMs) are attracting significant research attention
due to their instruction-following abilities, allowing users and developers to
leverage LLMs for a variety of tasks. However, LLMs are vulnerable to
prompt-injection attacks: a class of attacks that hijack the model's
instruction-following abilities, changing responses to prompts to undesired,
possibly malicious ones. In this work, we introduce Jatmo, a method for
generating task-specific models resilient to prompt-injection attacks. Jatmo
leverages the fact that LLMs can only follow instructions once they have
undergone instruction tuning. It harnesses a teacher instruction-tuned model to
generate a task-specific dataset, which is then used to fine-tune a base model
(i.e., a non-instruction-tuned model). Jatmo only needs a task prompt and a
dataset of inputs for the task: it uses the teacher model to generate outputs.
For situations with no pre-existing datasets, Jatmo can use a single example,
or in some cases none at all, to produce a fully synthetic dataset. Our
experiments on six tasks show that Jatmo models provide the same quality of
outputs on their specific task as standard LLMs, while being resilient to
prompt injections. The best attacks succeeded in less than 0.5% of cases
against our models, versus over 90% success rate against GPT-3.5-Turbo. We
release Jatmo at this https URL

本研究中，我们引入了一种名为 Jatmo 的方法，它可生成对注入攻击具有弹性的特定任务模型，并通过六个任务的实验证明，Jatmo 模型在其特定任务上提供与标准 LLMs 相同质量的输出。