Auto-GPT for Online Decision Making: Benchmarks and Additional Opinions

By Hui Yang, Sifu Yue, Yunzhong He. arXiv.org, 2023

324 citations recorded by the source corpus.

Auto-GPT is an autonomous agent that leverages recent advancements in adapting Large Language Models (LLMs) for decision-making tasks. While there has been a growing interest in Auto-GPT stypled agents, questions remain regarding the effectiveness and flexibility of Auto-GPT in solving real-world decision-making tasks. Its limited capability for real-world engagement and the absence of benchmarks contribute to these uncertainties. In this paper, we present a comprehensive benchmark study of Auto-GPT styled agents in decision-making tasks that simulate real-world scenarios. Our aim is to gain deeper insights into this problem and understand the adaptability of GPT-based agents. We compare the performance of popular LLMs such as GPT-4, GPT-3.5, Claude, and Vicuna in Auto-GPT styled decision-making tasks. Furthermore, we introduce the Additional Opinions algorithm, an easy and effective method that incorporates supervised/imitation-based learners into the Auto-GPT scheme. This approach enables lightweight supervised learning without requiring fine-tuning of the foundational LLMs. We demonstrate through careful baseline comparisons and ablation studies that the Additional Opinions algorithm significantly enhances performance in online decision-making benchmarks, including WebShop and ALFWorld.

Subfields: Artificial Intelligence, Health Informatics

View Paper: https://www.semanticscholar.org/paper/3b8871e4c25d3aaca2bee6606c07bc870337253c

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Fei Huang
2. Haiyang Xu
3. Mingshi Yan
4. Ji Zhang
5. Jiabo Ye
6. Haofen Wang
7. Grégoire Mialon
8. Thomas Scialom

Citations in the corpus

• AppAgent: Multimodal Agents as Smartphone Users (2023, unknown): “Initiatives like AutoGPT [45], HuggingGPT [30], and MetaGPT [15] illustrate this trend, and many projects demonstrate impressive capabilities, moving beyond basic language tasks to engaging in activities requiring higher cognitive functions, such as software development [6, 27] and gaming [10, 26,…”
• AI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and Challenges (2025, unknown): “In the wake of this breakthrough, the AI landscape underwent a rapid transformation, shifting from the use of standalone LLMs toward more autonomous, task-oriented frameworks [29].”
• Retrieval-Augmented Generation for Large Language Models: A Survey (2023, methodology): “Vid2Seq augments language models with specialized temporal markers, facilitating the prediction of event boundaries and textual descriptions within a unified output sequence [ Yang et al. , 2023a ] .”
• Mobile-Agent: Autonomous Multi-Modal Mobile Device Agent with Visual Perception (2024, methodology): “LLM-based agents Li et al. [2023], Liu et al. [2023a,b,c], Shen et al. [2023], Wu et al. [2023], Yang et al. [2023a], Shen et al. [2024], Yang et al. [2023b], Hong et al. [2023], Yang et al. [2023c], utilizing a variety of tools, have demonstrated strong capabilities in task planning and reasoning.”
• GAIA: a benchmark for General AI Assistants (2023, methodology): “On the contrary, AutoGPT is able to do this selection automatically.”