A Survey on Large Language Model based Autonomous Agents

Abstract

Autonomous agents have long been a prominent research focus in both academic and industry communities. Previous research in this field often focuses on training agents with limited knowledge within isolated environments, which diverges significantly from human learning processes, and thus makes the agents hard to achieve human-like decisions. Recently, through the acquisition of vast amounts of web knowledge, large language models (LLMs) have demonstrated remarkable potential in achieving human-level intelligence. This has sparked an upsurge in studies investigating LLM-based autonomous agents. In this paper, we present a comprehensive survey of these studies, delivering a systematic review of the field of LLM-based autonomous agents from a holistic perspective. More specifically, we first discuss the construction of LLM-based autonomous agents, for which we propose a unified framework that encompasses a majority of the previous work. Then, we present a comprehensive overview of the diverse applications of LLM-based autonomous agents in the fields of social science, natural science, and engineering. Finally, we delve into the evaluation strategies commonly used for LLM-based autonomous agents. Based on the previous studies, we also present several challenges and future directions in this field. To keep track of this field and continuously update our survey, we maintain a repository of relevant references at https://github.com/Paitesanshi/LLM-Agent-Survey.

Correcting several typos, 35 pages, 5 figures, 3 tables

References in corpus (10)

• Survey of Hallucination in Natural Language Generation
• Llama 2: Open Foundation and Fine-Tuned Chat Models
• Out of One, Many: Using Language Models to Simulate Human Samples
• Do As I Can, Not As I Say: Grounding Language in Robotic Affordances
• Graph of Thoughts: Solving Elaborate Problems with Large Language Models
• ChatGPT and Software Testing Education: Promises & Perils
• A Neural Network Solves, Explains, and Generates University Math Problems by Program Synthesis and Few-Shot Learning at Human Level
• Towards autonomous system: flexible modular production system enhanced with large language model agents
• Do LLMs Understand Social Knowledge? Evaluating the Sociability of Large Language Models with SocKET Benchmark
• CALYPSO: LLMs as Dungeon Masters' Assistants

Cited by in corpus (83)

• Survey on Large Language Model-Enhanced Reinforcement Learning: Concept, Taxonomy, and Methods
• A Survey on Large Language Models for Code Generation
• Agentic AI: A Comprehensive Survey of Architectures, Applications, and Future Directions
• RCAgent: Cloud Root Cause Analysis by Autonomous Agents with Tool-Augmented Large Language Models
• Tool Learning with Large Language Models: A Survey
• Generative AI for Self-Adaptive Systems: State of the Art and Research Roadmap
• A Survey of Large Language Models for Graphs
• Emergent social conventions and collective bias in LLM populations
• Evaluation and Benchmarking of LLM Agents: A Survey
• Language Models as Zero-Shot Trajectory Generators
• Large Language Model for Table Processing: A Survey
• Exploring the Roles of Large Language Models in Reshaping Transportation Systems: A Survey, Framework, and Roadmap
• The simulation of judgment in LLMs
• Let Me Do It For You: Towards LLM Empowered Recommendation via Tool Learning
• Learning without Forgetting for Vision-Language Models
• Generative Students: Using LLM-Simulated Student Profiles to Support Question Item Evaluation
• Assessing and Understanding Creativity in Large Language Models
• Remote Sensing SpatioTemporal Vision-Language Models: A Comprehensive Survey
• When Geoscience Meets Foundation Models: Towards General Geoscience Artificial Intelligence System
• Exploring the Potential of Large Language Models for Improving Digital Forensic Investigation Efficiency
• How malicious AI swarms can threaten democracy: The fusion of agentic AI and LLMs marks a new frontier in information warfare
• AI-Driven Day-to-Day Route Choice
• UXAgent: An LLM Agent-Based Usability Testing Framework for Web Design
• Plan-Then-Execute: An Empirical Study of User Trust and Team Performance When Using LLM Agents As A Daily Assistant
• CERN for AI: A Theoretical Framework for Autonomous Simulation-Based Artificial Intelligence Testing and Alignment
• CheatAgent: Attacking LLM-Empowered Recommender Systems via LLM Agent
• Synthetic Participatory Planning of Shard Automated Electric Mobility Systems
• Multi-step retrieval and reasoning improves radiology question answering with large language models
• Exploring Collaborative GenAI Agents in Synchronous Group Settings: Eliciting Team Perceptions and Design Considerations for the Future of Work
• Hybrid Agentic AI and Multi-Agent Systems in Smart Manufacturing
• MetaAgents: Large Language Model Based Agents for Decision-Making on Teaming
• RecUserSim: A Realistic and Diverse User Simulator for Evaluating Conversational Recommender Systems
• Emergent Language: A Survey and Taxonomy
• Conversational Text Extraction with Large Language Models Using Retrieval-Augmented Systems
• A Comprehensive Survey on Self-Interpretable Neural Networks
• Large Language Models for Combinatorial Optimization: A Systematic Review
• Automating Bibliometric Analysis with Sentence Transformers and Retrieval-Augmented Generation (RAG): A Pilot Study in Semantic and Contextual Search for Customized Literature Characterization for High-Impact Urban Research
• LLLMs: A Data-Driven Survey of Evolving Research on Limitations of Large Language Models
• Large Language Models as Autonomous Spacecraft Operators in Kerbal Space Program
• LLM-Agent-UMF: LLM-based Agent Unified Modeling Framework for Seamless Design of Multi Active/Passive Core-Agent Architectures
• DRC-Coder: Automated DRC Checker Code Generation Using LLM Autonomous Agent
• RS-Agent: Automating Remote Sensing Tasks through Intelligent Agent
• AnaFlow: Agentic LLM-based Workflow for Reasoning-Driven Explainable and Sample-Efficient Analog Circuit Sizing
• Can AI with High Reasoning Ability Replicate Human-like Decision Making in Economic Experiments?
• AI, Meet Human: Learning Paradigms for Hybrid Decision Making Systems
• SoAy: A Solution-based LLM API-using Methodology for Academic Information Seeking
• Decoding Urban Industrial Complexity: Enhancing Knowledge-Driven Insights via IndustryScopeGPT
• Engineering RAG Systems for Real-World Applications: Design, Development, and Evaluation
• Efficient Portfolio Selection through Preference Aggregation with Quicksort and the Bradley--Terry Model
• STARec: An Efficient Agent Framework for Recommender Systems via Autonomous Deliberate Reasoning
• Visual Analysis of LLM-based Entity Resolution from Scientific Papers
• A VLM-based Method for Visual Anomaly Detection in Robotic Scientific Laboratories
• LLM meets ML: Data-efficient Anomaly Detection on Unstable Logs
• GRILLBot In Practice: Lessons and Tradeoffs Deploying Large Language Models for Adaptable Conversational Task Assistants
• Approximating Human Strategic Reasoning with LLM-Enhanced Recursive Reasoners Leveraging Multi-agent Hypergames
• EventChat: Implementation and user-centric evaluation of a large language model-driven conversational recommender system for exploring leisure events in an SME context
• SituationalLLM: Proactive language models with scene awareness for dynamic, contextual task guidance
• Pie: A Programmable Serving System for Emerging LLM Applications
• Large Language Model Agent for User-friendly Chemical Process Simulations
• When control meets large language models: From words to dynamics
• Insight Agents: An LLM-Based Multi-Agent System for Data Insights
• Operational Hallucination and Safety Drift in AI Agents
• Learning a Thousand Tasks in a Day
• Active Learning for Neurosymbolic Program Synthesis
• Improving Interface Design in Interactive Task Learning for Hierarchical Tasks based on a Qualitative Study
• Episodic Memory Verbalization using Hierarchical Representations of Life-Long Robot Experience
• Crowd: A Social Network Simulation Framework
• Improving Merge Sort and Quick Sort Performance by Utilizing Alphadev's Sorting Networks as Base Cases
• The meaning of prompts and the prompts of meaning: Semiotic reflections and modelling
• Design and Evaluation of Generative Agent-based Platform for Human-Assistant Interaction Research: A Tale of 10 User Studies
• LLM-Enhanced Reinforcement Learning for Long-Term User Satisfaction in Interactive Recommendation
• LLM-Augmented Knowledge Base Construction For Root Cause Analysis
• Artificial intelligence for representing and characterizing quantum systems
• Scientific-Intention Driven Embodied Intelligent Solar Telescope: Conceptual Design
• Human-Centric Community Detection in Hybrid Metaverse Networks with Integrated AI Entities
• Agentic AI for Mobile Network RAN Management and Optimization
• Pairing Analogy-Augmented Generation with Procedural Memory for Procedural Q&A
• How to Steer Your Multi-Agent System: Human-LLM Collaborative Planning
• A Training-Free Mixture-of-Agents Framework for Multi-Document Summarization using LLMs and Knowledge Graphs
• PillagerBench: Benchmarking LLM-Based Agents in Competitive Minecraft Team Environments
• LLM Agents Factory: Retrieval of Domain-Specific LLM Agents
• Addressing Moral Uncertainty using Large Language Models for Ethical Decision-Making
• Six misconceptions about large language models: A minimal model and diagnostic taxonomy