The Rise and Potential of Large Language Model Based Agents: A Survey

By Zhiheng Xi, Wenxiang Chen, Xin Guo, Wei He, Yiwen Ding, Boyang Hong, Ming Zhang, Junzhe Wang, Senjie Jin, Enyu Zhou and 20 more. arXiv.org, 2023

1,915 citations recorded by the source corpus.

For a long time, humanity has pursued artificial intelligence (AI) equivalent to or surpassing the human level, with AI agents considered a promising vehicle for this pursuit. AI agents are artificial entities that sense their environment, make decisions, and take actions. Many efforts have been made to develop intelligent agents, but they mainly focus on advancement in algorithms or training strategies to enhance specific capabilities or performance on particular tasks. Actually, what the community lacks is a general and powerful model to serve as a starting point for designing AI agents that can adapt to diverse scenarios. Due to the versatile capabilities they demonstrate, large language models (LLMs) are regarded as potential sparks for Artificial General Intelligence (AGI), offering hope for building general AI agents. Many researchers have leveraged LLMs as the foundation to build AI agents and have achieved significant progress. In this paper, we perform a comprehensive survey on LLM-based agents. We start by tracing the concept of agents from its philosophical origins to its development in AI, and explain why LLMs are suitable foundations for agents. Building upon this, we present a general framework for LLM-based agents, comprising three main components: brain, perception, and action, and the framework can be tailored for different applications. Subsequently, we explore the extensive applications of LLM-based agents in three aspects: single-agent scenarios, multi-agent scenarios, and human-agent cooperation. Following this, we delve into agent societies, exploring the behavior and personality of LLM-based agents, the social phenomena that emerge from an agent society, and the insights they offer for human society. Finally, we discuss several key topics and open problems within the field. A repository for the related papers at https://github.com/WooooDyy/LLM-Agent-Paper-List.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/0c72450890a54b68d63baa99376131fda8f06cf9

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

Citations in the corpus

CodeAgent: Enhancing Code Generation with Tool-Integrated Agent Systems for Real-World Repo-level Coding Challenges (2024, methodology): “Recent research has increasingly shown that LLMs can be instrumental in developing AI agents (Palo et al., 2023; Wang et al., 2023a; Xi et al., 2023).”
BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions (2024, background): “Interaction Recent interests are around the concept of LLMs as Agents [61], which is deemed as a way towards artificial general intelligence.”
Why Do Multi-Agent LLM Systems Fail? (2025, neutral): “Although the formal definition of agents remains a topic of debate (Cheng et al., 2024; Xi et al., 2023; Guo et al., 2024a; Li et al., 2024b; Wang et al., 2024b), in this study, we define a LLM-based agent as an artificial entity with prompt specifications (initial state), conversation trace…”
Large Language Model (LLM) for Telecommunications: A Comprehensive Survey on Principles, Key Techniques, and Opportunities (2024, background): “…that there have been diverse state-of-the-art explorations that are beyond the conventional language processing tasks, e.g., coding and debugging [18], recommendation [19], LLM-enabled agents [20], instruction-based optimization [21], network time-series prediction and decision making [22], etc.”
AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation (2023, neutral): “Large language models (LLMs) are becoming a crucial building block in developing powerful agents that utilize LLMs for reasoning, tool usage, and adapting to new observations (Yao et al., 2022; Xi et al., 2023; Wang et al., 2023b) in many real-world tasks.”
Agentless: Demystifying LLM-based Software Engineering Agents (2024, methodology): “As such, A GENTLESS builds a compressed format of each file that contains the list of class, function, or variable declarations.”
ReEvo: Large Language Models as Hyper-Heuristics with Reflective Evolution (2024, neutral): “The rise of LLMs introduces new prospects for diverse fields (Xi et al., 2023; Wang et al., 2023c; Zhao et al., 2023; Ji et al., 2023; Lu et al., 2023; Zhang et al., 2023a).”
Aligning Cyber Space With Physical World: A Comprehensive Survey on Embodied AI (2024, positive): “When these MLM-based agents are embodied in physical entities, they can effectively transfer their capabilities from virtual space to physical world, thereby becoming embodied agents [169].”
Empowering Biomedical Discovery with AI Agents (2024, neutral): “An AI agent is built as a compound system that consists of modules [3, 57, 58] each implementing a distinct functionality.”
A Survey on the Memory Mechanism of Large Language Model-based Agents (2024, neutral): “In previous works, the memory contents may come from different sources.”
Large Language Model based Multi-Agents: A Survey of Progress and Challenges (2024, methodology): “Timely survey papers systematically summarize the progress of LLM-based agents, as seen in works [Xi et al. , 2023; Wang et al. , 2023b].”
Security and Privacy Challenges of Large Language Models: A Survey (2024, neutral): “In Figure 3, we show different categories of security attacks in LLMs with their examples.”
Orthogonal Subspace Learning for Language Model Continual Learning (2023, background): “Learning tasks sequentially is crucial for developing real-world NLP models (Wang et al., 2023b; Xi et al., 2023), as it enables continuous evolution when encountering new tasks or knowledge.”
Recommendation as Instruction Following: A Large Language Model Empowered Recommendation Approach (2023, neutral): “Overall, we can flexibly integrate these four parts in the form of natural language text.”
Self-Polish: Enhance Reasoning in Large Language Models via Problem Refinement (2023, background): “We then include demonstrations in the prompts (Brown et al., 2020; Chowdhery et al., 2022) to enable models to better internalize and apply design principles, which is defined as in-context problem refining .”
Building Cooperative Embodied Agents Modularly with Large Language Models (2023, background): “Recently, numerous studies have explored language agents which use LLMs for sequential decision-making (Yang et al., 2023; Wang et al., 2023b; Xi et al., 2023; Sumers et al., 2023).”
AppAgent: Multimodal Agents as Smartphone Users (2023, neutral): “This includes performing tasks that require understanding context, making decisions, and learning from interactions [17, 40].”
Tool learning with large language models: a survey (2024, positive): “Meanwhile, we also acknowledge the foundational contributions of earlier perspective papers like those by Mialon et al. (2023) [45] and Qin et al. (2023) [16], which initially highlighted the promising opportunities that tools present to enhance LLMs capabilities.”
VisualWebArena: Evaluating Multimodal Agents on Realistic Visual Web Tasks (2024, background): “LLM Agents There has been significant recent interest in using Large Language Models (LLMs) for developing autonomous agents (Xi et al., 2023; Wang et al., 2023a).”