mlsanityData to 14 Oct 2026

From Language to Action: A Review of Large Language Models as Autonomous Agents and Tool Users

arXiv 2508.17281 ↗First posted 24 Aug 2025cs.CLcited by 32

On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks

Abstract (arXiv)

The pursuit of human-level artificial intelligence (AI) has significantly advanced the development of autonomous agents and Large Language Models (LLMs). LLMs are now widely utilized as decision-making agents for their ability to interpret instructions, manage sequential tasks, and adapt through feedback. This review examines recent developments in employing LLMs as autonomous agents and tool users and comprises seven research questions. We only used the papers published between 2023 and 2025 in conferences of the A* and A rank and Q1 journals. A structured analysis of the LLM agents' architectural design principles, dividing their applications into single-agent and multi-agent systems, and strategies for integrating external tools is presented. In addition, the cognitive mechanisms of LLM, including reasoning, planning, and memory, and the impact of prompting methods and fine-tuning procedures on agent performance are also investigated. Furthermore, we evaluated current benchmarks and assessment protocols and have provided an analysis of 68 publicly available datasets to assess the performance of LLM-based agents in various tasks. In conducting this review, we have identified critical findings on verifiable reasoning of LLMs, the capacity for self-improvement, and the personalization of LLM-based agents. Finally, we have discussed ten future research directions to overcome these gaps.

Key facts. Cited by 32 papers in the map (data through 14 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. Builds on 163 of its 221 references that are in the map. First posted on arXiv 24 Aug 2025.

Builds on

163 of 221 references.

Closest ancestors · 40

Same direction, newest first

  1. 2025Theorem-of-Thought: A Multi-Agent Framework for Abductive, Deductive, and Inductive Reasoning in Language Models8 Jun
  2. 2025From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review28 Apr
  3. 2025Large Language Model Agent: A Survey on Methodology, Applications and Challenges27 Mar
  4. 2024Star-Agents: Automatic Data Optimization with LLM Agents for Instruction Tuning21 Nov
  5. 2024Probing the Capacity of Language Model Agents to Operationalize Disparate Experiential Context Despite Distraction19 Nov
  6. 2024ComfyBench: Benchmarking LLM-based Agents in ComfyUI for Autonomously Designing Collaborative AI Systems2 Sep
  7. 2024On the Resilience of LLM-Based Multi-Agent Collaboration with Faulty Agents2 Aug
  8. 2024Recursive Introspection: Teaching Language Model Agents How to Self-Improve25 Jul
  9. 2024AvaTaR: Optimizing LLM Agents for Tool Usage via Contrastive Reasoning17 Jun
  10. 2024A Review of Prominent Paradigms for LLM-Based Agents: Tool Use (Including RAG), Planning, and Feedback Learning9 Jun
  11. 2024Chain of Agents: Large Language Models Collaborating on Long-Context Tasks4 Jun
  12. 2024Agent Planning with World Knowledge Model23 May
28 more
  1. 2024Fleet of Agents: Coordinated Problem Solving with Large Language Models7 May
  2. 2024AutoGuide: Automated Generation and Selection of Context-Aware Guidelines for Large Language Model Agents13 Mar
  3. 2024SOTOPIA-π: Interactive Learning of Socially Intelligent Language Agents13 Mar
  4. 2024Bootstrapping Cognitive Agents with a Large Language Model25 Feb
  5. 2024Large Language Model-based Human-Agent Collaboration for Complex Task Solving20 Feb
  6. 2024Offline Training of Language Model Agents with Functions as Learnable Weights17 Feb
  7. 2024Tell Me More! Towards Implicit User Intention Understanding of Language Model Driven Agents14 Feb
  8. 2024TimeArena: Shaping Efficient Multitasking Language Agents in a Time-Aware Simulation8 Feb
  9. 2024LLM Multi-Agent Systems: Challenges and Open Problems5 Feb
  10. 2024TravelPlanner: A Benchmark for Real-World Planning with Language Agents2 Feb
  11. 2024AgentBoard: An Analytical Evaluation Board of Multi-turn LLM Agents24 Jan
  12. 2024Large Language Model based Multi-Agents: A Survey of Progress and Challenges21 Jan
  13. 2024Exploring Large Language Model based Intelligent Agents: Definitions, Methods, and Prospects7 Jan
  14. 2023Large Language Models Empowered Agent-based Modeling and Simulation: A Survey and Perspectives19 Dec
  15. 2023Agent Lumos: Unified and Modular Training for Open-Source Language Agents9 Nov
  16. 2023Theory of Mind for Multi-Agent Collaboration via Large Language Models16 Oct
  17. 2023Lemur: Harmonizing Natural Language and Code for Language Agents10 Oct
  18. 2023SMART-LLM: Smart Multi-Agent Robot Task Planning using Large Language Models18 Sep
  19. 2023The Rise and Potential of Large Language Model Based Agents: A Survey14 Sep
  20. 2023A Survey on Large Language Model based Autonomous Agents22 Aug
  21. 2023ProAgent: Building Proactive Cooperative Agents with Large Language Models22 Aug
  22. 2023AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors21 Aug
  23. 2023AgentBench: Evaluating LLMs as Agents7 Aug
  24. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework1 Aug
  25. 2023Building Cooperative Embodied Agents Modularly with Large Language Models5 Jul
  26. 2023Multi-Agent Collaboration: Harnessing the Power of Intelligent LLM Agents5 Jun
  27. 2023CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society31 Mar
  28. 2023Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agents3 Feb

Other references · 123

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2022Training language models to follow instructions with human feedbackcited by 15,971
  3. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  4. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  5. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  6. 2021Evaluating Large Language Models Trained on Codecited by 8,320
  7. 2020Measuring Massive Multitask Language Understandingcited by 7,963
  8. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,276
  9. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,182
  10. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
  11. 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,720
  12. 2014Deep Learning Face Attributes in the Wildcited by 3,693
38 more
  1. 2021Program Synthesis with Large Language Modelscited by 3,637
  2. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,568
  3. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,211
  4. 2023Universal and Transferable Adversarial Attacks on Aligned Language Modelscited by 3,104
  5. 2023Voyager: An Open-Ended Embodied Agent with Large Language Modelscited by 2,191
  6. 2023PaLM-E: An Embodied Multimodal Language Modelcited by 2,071
  7. 2022Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language modelscited by 1,998
  8. 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversationcited by 1,988
  9. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIscited by 1,947
  10. 2018FEVER: a large-scale dataset for Fact Extraction and VERificationcited by 1,375
  11. 2023Mind2Web: Towards a Generalist Agent for the Webcited by 1,242
  12. 2020ALFWorld: Aligning Text and Embodied Environments for Interactive Learningcited by 1,205
  13. 2024The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scalecited by 1,160
  14. 2023GAIA: a benchmark for General AI Assistantscited by 1,128
  15. 2022Measuring and Narrowing the Compositionality Gap in Language Modelscited by 1,075
  16. 2025A-MEM: Agentic Memory for LLM Agentscited by 1,063
  17. 2017Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environmentscited by 1,027
  18. 2023Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotationscited by 928
  19. 2023ChatDev: Communicative Agents for Software Developmentcited by 919
  20. 2021MuSiQue: Multihop Questions via Single-hop Question Compositioncited by 916
  21. 2023BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Datasetcited by 860
  22. 2019ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Taskscited by 783
  23. 2023The RefinedWeb Dataset for Falcon LLM: Outperforming Curated Corpora with Web Data, and Web Data Onlycited by 763
  24. 2021Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategiescited by 743
  25. 2023WizardCoder: Empowering Code Large Language Models with Evol-Instructcited by 733
  26. 2023OpenAssistant Conversations -- Democratizing Large Language Model Alignmentcited by 721
  27. 2023CogAgent: A Visual Language Model for GUI Agentscited by 704
  28. 2023BridgeData V2: A Dataset for Robot Learning at Scalecited by 657
  29. 2023ChemCrow: Augmenting large-language models with chemistry toolscited by 631
  30. 2024WildChat: 1M ChatGPT Interaction Logs in the Wildcited by 629
  31. 2017The NarrativeQA Reading Comprehension Challengecited by 597
  32. 2023Identifying the Risks of LM Agents with an LM-Emulated Sandboxcited by 548
  33. 2022Language Models are Multilingual Chain-of-Thought Reasonerscited by 530
  34. 2023"Do Anything Now": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Modelscited by 489
  35. 2021A Dataset of Information-Seeking Questions and Answers Anchored in Research Paperscited by 486
  36. 2022LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language Modelscited by 462
  37. 2025Agent Laboratory: Using LLM Agents as Research Assistantscited by 425
  38. 2025Accelerating scientific discovery with Co-Scientistcited by 401

50 most cited of 123 All 123 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 5; 2026: 27.

32 papers.

Sort:

By area:

  1. 2026Long-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks with Dense Reward-Based Gradingcited by 31
  2. 2026Recursive Synthesis for Long-Horizon Terminal Taskscited by 19
  3. 2026DualPath: Breaking the Storage Bandwidth Bottleneck in Agentic LLM Inferencecited by 15
  4. 2026Toward Personalized LLM-Powered Agents: Foundations, Evaluation, and Future Directionscited by 14
  5. 2026AI Agent Systems: Architectures, Applications, and Evaluationcited by 13
  6. 2025BiasBusters: Uncovering and Mitigating Tool Selection Bias in Large Language Modelscited by 11
  7. 2025Agentic AI Home Energy Management System: A Large Language Model Framework for Residential Load Schedulingcited by 8
  8. 2026FAMA: Failure-Aware Meta-Agentic Framework for Open-Source LLMs in Interactive Tool Use Environmentscited by 4
  9. 2026AIvilization v0: Toward Large-Scale Artificial Social Simulation with a Unified Agent Architecture and Adaptive Agent Profilescited by 3
  10. 2026Architecting Trust in Artificial Epistemic Agentscited by 3
  11. 2026Distilling Feedback into Memory-as-a-Toolcited by 2
  12. 2026A multi-agent system for spine MRI report generation from multi-sequence imagingcited by 2
20 more
  1. 2025An LLM-Powered Cooperative Framework for Large-Scale Multi-Vehicle Navigationcited by 1
  2. 2026Project Synapse: A Hierarchical Multi-Agent Framework with Hybrid Memory for Autonomous Resolution of Last-Mile Delivery Disruptionscited by 1
  3. 2026Fine-Tuning Large Language Models for Cooperative Tactical Deconfliction of Small Unmanned Aerial Systemscited by 1
  4. 2026SelfHeal: Empirical Fix Pattern Analysis and Bug Repair in LLM Agentscited by 1
  5. 2026Plausible but Wrong: A case study on Agentic Failures in Astrophysical Workflowscited by 1
  6. 2026What We Talk About When We Talk About LLM Planning: Evidence for Two Distinct Planning Abilitiescited by 1
  7. 2026TrajWiki: Source-Grounded Memory Trajectories for Long-Horizon Dialogue Agentscited by 1
  8. 2026Agents in the Large: Perception-Centered Architecture for Persistent Agentscited by 1
  9. 2026WeAgent-MMGenEdit: A Full-Stack Recipe for Multimodal Agentic Image Generation and Editingcited by 1
  10. 2025Lark: Biologically Inspired Neuroevolution for Multi-Stakeholder LLM Agentscited by 0
  11. 2025Needle in the Web: A Benchmark for Retrieving Targeted Web Pages in the Wildcited by 0
  12. 2026Conversational Demand Response: Bidirectional Aggregator-Prosumer Coordination through Agentic AIcited by 0
  13. 2026Detection of adversarial intent in Human-AI teams using LLMscited by 0
  14. 2026Rule-VLN: Bridging Perception and Compliance via Semantic Reasoning and Geometric Rectificationcited by 0
  15. 2026Multi-Agent Systems: From Classical Paradigms to Large Foundation Model-Enabled Futurescited by 0
  16. 2026Alignment has a Fantasia Problemcited by 0
  17. 2026LLM-enabled Social Agentscited by 0
  18. 2026Diagnosis-Driven Automatic Repair for Agentic Workflow via Symbolic Inferencecited by 0
  19. 2026Communication-Efficient Digital-Twin Coordination for Heterogeneous LLM Embodied Agents over Computing Power Networkscited by 0
  20. 2026Jev-IDS: System One Models for Network Intrusion Detectioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Fundamentals of Building Autonomous LLM Agents
  2. 2024Understanding the planning of LLM agents: A survey
  3. 2026The Path Ahead for Agentic AI: Challenges and Opportunities
  4. 2024Exploring Autonomous Agents through the Lens of Large Language Models: A Review
  5. 2025LLM-Based Human-Agent Collaboration and Interaction Systems: A Survey
  6. 2023An In-depth Survey of Large Language Model-based Artificial Intelligence Agents
  7. 2024Practical Considerations for Agentic LLM Systems
  8. 2023TPTU: Large Language Model-based AI Agents for Task Planning and Tool Usage