Agents: An Open-source Framework for Autonomous Language Agents
On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks
Abstract (arXiv)
Recent advances on large language models (LLMs) enable researchers and developers to build autonomous language agents that can automatically solve various tasks and interact with environments, humans, and other agents using natural language interfaces. We consider language agents as a promising direction towards artificial general intelligence and release Agents, an open-source library with the goal of opening up these advances to a wider non-specialist audience. Agents is carefully engineered to support important features including planning, memory, tool usage, multi-agent communication, and fine-grained symbolic control. Agents is user-friendly as it enables non-specialists to build, customize, test, tune, and deploy state-of-the-art autonomous language agents without much coding. The library is also research-friendly as its modularized design makes it easily extensible for researchers. Agents is available at https://github.com/aiwaves-cn/agents.
Key facts. Cited by 116 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 16 of its 26 references that are in the map. First posted on arXiv 14 Sep 2023.
Builds on
16 of 26 references.
Closest ancestors · 3
Same direction, newest first
- 2023AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors21 Aug
- 2023Gentopia: A Collaborative Platform for Tool-Augmented LLMs8 Aug
- 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework1 Aug
Other references · 13
- 2020Language Models are Few-Shot Learnerscited by 32,419
- 2022Training language models to follow instructions with human feedbackcited by 15,971
- 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
- 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
- 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,182
- 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,568
- 2021WebGPT: Browser-assisted question-answering with human feedbackcited by 1,745
- 2023Gorilla: Large Language Model Connected with Massive APIscited by 1,332
- 2021Show Your Work: Scratchpads for Intermediate Computation with Language Modelscited by 886
- 2016Learning to Communicate with Deep Multi-Agent Reinforcement Learningcited by 575
- 2023A Real-World WebAgent with Planning, Long Context Understanding, and Program Synthesiscited by 353
- 2019Gradio: Hassle-Free Sharing and Testing of ML Models in the Wildcited by 178
1 more
Built on by
Citing papers per year: 2023: 14; 2024: 44; 2025: 49; 2026: 9.
116 papers.
Sort:
By area:
- 2024Large Language Model based Multi-Agents: A Survey of Progress and Challengescited by 769
- 2025Memory in the Age of AI Agentscited by 303
- 2024R-Judge: Benchmarking Safety Risk Awareness for LLM Agentscited by 288
- 2024Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Securitycited by 260
- 2024Scaling Large Language Model-based Multi-Agent Collaborationcited by 241
- 2024Agent-as-a-Judge: Evaluate Agents with Agentscited by 238
- 2024Data Interpreter: An LLM Agent For Data Sciencecited by 225
- 2023Exploring Collaboration Mechanisms for LLM Agents: A Social Psychology Viewcited by 222
- 2025WebDancer: Towards Autonomous Information Seeking Agencycited by 188
- 2025MultiAgentBench: Evaluating the Collaboration and Competition of LLM agentscited by 178
- 2025WebWalker: Benchmarking LLMs in Web Traversalcited by 175
- 2023OpenAgents: An Open Platform for Language Agents in the Wildcited by 137
38 more
- 2025A Survey of Context Engineering for Large Language Modelscited by 126
- 2024AgentScope: A Flexible yet Robust Multi-Agent Platformcited by 121
- 2023How Many Unicorns Are in This Image? A Safety Evaluation Benchmark for Vision LLMscited by 108
- 2025Multi-Agent Collaboration via Evolving Orchestrationcited by 108
- 2025Memp: Exploring Agent Procedural Memorycited by 103
- 2024On the Resilience of LLM-Based Multi-Agent Collaboration with Faulty Agentscited by 99
- 2024Chain of Ideas: Revolutionizing Research Via Novel Idea Development with LLM Agentscited by 97
- 2025Agent KB: Leveraging Cross-Domain Experience for Agentic Problem Solvingcited by 94
- 2023TaskWeaver: A Code-First Agent Frameworkcited by 86
- 2025Chain-of-Agents: End-to-End Agent Foundation Models via Multi-Agent Distillation and Agentic RLcited by 80
- 2023Igniting Language Intelligence: The Hitchhiker's Guide From Chain-of-Thought Reasoning to Language Agentscited by 72
- 2024Agent Planning with World Knowledge Modelcited by 70
- 2023ML-Bench: Evaluating Large Language Models and Agents for Machine Learning Tasks on Repository-Level Codecited by 65
- 2024A Comparative Study on Reasoning Patterns of OpenAI's o1 Modelcited by 63
- 2025Scaling Test-time Compute for LLM Agentscited by 63
- 2025A Survey on (M)LLM-Based GUI Agentscited by 62
- 2024KnowAgent: Knowledge-Augmented Planning for LLM-Based Agentscited by 61
- 2025Contextual Agent Security: A Policy for Every Purposecited by 59
- 2023Experiential Co-Learning of Software-Developing Agentscited by 57
- 2025Towards General Agentic Intelligence via Environment Scalingcited by 54
- 2024WIPI: A New Web Threat for LLM-Driven Web Agentscited by 51
- 2025TaskCraft: Automated Generation of Agentic Taskscited by 51
- 2023Lyfe Agents: Generative agents for low-cost real-time social interactionscited by 49
- 2024Risks of AI Scientists: Prioritizing Safeguarding Over Autonomycited by 49
- 2023LLM-Powered Hierarchical Language Agent for Real-time Human-AI Coordinationcited by 48
- 2024A Multi-Agent Conversational Recommender Systemcited by 43
- 2025EvolveSearch: An Iterative Self-Evolving Search Agentcited by 43
- 2024Adaptive In-conversation Team Building for Language Model Agentscited by 39
- 2024CellAgent: An LLM-driven Multi-Agent Framework for Automated Single-cell Data Analysiscited by 39
- 2023LLM as OS, Agents as Apps: Envisioning AIOS, Agents and the AIOS-Agent Ecosystemcited by 38
- 2024Benchmarking Agentic Workflow Generationcited by 37
- 2025MPO: Boosting LLM Agents with Meta Plan Optimizationcited by 36
- 2025OS Agents: A Survey on MLLM-based Agents for General Computing Devices Usecited by 35
- 2025Flow: Modularized Agentic Workflow Automationcited by 34
- 2025textitAgents Under Siege: Breaking Pragmatic Multi-Agent LLM Systems with Optimized Prompt Attackscited by 34
- 2025A Survey of Large Language Model Empowered Agents for Recommendation and Search: Towards Next-Generation Information Retrievalcited by 33
- 2024AI PERSONA: Towards Life-long Personalization of LLMscited by 32
- 2025Efficient Agents: Building Effective Agents While Reducing Costcited by 32
50 most cited of 116 All 116 (JSON)
- 2026AgentXploit: Autonomous Repository-to-Runtime Red-Teaming for AI Agents25 Sep 2026
- 2026Resource-Optimized and Energy-Aware Agentic AI Framework Anchored on Blockchain for Secure Software Supply Chains25 Sep 2026
- 2026ConsistencyGate: Preventing Memory Contamination in LLM Agents via Self-Consistency Admission Control25 Jul 2026
- 2026What makes a harness a harness: necessary and sufficient conditions for an agent harness8 Jun 2026
- 2026PAC-BENCH: Evaluating Multi-Agent Collaboration under Privacy Constraints13 Apr 2026
- 2026LangMARL: Natural Language Multi-Agent Reinforcement Learning1 Apr 2026
- 2026RoboRouter: Training-Free Policy Routing for Robotic Manipulation9 Mar 2026
- 2026Search More, Think Less: Rethinking Long-Horizon Agentic Search for Efficiency and Generalization26 Feb 2026
- 2026O-Researcher: An Open Ended Deep Research Model via Multi-Agent Distillation and Agentic RL7 Jan 2026
- 2025Memory in the Age of AI Agents15 Dec 2025
- 2025Dynamic System Instructions and Tool Exposure for Efficient Agentic LLMs1 Dec 2025
- 2025O-Mem: Omni Memory System for Personalized, Long Horizon, Self-Evolving Agents17 Nov 2025
38 more
- 2025Agentic Meta-Orchestrator for Multi-task Copilots26 Oct 2025
- 2025Fetch.ai: An Architecture for Modern Multi-Agent Systems21 Oct 2025
- 2025A Goal Without a Plan Is Just a Wish: Efficient and Effective Global Planner Training for Long-Horizon Agent Tasks7 Oct 2025
- 2025JoyAgent-JDGenie: Technical Report on the GAIA1 Oct 2025
- 2025Flash-Searcher: Fast and Effective Web Agents via DAG-Based Parallel Execution29 Sep 2025
- 2025Towards Personalized Deep Research: Benchmarks and Evaluations29 Sep 2025
- 2025Scaling Generalist Data-Analytic Agents29 Sep 2025
- 2025Towards General Agentic Intelligence via Environment Scaling16 Sep 2025
- 2025Memp: Exploring Agent Procedural Memory8 Aug 2025
- 2025Chain-of-Agents: End-to-End Agent Foundation Models via Multi-Agent Distillation and Agentic RL6 Aug 2025
- 2025OS Agents: A Survey on MLLM-based Agents for General Computing Devices Use6 Aug 2025
- 2025Efficient Agents: Building Effective Agents While Reducing Cost24 Jul 2025
- 2025A Survey of Context Engineering for Large Language Models17 Jul 2025
- 2025Introspection of Thought Helps AI Agents11 Jul 2025
- 2025Agent KB: Leveraging Cross-Domain Experience for Agentic Problem Solving8 Jul 2025
- 2025Unleashing Embodied Task Planning Ability in LLMs via Reinforcement Learning29 Jun 2025
- 2025CitySim: Modeling Urban Behaviors and City Dynamics with Large-Scale LLM-Driven Agent Simulation26 Jun 2025
- 2025SwarmAgentic: Towards Fully Automated Agentic System Generation via Swarm Intelligence18 Jun 2025
- 2025OAgents: An Empirical Study of Building Effective Agents17 Jun 2025
- 2025Scaling Test-time Compute for LLM Agents15 Jun 2025
- 2025TaskCraft: Automated Generation of Agentic Tasks11 Jun 2025
- 2025Self-Evolving Multi-Agent Systems via Textual Backpropagation10 Jun 2025
- 2025WebDancer: Towards Autonomous Information Seeking Agency28 May 2025
- 2025EvolveSearch: An Iterative Self-Evolving Search Agent28 May 2025
- 2025Large Language Models Miss the Multi-Agent Mark27 May 2025
- 2025Multi-Agent Collaboration via Evolving Orchestration26 May 2025
- 2025Get Experience from Practice: LLM Agents with Record & Replay23 May 2025
- 2025ReflAct: World-Grounded Decision Making in LLM Agents via Goal-State Reflection21 May 2025
- 2025GuideBench: Benchmarking Domain-Oriented Guideline Following for LLM Agents16 May 2025
- 2025The Hitchhikers Guide to Production-ready Trustworthy Foundation Model powered Software (FMware)15 May 2025
- 2025MobileCity: An Efficient Framework for Large-Scale Urban Behavior Simulation18 Apr 2025
- 2025Orchestrating Agents and Data for Enterprise: A Blueprint Architecture for Compound AI10 Apr 2025
- 2025FactGuard: Leveraging Multi-Agent Systems to Generate Answerable and Unanswerable Questions for Enhanced Long-Context LLM Extraction8 Apr 2025
- 2025SynWorld: Virtual Scenario Synthesis for Agentic Action Knowledge Refinement4 Apr 2025
- 2025textitAgents Under Siege: Breaking Pragmatic Multi-Agent LLM Systems with Optimized Prompt Attacks31 Mar 2025
- 2025EncGPT: A Multi-Agent Workflow for Dynamic Encryption Algorithms29 Mar 2025
- 2025A Survey on (M)LLM-Based GUI Agents27 Mar 2025
- 2025Inducing Personality in LLM-Based Honeypot Agents: Measuring the Effect on Human-Like Agenda Generation25 Mar 2025
50 newest of 116 All 116 (JSON)
- 2024Large Language Model based Multi-Agents: A Survey of Progress and Challengescited by 769
- 2025Memory in the Age of AI Agentscited by 303
- 2024R-Judge: Benchmarking Safety Risk Awareness for LLM Agentscited by 288
- 2024Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Securitycited by 260
- 2024Scaling Large Language Model-based Multi-Agent Collaborationcited by 241
- 2024Agent-as-a-Judge: Evaluate Agents with Agentscited by 238
- 2024Data Interpreter: An LLM Agent For Data Sciencecited by 225
- 2025WebDancer: Towards Autonomous Information Seeking Agencycited by 188
- 2023OpenAgents: An Open Platform for Language Agents in the Wildcited by 137
- 2024AgentScope: A Flexible yet Robust Multi-Agent Platformcited by 121
- 2025Multi-Agent Collaboration via Evolving Orchestrationcited by 108
- 2025Memp: Exploring Agent Procedural Memorycited by 103
12 most cited of 80 All 80 (JSON)
- 2026AgentXploit: Autonomous Repository-to-Runtime Red-Teaming for AI Agents25 Sep 2026
- 2026What makes a harness a harness: necessary and sufficient conditions for an agent harness8 Jun 2026
- 2026LangMARL: Natural Language Multi-Agent Reinforcement Learning1 Apr 2026
- 2026Search More, Think Less: Rethinking Long-Horizon Agentic Search for Efficiency and Generalization26 Feb 2026
- 2026O-Researcher: An Open Ended Deep Research Model via Multi-Agent Distillation and Agentic RL7 Jan 2026
- 2025Memory in the Age of AI Agents15 Dec 2025
- 2025Dynamic System Instructions and Tool Exposure for Efficient Agentic LLMs1 Dec 2025
- 2025O-Mem: Omni Memory System for Personalized, Long Horizon, Self-Evolving Agents17 Nov 2025
- 2025Agentic Meta-Orchestrator for Multi-task Copilots26 Oct 2025
- 2025Fetch.ai: An Architecture for Modern Multi-Agent Systems21 Oct 2025
- 2025A Goal Without a Plan Is Just a Wish: Efficient and Effective Global Planner Training for Long-Horizon Agent Tasks7 Oct 2025
- 2025Flash-Searcher: Fast and Effective Web Agents via DAG-Based Parallel Execution29 Sep 2025
12 newest of 80 All 80 (JSON)
- 2025MultiAgentBench: Evaluating the Collaboration and Competition of LLM agentscited by 178
- 2023How Many Unicorns Are in This Image? A Safety Evaluation Benchmark for Vision LLMscited by 108
- 2025Chain-of-Agents: End-to-End Agent Foundation Models via Multi-Agent Distillation and Agentic RLcited by 80
- 2023Igniting Language Intelligence: The Hitchhiker's Guide From Chain-of-Thought Reasoning to Language Agentscited by 72
- 2024A Comparative Study on Reasoning Patterns of OpenAI's o1 Modelcited by 63
- 2025Scaling Test-time Compute for LLM Agentscited by 63
- 2026ConsistencyGate: Preventing Memory Contamination in LLM Agents via Self-Consistency Admission Controlcited by 6
- 2025Introspection of Thought Helps AI Agentscited by 4
- 2026ConsistencyGate: Preventing Memory Contamination in LLM Agents via Self-Consistency Admission Control25 Jul 2026
- 2025Chain-of-Agents: End-to-End Agent Foundation Models via Multi-Agent Distillation and Agentic RL6 Aug 2025
- 2025Introspection of Thought Helps AI Agents11 Jul 2025
- 2025Scaling Test-time Compute for LLM Agents15 Jun 2025
- 2025MultiAgentBench: Evaluating the Collaboration and Competition of LLM agents3 Mar 2025
- 2024A Comparative Study on Reasoning Patterns of OpenAI's o1 Model17 Oct 2024
- 2023How Many Unicorns Are in This Image? A Safety Evaluation Benchmark for Vision LLMs27 Nov 2023
- 2023Igniting Language Intelligence: The Hitchhiker's Guide From Chain-of-Thought Reasoning to Language Agents20 Nov 2023
- 2023Exploring Collaboration Mechanisms for LLM Agents: A Social Psychology Viewcited by 222
- 2024Agent Planning with World Knowledge Modelcited by 70
- 2024Agent Planning with World Knowledge Model23 May 2024
- 2023Exploring Collaboration Mechanisms for LLM Agents: A Social Psychology View3 Oct 2023
- 2024ING-VP: MLLMs cannot Play Easy Vision-based Games Yetcited by 11
- 2024ING-VP: MLLMs cannot Play Easy Vision-based Games Yet9 Oct 2024
- 2025WebWalker: Benchmarking LLMs in Web Traversalcited by 175
- 2025WebWalker: Benchmarking LLMs in Web Traversal13 Jan 2025
- 2025A Survey of Context Engineering for Large Language Modelscited by 126
- 2025Contextual Agent Security: A Policy for Every Purposecited by 59
- 2024Risks of AI Scientists: Prioritizing Safeguarding Over Autonomycited by 49
- 2024AI PERSONA: Towards Life-long Personalization of LLMscited by 32
- 2024How Far Are We From AGI: Are LLMs All We Need?cited by 31
- 2024AI for social science and social science of AI: A Surveycited by 29
- 2024PsychoGAT: A Novel Psychological Measurement Paradigm through Interactive Fiction Games with LLM Agentscited by 28
- 2023Editing Personality for Large Language Modelscited by 22
- 2024A Survey on Game Playing Agents and Large Models: Methods, Applications, and Challengescited by 22
- 2024MobileAgent: enhancing mobile control via human-machine interaction and SOP integrationcited by 18
- 2023Large Knowledge Model: Perspectives and Challengescited by 12
- 2024Toward a Team of AI-made Scientists for Scientific Discovery from Gene Expression Datacited by 10
12 most cited of 23 All 23 (JSON)
- 2026Resource-Optimized and Energy-Aware Agentic AI Framework Anchored on Blockchain for Secure Software Supply Chains25 Sep 2026
- 2026PAC-BENCH: Evaluating Multi-Agent Collaboration under Privacy Constraints13 Apr 2026
- 2025JoyAgent-JDGenie: Technical Report on the GAIA1 Oct 2025
- 2025A Survey of Context Engineering for Large Language Models17 Jul 2025
- 2025Unleashing Embodied Task Planning Ability in LLMs via Reinforcement Learning29 Jun 2025
- 2025The Hitchhikers Guide to Production-ready Trustworthy Foundation Model powered Software (FMware)15 May 2025
- 2025Reviewing Clinical Knowledge in Medical Large Language Models: Training and Beyond28 Feb 2025
- 2025Contextual Agent Security: A Policy for Every Purpose28 Jan 2025
- 2024AI PERSONA: Towards Life-long Personalization of LLMs17 Dec 2024
- 2024Transforming Agency. On the mode of existence of Large Language Models15 Jul 2024
- 2024LangSuitE: Planning, Controlling and Interacting with Large Language Models in Embodied Text Environments24 Jun 2024
- 2024How Far Are We From AGI: Are LLMs All We Need?16 May 2024
12 newest of 23 All 23 (JSON)
Similar, not cited
Close in wording, no citation either way
- 2023The Rise and Potential of Large Language Model Based Agents: A Survey
- 2025Large Language Model Agent: A Survey on Methodology, Applications and Challenges
- 2024Exploring Large Language Model based Intelligent Agents: Definitions, Methods, and Prospects
- 2023A Survey on Large Language Model based Autonomous Agents
- 2025From Language to Action: A Review of Large Language Models as Autonomous Agents and Tool Users
- 2025Small Language Models are the Future of Agentic AI
- 2024AgentGym: Evolving Large Language Model-based Agents across Diverse Environments
- 2026Cognitive Models and AI Algorithms Provide Templates for Designing Language Agents