mlsanityData to 7 Oct 2026

TDAG: A Multi-Agent Framework based on Dynamic Task Decomposition and Agent Generation

arXiv 2402.10178 ↗First posted 15 Feb 2024cs.CLcited by 50

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

Abstract (arXiv)

The emergence of Large Language Models (LLMs) like ChatGPT has inspired the development of LLM-based agents capable of addressing complex, real-world tasks. However, these agents often struggle during task execution due to methodological constraints, such as error propagation and limited adaptability. To address this issue, we propose a multi-agent framework based on dynamic Task Decomposition and Agent Generation (TDAG). This framework dynamically decomposes complex tasks into smaller subtasks and assigns each to a specifically generated subagent, thereby enhancing adaptability in diverse and unpredictable real-world tasks. Simultaneously, existing benchmarks often lack the granularity needed to evaluate incremental progress in complex, multi-step tasks. In response, we introduce ItineraryBench in the context of travel planning, featuring interconnected, progressively complex tasks with a fine-grained evaluation system. ItineraryBench is designed to assess agents' abilities in memory, planning, and tool usage across tasks of varying complexity. Our experimental results reveal that TDAG significantly outperforms established baselines, showcasing its superior adaptability and context awareness in complex task scenarios.

Key facts. Cited by 50 papers in the map (data through 7 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. Builds on 17 of its 29 references that are in the map. First posted on arXiv 15 Feb 2024.

Builds on

17 of 29 references.

Closest ancestors · 4

Same direction, newest first

  1. 2023Igniting Language Intelligence: The Hitchhiker's Guide From Chain-of-Thought Reasoning to Language Agents20 Nov
  2. 2023Agent Instructs Large Language Models to be General Zero-Shot Reasoners5 Oct
  3. 2023The Rise and Potential of Large Language Model Based Agents: A Survey14 Sep
  4. 2023Gentopia: A Collaborative Platform for Tool-Augmented LLMs8 Aug

Other references · 13

  1. 2022Training language models to follow instructions with human feedbackcited by 15,712
  2. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  3. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,064
  4. 2023Voyager: An Open-Ended Embodied Agent with Large Language Modelscited by 2,081
  5. 2022Survey of Hallucination in Natural Language Generationcited by 2,056
  6. 2022WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agentscited by 1,197
  7. 2020ALFWorld: Aligning Text and Embodied Environments for Interactive Learningcited by 1,143
  8. 2023GAIA: a benchmark for General AI Assistantscited by 1,084
  9. 2024OS-Copilot: Towards Generalist Computer Agents with Self-Improvementcited by 203
  10. 2023OpenAGI: When LLM Meets Domain Expertscited by 196
  11. 2023ADaPT: As-Needed Decomposition and Planning with Language Modelscited by 172
  12. 2023PEARL: Prompting Large Language Models to Plan and Execute Actions Over Long Documentscited by 61
1 more
  1. 2023SheetCopilot: Bringing Software Productivity to the Next Level through Large Language Modelscited by 53

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 5; 2025: 26; 2026: 19.

50 papers.

Sort:

By area:

  1. 2024LLM Agents can Autonomously Exploit One-day Vulnerabilitiescited by 125
  2. 2025Deep Research Agents: A Systematic Examination And Roadmapcited by 122
  3. 2025Evaluating LLM-based Agents for Multi-Turn Conversations: A Surveycited by 56
  4. 2025A Survey of LLM-Driven AI Agent Communication: Protocols, Security Risks, and Defense Countermeasurescited by 54
  5. 2025LLM-based Agents Suffer from Hallucinations: A Survey of Taxonomy, Methods, and Directionscited by 49
  6. 2024Adaptive In-conversation Team Building for Language Model Agentscited by 38
  7. 2025Flow: Modularized Agentic Workflow Automationcited by 31
  8. 2025Internet of Agents: Fundamentals, Applications, and Challengescited by 31
  9. 2025Single-agent or Multi-agent Systems? Why Not Both?cited by 28
  10. 2024THREAD: Thinking Deeper with Recursive Spawningcited by 24
  11. 2024Advancing Agentic Systems: Dynamic Task Decomposition, Tool Integration and Evaluation using Novel Metrics and Datasetcited by 24
  12. 2025Adaptive Graph of Thoughts: Test-Time Adaptive Reasoning Unifying Chain, Tree, and Graph Structurescited by 16
38 more
  1. 2025A2Flow: Automating Agentic Workflow Generation via Self-Adaptive Abstraction Operatorscited by 14
  2. 2025Comparing AI Agents to Cybersecurity Professionals in Real-World Penetration Testingcited by 14
  3. 2025Exploring the Necessity of Reasoning in LLM-based Agent Scenarioscited by 10
  4. 2025Orchestrating Human-AI Teams: The Manager Agent as a Unifying Research Challengecited by 8
  5. 2025RedTeamLLM: an Agentic AI framework for offensive securitycited by 6
  6. 2025ROVER: Recursive Reasoning Over Videos with Vision-Language Models for Embodied Taskscited by 6
  7. 2025Select-Then-Decompose: From Empirical Analysis to Adaptive Selection Strategy for Task Decomposition in Large Language Modelscited by 5
  8. 2025TALM: Dynamic Tree-Structured Multi-Agent Framework with Long-Term Memory for Scalable Code Generationcited by 5
  9. 2025COALESCE: Economic and Security Dynamics of Skill-Based Task Outsourcing Among Team of Autonomous LLM Agentscited by 4
  10. 2025STRIDE: A Systematic Framework for Selecting AI Modalities -- Agentic AI, AI Assistants, or LLM Callscited by 4
  11. 2026VeriAgent: A Tool-Integrated Multi-Agent System with Evolving Memory for PPA-Aware RTL Code Generationcited by 4
  12. 2025AdaptBot: Combining LLM with Knowledge Graphs and Human Input for Generic-to-Specific Task Decomposition and Knowledge Refinementcited by 3
  13. 2025Instructional Agents: Reducing Teaching Faculty Workload through Multi-Agent Instructional Designcited by 3
  14. 2026The Six Sigma Agent: Achieving Enterprise-Grade Reliability in LLM Systems Through Consensus-Driven Decomposed Executioncited by 3
  15. 2025A Multi-Agent Framework for Mitigating Dialect Biases in Privacy Policy Question-Answering Systemscited by 2
  16. 2025Automating modeling in mechanics: LLMs as designers of physics-constrained neural networks for constitutive modeling of materialscited by 2
  17. 2026CoMAI: A Collaborative Multi-Agent Framework for Robust and Equitable Interview Evaluationcited by 2
  18. 2026MT-OSC: Path for LLMs that Get Lost in Multi-Turn Conversationcited by 2
  19. 2026TriVAL: A Tri-Validation Framework for Faithful Automatic Optimization Modelingcited by 2
  20. 2024Adaptable and Precise: Enterprise-Scenario LLM Function-Calling Capability Training Pipelinecited by 1
  21. 2025More Agents Improve Math Problem Solving but Adversarial Robustness Gap Persistscited by 1
  22. 2026TeamLLM: A Human-Like Team-Oriented Collaboration Framework for Multi-Step Contextualized Taskscited by 1
  23. 2026RefEvo: Agentic Design with Co-Evolutionary Verification for Agile Reference Model Generationcited by 1
  24. 2026Graph Engineering in the Era of LLM Agents: From Individual Intelligence to System Intelligencecited by 1
  25. 2025A Training-free LLM Framework with Interaction between Contextually Related Subtasks in Solving Complex Taskscited by 0
  26. 2025XAgents: A Unified Framework for Multi-Agent Cooperation via IF-THEN Rules and Multipolar Task Processing Graphcited by 0
  27. 2025From Passive to Proactive: A Hierarchical Multi-Agent Framework for Automated Medical Pre-Consultationcited by 0
  28. 2026ReusStdFlow: A Standardized Reusability Framework for Dynamic Workflow Construction in Agentic AIcited by 0
  29. 2026From Skills to Talent: Organising Heterogeneous Agents as a Real-World Companycited by 0
  30. 2026LLM-driven design of physics-constrained constitutive models: two agents are better than onecited by 0
  31. 2026Content-Based Smart E-Mail Dispatcher Using Large Language Modelscited by 0
  32. 2026When Do Multi-Agent Systems Help? An Information Bottleneck Perspectivecited by 0
  33. 2026Agents in the Wild: Where Research Meets Deploymentcited by 0
  34. 2026OrchBench: Evaluating Multi-Agent Orchestration Plans in Isolation via Deterministic Simulationcited by 0
  35. 2026Right-Sizing LLM-Agent Decomposition in VAT Determination: A Pilot Controlled Sweepcited by 0
  36. 2026A Hybrid Dependency-Aware Framework for Task Decomposition and Dynamic Agent Generation in Oracle-to-PostgreSQL Migrationcited by 0
  37. 2026Rethinking Multi-Agent Collaboration: When More Is Lesscited by 0
  38. 2026Pay for the Fault, Not the Flow: Label-Free In-Flow Multi-Agent Workflow Optimizationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025ReAcTree: Hierarchical LLM Agent Trees with Control Flow for Long-Horizon Task Planning
  2. 2025Adaptive Domain Modeling with Language Models: A Multi-Agent Approach to Task Planning
  3. 2024AgentGen: Enhancing Planning Abilities for Large Language Model based Agent via Environment and Task Generation
  4. 2025Plan-and-Act: Improving Planning of Agents for Long-Horizon Tasks
  5. 2025Multi-Mission Tool Bench: Assessing the Robustness of LLM based Agents through Related and Dynamic Missions
  6. 2026A Comprehensive Survey on Agent Skills: Taxonomy, Techniques, and Applications
  7. 2025CostBench: Evaluating Multi-Turn Cost-Optimal Planning and Adaptation in Dynamic Environments for LLM Tool-Use Agents
  8. 2025DynTaskMAS: A Dynamic Task Graph-driven Framework for Asynchronous and Parallel LLM-based Multi-Agent Systems