# Advancing Agentic Systems: Dynamic Task Decomposition, Tool Integration and Evaluation using Novel Metrics and Dataset

arXiv: https://arxiv.org/abs/2410.22457 · HTML: https://mlsanity.com/paper/2410.22457/

## Key facts

- Cited by 24 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 19 of its 32 references that are in the map.
- First posted on arXiv 29 Oct 2024.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 19 of 19)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [A Survey on Large Language Model based Autonomous Agents](https://mlsanity.com/paper/2308.11432/) (2023)
- [The Rise and Potential of Large Language Model Based Agents: A Survey](https://mlsanity.com/paper/2309.07864/) (2023)
- [AgentBench: Evaluating LLMs as Agents](https://mlsanity.com/paper/2308.03688/) (2023)
- [AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors](https://mlsanity.com/paper/2308.10848/) (2023)
- [AutoAgents: A Framework for Automatic Agent Generation](https://mlsanity.com/paper/2309.17288/) (2023)
- [TaskBench: Benchmarking Large Language Models for Task Automation](https://mlsanity.com/paper/2311.18760/) (2023)
- [VisualAgentBench: Towards Large Multimodal Models as Visual Foundation Agents](https://mlsanity.com/paper/2408.06327/) (2024)
- [Multi-Hop Knowledge Graph Reasoning with Reward Shaping](https://mlsanity.com/paper/1808.10568/) (2018)
- [TDAG: A Multi-Agent Framework based on Dynamic Task Decomposition and Agent Generation](https://mlsanity.com/paper/2402.10178/) (2024)
- [Metrics for Graph Comparison: A Practitioner's Guide](https://mlsanity.com/paper/1904.07414/) (2019)
- [Graph-enhanced Large Language Models in Asynchronous Plan Reasoning](https://mlsanity.com/paper/2402.02805/) (2024)
- [VillagerAgent: A Graph-Based Multi-Agent Framework for Coordinating Complex Task Dependencies in Minecraft](https://mlsanity.com/paper/2406.05720/) (2024)
- [A Comprehensive Survey of Dynamic Graph Neural Networks: Models, Frameworks, Benchmarks, Experiments and Challenges](https://mlsanity.com/paper/2405.00476/) (2024)
- [AgentQuest: A Modular Benchmark Framework to Measure Progress and Improve LLM Agents](https://mlsanity.com/paper/2404.06411/) (2024)
- [Coarse-grained decomposition and fine-grained interaction for multi-hop question answering](https://mlsanity.com/paper/2101.05988/) (2021)
- [BMW Agents -- A Framework For Task Automation Through Multi-Agent Collaboration](https://mlsanity.com/paper/2406.20041/) (2024)
- [Microstructures and Accuracy of Graph Recall by Large Language Models](https://mlsanity.com/paper/2402.11821/) (2024)

## Built on by (most cited first, 24 of 24)

- [Multi-Agent Collaboration Mechanisms: A Survey of LLMs](https://mlsanity.com/paper/2501.06322/) (2025)
- [A Survey of Frontiers in LLM Reasoning: Inference Scaling, Learning to Reason, and Agentic Systems](https://mlsanity.com/paper/2504.09037/) (2025)
- [A Survey of LLM-Driven AI Agent Communication: Protocols, Security Risks, and Defense Countermeasures](https://mlsanity.com/paper/2506.19676/) (2025)
- [Failure-Driven Workflow Refinement](https://mlsanity.com/paper/2510.10035/) (2025)
- [Auditing Multi-Agent LLM Reasoning Trees Outperforms Majority Vote and LLM-as-Judge](https://mlsanity.com/paper/2602.09341/) (2026)
- [The Measurement Imbalance in Agentic AI Evaluation Undermines Industry Productivity Claims](https://mlsanity.com/paper/2506.02064/) (2025)
- [Maestro: Learning to Collaborate via Conditional Listwise Policy Optimization for Multi-Agent LLMs](https://mlsanity.com/paper/2511.06134/) (2025)
- [Adaptive Collaboration with Humans: Metacognitive Policy Optimization for Multi-Agent LLMs with Continual Learning](https://mlsanity.com/paper/2603.07972/) (2026)
- [Long Context Scaling: Divide and Conquer via Multi-Agent Question-driven Collaboration](https://mlsanity.com/paper/2505.20625/) (2025)
- [Hey AI, Generate Me a Hardware Code! Agentic AI-based Hardware Design & Verification](https://mlsanity.com/paper/2507.02660/) (2025)
- [EpidemIQs: Prompt-to-Paper LLM Agents for Epidemic Modeling and Analysis](https://mlsanity.com/paper/2510.00024/) (2025)
- [STRIDE: A Systematic Framework for Selecting AI Modalities -- Agentic AI, AI Assistants, or LLM Calls](https://mlsanity.com/paper/2512.02228/) (2025)
- [Agentic AI Systems in Electrical Power Systems Engineering: Current State-of-the-Art and Challenges](https://mlsanity.com/paper/2511.14478/) (2025)
- [TopoPilot: Reliable Conversational Workflow Automation for Topological Data Analysis and Visualization](https://mlsanity.com/paper/2603.25063/) (2026)
- [Toward Data Systems That Are Business Semantic Centric and AI Agents Assisted](https://mlsanity.com/paper/2506.05520/) (2025)
- [Guided Collaboration in Heterogeneous LLM-Based Multi-Agent Systems via Entropy-Based Understanding Assessment and Experience Retrieval](https://mlsanity.com/paper/2602.13639/) (2026)
- [Agentic AI with Orchestrator-Agent Trust: A Modular Visual Classification Framework with Trust-Aware Orchestration and RAG-Based Reasoning](https://mlsanity.com/paper/2507.10571/) (2025)
- [RefEvo: Agentic Design with Co-Evolutionary Verification for Agile Reference Model Generation](https://mlsanity.com/paper/2604.24218/) (2026)
- [Position: Vibe Coding Needs Vibe Reasoning: Improving Vibe Coding with Formal Verification](https://mlsanity.com/paper/2511.00202/) (2025)
- [What's the next frontier for Data-centric AI? Data Savvy Agents](https://mlsanity.com/paper/2511.01015/) (2025)
- [ReusStdFlow: A Standardized Reusability Framework for Dynamic Workflow Construction in Agentic AI](https://mlsanity.com/paper/2602.14922/) (2026)
- [Agentic AI-based Coverage Closure for Formal Verification](https://mlsanity.com/paper/2603.03147/) (2026)
- [Generative AI and Digital Ecosystem Resilience: A Proactive Lifecycle-Based Survey](https://mlsanity.com/paper/2606.00136/) (2026)
- [Agents in the Wild: Where Research Meets Deployment](https://mlsanity.com/paper/2607.19336/) (2026)

## Abstract (arXiv)

Advancements in Large Language Models (LLMs) are revolutionizing the development of autonomous agentic systems by enabling dynamic, context-aware task decomposition and automated tool selection. These sophisticated systems possess significant automation potential across various industries, managing complex tasks, interacting with external systems to enhance knowledge, and executing actions independently. This paper presents three primary contributions to advance this field: - Advanced Agentic Framework: A system that handles multi-hop queries, generates and executes task graphs, selects appropriate tools, and adapts to real-time changes. - Novel Evaluation Metrics: Introduction of Node F1 Score, Structural Similarity Index (SSI), and Tool F1 Score to comprehensively assess agentic systems. - Specialized Dataset: Development of an AsyncHow-based dataset for analyzing agent behavior across different task complexities. Our findings reveal that asynchronous and dynamic task graph decomposition significantly enhances system responsiveness and scalability, particularly for complex, multi-step tasks. Detailed analysis shows that structural and node-level metrics are crucial for sequential tasks, while tool-related metrics are more important for parallel tasks. Specifically, the Structural Similarity Index (SSI) is the most significant predictor of performance in sequential tasks, and the Tool F1 Score is essential for parallel tasks. These insights highlight the need for balanced evaluation methods that capture both structural and operational dimensions of agentic systems. Additionally, our evaluation framework, validated through empirical analysis and statistical testing, provides valuable insights for improving the adaptability and reliability of agentic systems in dynamic environments.