mlsanityData to 14 Oct 2026

AgentKit: Structured LLM Reasoning with Dynamic Graphs

arXiv 2404.11483 ↗First posted 17 Apr 2024cs.AI cs.LGcited by 13

On the map: LLM reasoning → Reasoning for agents, planning and code

Abstract (arXiv)

We propose an intuitive LLM prompting framework (AgentKit) for multifunctional agents. AgentKit offers a unified framework for explicitly constructing a complex "thought process" from simple natural language prompts. The basic building block in AgentKit is a node, containing a natural language prompt for a specific subtask. The user then puts together chains of nodes, like stacking LEGO pieces. The chains of nodes can be designed to explicitly enforce a naturally structured "thought process". For example, for the task of writing a paper, one may start with the thought process of 1) identify a core message, 2) identify prior research gaps, etc. The nodes in AgentKit can be designed and combined in different ways to implement multiple advanced capabilities including on-the-fly hierarchical planning, reflection, and learning from interactions. In addition, due to the modular nature and the intuitive design to simulate explicit human thought process, a basic agent could be implemented as simple as a list of prompts for the subtasks and therefore could be designed and tuned by someone without any programming experience. Quantitatively, we show that agents designed through AgentKit achieve SOTA performance on WebShop and Crafter. These advances underscore AgentKit's potential in making LLM agents effective and accessible for a wider range of applications. https://github.com/holmeswww/AgentKit

Key facts. Cited by 13 papers in the map (data through 14 Oct 2026). Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning. Builds on 38 of its 43 references that are in the map. First posted on arXiv 17 Apr 2024.

Builds on

38 of 43 references.

References · 38

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2022Training language models to follow instructions with human feedbackcited by 15,971
  3. 2017Proximal Policy Optimization Algorithmscited by 15,215
  4. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  5. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  6. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  7. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  8. 2020Measuring Massive Multitask Language Understandingcited by 7,963
  9. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,326
  10. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,276
  11. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,442
  12. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,211
26 more
  1. 2023Mistral 7Bcited by 3,164
  2. 2023Sparks of Artificial General Intelligence: Early experiments with GPT-4cited by 2,592
  3. 2023Voyager: An Open-Ended Embodied Agent with Large Language Modelscited by 2,191
  4. 2023AgentBench: Evaluating LLMs as Agentscited by 1,267
  5. 2023Mastering Diverse Domains through World Modelscited by 1,253
  6. 2022WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agentscited by 1,251
  7. 2022Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agentscited by 1,035
  8. 2020Mastering Atari with Discrete World Modelscited by 1,007
  9. 2018Exploration by Random Network Distillationcited by 993
  10. 2023Graph of Thoughts: Solving Elaborate Problems with Large Language Modelscited by 886
  11. 2023DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelinescited by 832
  12. 2017Rainbow: Combining Improvements in Deep Reinforcement Learningcited by 786
  13. 2023Textbooks Are All You Need II: phi-1.5 technical reportcited by 565
  14. 2022LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language Modelscited by 462
  15. 2023Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agentscited by 398
  16. 2015Neural Module Networkscited by 376
  17. 2020Planning to Explore via Self-Supervised World Modelscited by 368
  18. 2021Benchmarking the Spectrum of Agent Capabilitiescited by 200
  19. 2023Guiding Pretraining in Reinforcement Learning with Large Language Modelscited by 187
  20. 2023JARVIS-1: Open-World Multi-task Agents with Memory-Augmented Multimodal Language Modelscited by 171
  21. 2023SmartPlay: A Benchmark for LLMs as Intelligent Agentscited by 125
  22. 2022Prompting Is Programming: A Query Language for Large Language Modelscited by 110
  23. 2023CLIN: A Continually Learning Language Agent for Rapid Task Adaptation and Generalizationcited by 95
  24. 2023Read and Reap the Rewards: Learning to Play Atari with the Help of Instruction Manualscited by 45
  25. 2023Plan, Eliminate, and Track -- Language Models are Good Teachers for Embodied Agentscited by 32
  26. 2024Skill Set Optimization: Reinforcing Language Model Behavior via Transferable Skillscited by 26

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 5; 2026: 8.

13 papers.

Sort:

By area:

  1. 2025PolySkill: Learning Generalizable Skills Through Polymorphic Abstractioncited by 27
  2. 2025Graphs Meet AI Agents: Taxonomy, Progress, and Future Opportunitiescited by 23
  3. 2025Graph-Augmented Large Language Model Agents: Current Progress and Future Prospectscited by 14
  4. 2025UFO3: Weaving the Digital Agent Galaxycited by 6
  5. 2026SYMPHONY: Synergistic Multi-agent Planning with Heterogeneous Language Model Assemblycited by 5
  6. 2026From Agent Loops to Structured Graphs:A Scheduler-Theoretic Framework for LLM Agent Executioncited by 4
  7. 2026Don't Stop Early: Scalable Enterprise Deep Research with Controlled Information Flow and Evidence-Aware Terminationcited by 4
  8. 2025Symbolic Intermediaries as a Linguistic-Numerical Interface for LLM-Driven Geometric Reasoningcited by 2
  9. 2026Task-Aware LLM Council with Adaptive Decision Pathways for Decision Supportcited by 1
  10. 2026Diagnosis-Driven Automatic Repair for Agentic Workflow via Symbolic Inferencecited by 0
  11. 2026Towards Self-Evolving Agents: A Human-Inspired Adaptive Exploration-Exploitation Framework for Genetic Network Programmingcited by 0
  12. 2026GLIDE: Generalized Layer-wise Intrinsic Distributional Evaluation for Heterogeneous LLM Agentscited by 0
1 more
  1. 2026Beyond Corrected Actions: Training LLM Agents on Textual Critiquescited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Textualized Agent-Style Reasoning for Complex Tasks by Multiple Round LLM Generation
  2. 2025CodeAgents: A Token-Efficient Framework for Codified Multi-Agent Reasoning in LLMs
  3. 2025Agentic Reasoning: A Streamlined Framework for Enhancing LLM Reasoning with Agentic Tools
  4. 2025LLM-based Agentic Reasoning Frameworks: A Survey from Methods to Scenarios
  5. 2024AgentQuest: A Modular Benchmark Framework to Measure Progress and Improve LLM Agents
  6. 2025Distilling LLM Agent into Small Models with Retrieval and Code Tools
  7. 2023AgentTuning: Enabling Generalized Agent Abilities for LLMs
  8. 2025Layered Chain-of-Thought Prompting for Multi-Agent LLM Systems: A Comprehensive Approach to Explainable Large Language Models