mlsanityData to 7 Oct 2026

SynWorld: Virtual Scenario Synthesis for Agentic Action Knowledge Refinement

arXiv 2504.03561 ↗First posted 4 Apr 2025cs.CL cs.AI cs.CVcited by 9

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

Abstract (arXiv)

In the interaction between agents and their environments, agents expand their capabilities by planning and executing actions. However, LLM-based agents face substantial challenges when deployed in novel environments or required to navigate unconventional action spaces. To empower agents to autonomously explore environments, optimize workflows, and enhance their understanding of actions, we propose SynWorld, a framework that allows agents to synthesize possible scenarios with multi-step action invocation within the action space and perform Monte Carlo Tree Search (MCTS) exploration to effectively refine their action knowledge in the current environment. Our experiments demonstrate that SynWorld is an effective and general approach to learning action knowledge in new environments. Code is available at https://github.com/zjunlp/SynWorld.

Key facts. Cited by 9 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 34 of its 50 references that are in the map. First posted on arXiv 4 Apr 2025.

Builds on

34 of 50 references.

Closest ancestors · 11

Same direction, newest first

  1. 2025Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems31 Mar
  2. 2024Symbolic Learning Enables Self-Evolving Agents26 Jun
  3. 2024The Landscape of Emerging AI Agent Architectures for Reasoning, Planning, and Tool Calling: A Survey17 Apr
  4. 2024Understanding the planning of LLM agents: A survey5 Feb
  5. 2024Small LLMs Are Weak Tool Learners: A Multi-LLM Agent14 Jan
  6. 2024Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security10 Jan
  7. 2023Igniting Language Intelligence: The Hitchhiker's Guide From Chain-of-Thought Reasoning to Language Agents20 Nov
  8. 2023Agents: An Open-source Framework for Autonomous Language Agents14 Sep
  9. 2023A Survey on Large Language Model based Autonomous Agents22 Aug
  10. 2023AdaPlanner: Adaptive Planning from Feedback with Language Models26 May
  11. 2023Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agents3 Feb

Other references · 23

  1. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  2. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,686
  3. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,317
  4. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIscited by 1,880
  5. 2022WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agentscited by 1,197
  6. 2020ALFWorld: Aligning Text and Embodied Environments for Interactive Learningcited by 1,143
  7. 2022ScienceWorld: Is your Agent Smarter than a 5th Grader?cited by 298
  8. 2024RepairAgent: An Autonomous, LLM-Based Agent for Program Repaircited by 225
  9. 2023LLaVA-Plus: Learning to Use Tools for Creating Multimodal Agentscited by 188
  10. 2024EASYTOOL: Enhancing LLM-based Agents with Concise Tool Instructioncited by 153
  11. 2025A Survey of Efficient Reasoning for Large Reasoning Models: Language, Multimodality, and Beyondcited by 131
  12. 2024AnyTool: Self-Reflective, Hierarchical Agents for Large-Scale API Callscited by 121
11 more
  1. 2024A Survey on Large Language Model-Based Game Agentscited by 106
  2. 2024LongRAG: Enhancing Retrieval-Augmented Generation with Long-context LLMscited by 104
  3. 2025A Survey of WebAgents: Towards Next-Generation AI Agents for Web Automation with Large Foundation Modelscited by 87
  4. 2024Retrieval Augmented Generation (RAG) and Beyond: A Comprehensive Survey on How to Make your LLMs use External Data More Wiselycited by 65
  5. 2024Let Me Do It For You: Towards LLM Empowered Recommendation via Tool Learningcited by 51
  6. 2024From Exploration to Mastery: Enabling LLMs to Master Tools via Self-Driven Interactionscited by 46
  7. 2025Towards Trustworthy GUI Agents: A Surveycited by 33
  8. 2025OmniThink: Expanding Knowledge Boundaries in Machine Writing through Thinkingcited by 18
  9. 2024An LLM-Tool Compiler for Fused Parallel Function Callingcited by 14
  10. 2024Towards Practical Tool Usage for Continually Learning LLMscited by 6
  11. 2024Automating REST API Postman Test Cases Using LLMcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 6; 2026: 3.

9 papers.

  1. 2025WebDancer: Towards Autonomous Information Seeking Agencycited by 180
  2. 2025Memp: Exploring Agent Procedural Memorycited by 88
  3. 2025Towards General Agentic Intelligence via Environment Scalingcited by 51
  4. 2026SkillNet: Create, Evaluate, and Connect AI Skillscited by 48
  5. 2025Large Language Models for Planning: A Comprehensive and Systematic Surveycited by 38
  6. 2025Learning API Functionality from In-Context Demonstrations for Tool-based Agentscited by 1
  7. 2025AutoContext: Instance-Level Context Learning for LLM Agentscited by 1
  8. 2026The Periodic Table of LLM Reasoning: A Structured Survey of Reasoning Paradigms, Methods, and Failure Modescited by 0
  9. 2026Training the Orchestrator: A Supervised Approach to End-to-End PDDL Planning with LLM Agentscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026ProPlay: Procedural World Models for Self-Evolving LLM Agents
  2. 2026From Assumptions to Actions: Turning LLM Reasoning into Uncertainty-Aware Planning for Embodied Agents
  3. 2024Agent Planning with World Knowledge Model
  4. 2026From Traces to Agentic Worlds: Agentic Language World Models for Interactive Environment Simulation
  5. 2026ExpVoyager: Direct Experience Navigation for Dynamic Agent Skill Synthesis
  6. 2026MAP: A Map-then-Act Paradigm for Long-Horizon Interactive Agent Reasoning
  7. 2026Agent-World: Scaling Real-World Environment Synthesis for Evolving General Agent Intelligence
  8. 2026Schema: Discovering Unknown Environments via Agentic Program Induction