mlsanityData to 7 Oct 2026

Smurfs: Multi-Agent System using Context-Efficient DFSDT for Tool Planning

arXiv 2405.05955 ↗First posted 9 May 2024cs.CLcited by 12

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

also in 1 more
Abstract (arXiv)

Teaching large language models (LLMs) to use tools for solving complex problems can grant them human-like reasoning abilities. ReAct and its variants are popular frameworks for tool use in both single-agent and multi-agent systems. To address issues like error propagation and limited exploration in ReAct, the Deep First Search Decision Tree (DFSDT) was proposed, but it faces challenges such as rollback instability, redundant context, and premature termination in single-agent settings. We introduce "Smurfs," a novel multi-agent system (MAS) that enhances DFSDT with a modular, context-efficient, and training-free design. Smurfs surpasses baseline methods in both the open-ended StableToolBench and the closed-ended HotpotQA tasks, reducing token usage by 60.9% compared to DFSDT and enabling Mistral-7b to perform on par with GPT-4-DFSDT. Extensive ablation studies confirm the effectiveness of Smurfs' core components, offering valuable insights for the construction and interpretation of MAS, and paving the way for future exploration.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning. Builds on 22 of its 34 references that are in the map. First posted on arXiv 9 May 2024.

Builds on

22 of 34 references.

References · 22

  1. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  2. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  3. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,064
  4. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,686
  5. 2022FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awarenesscited by 3,611
  6. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,500
  7. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,383
  8. 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversationcited by 1,906
  9. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIscited by 1,880
  10. 2019Transformer-XL: Attentive Language Models Beyond a Fixed-Length Contextcited by 1,830
  11. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Frameworkcited by 1,761
  12. 2022Least-to-Most Prompting Enables Complex Reasoning in Large Language Modelscited by 1,397
10 more
  1. 2022When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memoriescited by 1,103
  2. 2023Large Language Models Can Be Easily Distracted by Irrelevant Contextcited by 820
  3. 2023In-Context Retrieval-Augmented Language Modelscited by 694
  4. 2023Learning to Compress Prompts with Gist Tokenscited by 379
  5. 2020How Context Affects Language Models' Factual Predictionscited by 181
  6. 2023ReWOO: Decoupling Reasoning from Observations for Efficient Augmented Language Modelscited by 174
  7. 2024EASYTOOL: Enhancing LLM-based Agents with Concise Tool Instructioncited by 153
  8. 2023RestGPT: Connecting Large Language Models with Real-World RESTful APIscited by 129
  9. 2024AutoAct: Automatic Agent Learning from Scratch for QA via Self-Planningcited by 81
  10. 2023Agent Lumos: Unified and Modular Training for Open-Source Language Agentscited by 72

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 6; 2026: 4.

12 papers.

  1. 2024ToolGen: Unified Tool Retrieval and Calling via Generationcited by 72
  2. 2025Stop Wasting Your Tokens: Towards Efficient Runtime Multi-Agent Systemscited by 11
  3. 2026The Evolution of Tool Use in LLM Agents: From Single-Tool Call to Multi-Tool Orchestrationcited by 11
  4. 2025Large Language Model Based Multi-Agent System Augmented Complex Event Processing Pipeline for Internet of Multimedia Thingscited by 8
  5. 2025MIRROR: Multi-agent Intra- and Inter-Reflection for Optimized Reasoning in Tool Learningcited by 7
  6. 2025A Survey on AgentOps: Categorization, Challenges, and Future Directionscited by 3
  7. 2024Reasoning, Memorization, and Fine-Tuning Language Models for Non-Cooperative Gamescited by 2
  8. 2026IoT-Brain: Grounding LLMs for Semantic-Spatial Sensor Schedulingcited by 2
  9. 2025ProST: Progressive Sub-task Training for Pareto-Optimal Multi-agent Systems Using Small Language Modelscited by 1
  10. 2025TUMS: Enhancing Tool-use Abilities of LLMs with Multi-structure Handlerscited by 0
  11. 2026Enhancing Multi-Agent Communication through Attention Steering with Context Relevancecited by 0
  12. 2026Agent System Operations: Categorization, Challenges, and Future Directionscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026ToolTree: Efficient LLM Agent Tool Planning via Dual-Feedback Monte Carlo Tree Search and Bidirectional Pruning
  2. 2024StateAct: Enhancing LLM Base Agents via Self-prompting and State-tracking
  3. 2025Multi-Mission Tool Bench: Assessing the Robustness of LLM based Agents through Related and Dynamic Missions
  4. 2024On the Brittle Foundations of ReAct Prompting for Agentic Large Language Models
  5. 2025ReAcTree: Hierarchical LLM Agent Trees with Control Flow for Long-Horizon Task Planning
  6. 2025Beyond ReAct: A Planner-Centric Framework for Complex Tool-Augmented LLM Reasoning
  7. 2026Scale-Plan: Scalable Language-Enabled Task Planning for Heterogeneous Multi-Robot Teams
  8. 2026AI Planning Framework for LLM-Based Web Agents