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

arXiv: https://arxiv.org/abs/2405.05955 · HTML: https://mlsanity.com/paper/2405.05955/

## 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 22 of its 34 references that are in the map.
- First posted on arXiv 9 May 2024.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)
- 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, 22 of 22)

- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://mlsanity.com/paper/2308.08155/) (2023)
- [ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs](https://mlsanity.com/paper/2307.16789/) (2023)
- [Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context](https://mlsanity.com/paper/1901.02860/) (2019)
- [MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework](https://mlsanity.com/paper/2308.00352/) (2023)
- [Least-to-Most Prompting Enables Complex Reasoning in Large Language Models](https://mlsanity.com/paper/2205.10625/) (2022)
- [When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories](https://mlsanity.com/paper/2212.10511/) (2022)
- [Large Language Models Can Be Easily Distracted by Irrelevant Context](https://mlsanity.com/paper/2302.00093/) (2023)
- [In-Context Retrieval-Augmented Language Models](https://mlsanity.com/paper/2302.00083/) (2023)
- [Learning to Compress Prompts with Gist Tokens](https://mlsanity.com/paper/2304.08467/) (2023)
- [ReWOO: Decoupling Reasoning from Observations for Efficient Augmented Language Models](https://mlsanity.com/paper/2305.18323/) (2023)
- [How Context Affects Language Models' Factual Predictions](https://mlsanity.com/paper/2005.04611/) (2020)
- [EASYTOOL: Enhancing LLM-based Agents with Concise Tool Instruction](https://mlsanity.com/paper/2401.06201/) (2024)
- [RestGPT: Connecting Large Language Models with Real-World RESTful APIs](https://mlsanity.com/paper/2306.06624/) (2023)
- [AutoAct: Automatic Agent Learning from Scratch for QA via Self-Planning](https://mlsanity.com/paper/2401.05268/) (2024)
- [Agent Lumos: Unified and Modular Training for Open-Source Language Agents](https://mlsanity.com/paper/2311.05657/) (2023)

## Built on by (most cited first, 13 of 13)

- [ToolGen: Unified Tool Retrieval and Calling via Generation](https://mlsanity.com/paper/2410.03439/) (2024)
- [The Evolution of Tool Use in LLM Agents: From Single-Tool Call to Multi-Tool Orchestration](https://mlsanity.com/paper/2603.22862/) (2026)
- [Stop Wasting Your Tokens: Towards Efficient Runtime Multi-Agent Systems](https://mlsanity.com/paper/2510.26585/) (2025)
- [Large Language Model Based Multi-Agent System Augmented Complex Event Processing Pipeline for Internet of Multimedia Things](https://mlsanity.com/paper/2501.00906/) (2025)
- [MIRROR: Multi-agent Intra- and Inter-Reflection for Optimized Reasoning in Tool Learning](https://mlsanity.com/paper/2505.20670/) (2025)
- [A Survey on AgentOps: Categorization, Challenges, and Future Directions](https://mlsanity.com/paper/2508.02121/) (2025)
- [Reasoning, Memorization, and Fine-Tuning Language Models for Non-Cooperative Games](https://mlsanity.com/paper/2410.14890/) (2024)
- [IoT-Brain: Grounding LLMs for Semantic-Spatial Sensor Scheduling](https://mlsanity.com/paper/2604.08033/) (2026)
- [ProST: Progressive Sub-task Training for Pareto-Optimal Multi-agent Systems Using Small Language Models](https://mlsanity.com/paper/2509.04508/) (2025)
- [TUMS: Enhancing Tool-use Abilities of LLMs with Multi-structure Handlers](https://mlsanity.com/paper/2505.08402/) (2025)
- [Enhancing Multi-Agent Communication through Attention Steering with Context Relevance](https://mlsanity.com/paper/2605.30136/) (2026)
- [Agent System Operations: Categorization, Challenges, and Future Directions](https://mlsanity.com/paper/2606.01581/) (2026)
- [DeReAct: Decomposed Reasoning and Acting for Reliable AI Agents](https://mlsanity.com/paper/2610.02351/) (2026)

## 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.