mlsanityData to 14 Oct 2026

BAR: A Backward Reasoning based Agent for Complex Minecraft Tasks

arXiv 2505.14079 ↗First posted 20 May 2025cs.CLcited by 0

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

also in 1 more
Abstract (arXiv)

Large language model (LLM) based agents have shown great potential in following human instructions and automatically completing various tasks. To complete a task, the agent needs to decompose it into easily executed steps by planning. Existing studies mainly conduct the planning by inferring what steps should be executed next starting from the agent's initial state. However, this forward reasoning paradigm doesn't work well for complex tasks. We propose to study this issue in Minecraft, a virtual environment that simulates complex tasks based on real-world scenarios. We believe that the failure of forward reasoning is caused by the big perception gap between the agent's initial state and task goal. To this end, we leverage backward reasoning and make the planning starting from the terminal state, which can directly achieve the task goal in one step. Specifically, we design a BAckward Reasoning based agent (BAR). It is equipped with a recursive goal decomposition module, a state consistency maintaining module and a stage memory module to make robust, consistent, and efficient planning starting from the terminal state. Experimental results demonstrate the superiority of BAR over existing methods and the effectiveness of proposed modules.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning. Builds on 16 of its 38 references that are in the map. First posted on arXiv 20 May 2025.

Builds on

16 of 38 references.

References · 16

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2024The Llama 3 Herd of Modelscited by 14,715
  3. 2024Understanding the planning of LLM agents: A surveycited by 421
  4. 2022Selection-Inference: Exploiting Large Language Models for Interpretable Logical Reasoningcited by 334
  5. 2023Ghost in the Minecraft: Generally Capable Agents for Open-World Environments via Large Language Models with Text-based Knowledge and Memorycited by 289
  6. 2023JARVIS-1: Open-World Multi-task Agents with Memory-Augmented Multimodal Language Modelscited by 171
  7. 2024Tree Search for Language Model Agentscited by 151
  8. 2022Faithful Reasoning Using Large Language Modelscited by 130
  9. 2023AgentSims: An Open-Source Sandbox for Large Language Model Evaluationcited by 88
  10. 2024Optimus-1: Hybrid Multimodal Memory Empowered Agents Excel in Long-Horizon Taskscited by 84
  11. 2023See and Think: Embodied Agent in Virtual Environmentcited by 54
  12. 2024MineDreamer: Learning to Follow Instructions via Chain-of-Imagination for Simulated-World Controlcited by 53
4 more
  1. 2023RCOT: Detecting and Rectifying Factual Inconsistency in Reasoning by Reversing Chain-of-Thoughtcited by 47
  2. 2023Skill Reinforcement Learning and Planning for Open-World Long-Horizon Taskscited by 36
  3. 2024RL-GPT: Integrating Reinforcement Learning and Code-as-policycited by 32
  4. 2024Flow of Reasoning: Training LLMs for Divergent Reasoning with Minimal Examplescited by 30

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025OpenHA: A Series of Open-Source Hierarchical Agentic Models in Minecraft
  2. 2025Parallelized Planning-Acting for Efficient LLM-based Multi-Agent Systems in Minecraft
  3. 2026MineNPC-Task: Task Suite for Memory-Aware Minecraft Agents
  4. 2022MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge
  5. 2023Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agents
  6. 2026MineExplorer: Evaluating Open-World Exploration of MLLM Agents in Minecraft
  7. 2026WISE: A Long-Horizon Agent in Minecraft with Why-Which Reasoning
  8. 2025Collaborating Action by Action: A Multi-agent LLM Framework for Embodied Reasoning