Lune

ACL Findings2025

BAR: A Backward Reasoning based Agent for Complex Minecraft Tasks

Weihong Du, Wenrui Liao, Binyu Yan, Hongru Liang, Anthony G. Cohn, Wenqiang Lei

Abstract

Large language model (LLM) based agents have shown great potential in following human instructions and automatically completing various tasks; to do this, the agent needs to decompose it into easily executed steps by planning. Existing LLM-based approaches to planning mostly proceed by inferring what steps should be inserted into the plan next by starting from the agent's initial state. However, this forward reasoning paradigm does not work well for complex tasks. We study this issue in Minecraft, a virtual environment that simulates complex tasks based on real-world scenarios. The failure of forward reasoning is often caused by the large perception gap between the agent's initial state and task goal. To alleviate this, we leverage backward reasoning and make the planning start from the terminal (or goal) state, by first considering which actions could directly achieve the task goal in one step, before proceeding to consider how the preconditions of those actions can in turn be achieved. Our BAckward Reasoning based agent (BAR) is equipped with a recursive goal decomposition module, a state consistency maintaining module and a stage memory module. Experimental results demonstrate the superiority of BAR over existing methods and the effectiveness of proposed modules. The code and dataset are available in https://github.com/SCUNLP/BAR.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Tree of Thoughts: Deliberate Problem Solving with Large Language Models cites Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents
  • Tree of Thoughts: Deliberate Problem Solving with Large Language Models cites Self-Refine: Iterative Refinement with Self-Feedback
  • Tree of Thoughts: Deliberate Problem Solving with Large Language Models cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
  • Tree of Thoughts: Deliberate Problem Solving with Large Language Models cites Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models
  • Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models cites Tree of Thoughts: Deliberate Problem Solving with Large Language Models
  • Self-Refine: Iterative Refinement with Self-Feedback cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
  • Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models cites Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents
  • Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
Builds onCited byLeft to right by year; the more cited, the higher.

Builds on14

  1. Chain-of-Thought Prompting Elicits Reasoning in Large Language ModelsJason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma et al.NeurIPS 2022 · 22,562 citations
  2. Tree of Thoughts: Deliberate Problem Solving with Large Language ModelsShunyu Yao, Dian Yu, Jeffrey Zhao, Izhak Shafran et al.NeurIPS 2023 · 5,068 citations
  3. Self-Refine: Iterative Refinement with Self-FeedbackAman Madaan, Niket Tandon, Prakhar Gupta, Skyler Hallinan et al.NeurIPS 2023 · 4,972 citations
  4. Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied AgentsWenlong Huang, Pieter Abbeel, Deepak Pathak, Igor MordatchICML 2022 · 1,539 citations
  5. Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language ModelsLei Wang, Wanyu Xu, Yihuai Lan, Zhiqiang Hu et al.ACL 2023 · 249 citations

Related papers

  1. Describe, Explain, Plan and Select: Interactive Planning with LLMs Enables Open-World Multi-Task AgentsZihao Wang, Shaofei Cai, Guanzhou Chen, Anji Liu et al.NeurIPS 2023 · 178 citations
  2. Experience-based Knowledge Correction for Robust Planning in MinecraftSeungjoon Lee, Suhwan Kim, Minhyeon Oh, Youngsik Yoon et al.ICLR 2026 · 1 citation
  3. Do Embodied Agents Dream of Pixelated Sheep: Embodied Decision Making using Language Guided World ModellingKolby Nottingham, Prithviraj Ammanabrolu, Alane Suhr, Yejin Choi et al.ICML 2023 · 110 citations
  4. Metagent-P: A Neuro-Symbolic Planning Agent with Metacognition for Open WorldsYanfang Zhou, Yuntao Liu, Xiaodong Li, Yongqiang Zhao et al.ACL Findings 2025 · 3 citations
  5. Reasoning with Language Model is Planning with World ModelShibo Hao, Yi Gu, Haodi Ma, Joshua Jiahua Hong et al.EMNLP 2023 · 109 citations
Dusk over the sea between two cliffs drawn in fine vertical lines