BAR: A Backward Reasoning based Agent for Complex Minecraft Tasks
Weihong Du, Wenrui Liao, Binyu Yan, Hongru Liang, Anthony G. Cohn, Wenqiang Lei

TL;DR
This paper introduces BAR, a backward reasoning agent for complex Minecraft tasks, which improves planning by starting from the goal state, addressing limitations of forward reasoning in complex scenarios.
Contribution
The paper proposes a novel backward reasoning approach with modules for goal decomposition, state consistency, and stage memory, enhancing planning in complex environments.
Findings
BAR outperforms existing methods in Minecraft tasks.
Backward reasoning reduces perception gap issues.
Modules improve robustness and efficiency.
Abstract
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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
Taxonomy
TopicsAI-based Problem Solving and Planning · Logic, Reasoning, and Knowledge · Multi-Agent Systems and Negotiation
