CyberIntel ⬡ News
★ Saved ◆ Cyber Reads
← Back ◬ AI & Machine Learning Jun 12, 2026

WISE: A Long-Horizon Agent in Minecraft with Why-Which Reasoning

arXiv AI Archived Jun 12, 2026 ✓ Full text saved

arXiv:2606.12852v1 Announce Type: new Abstract: Rapid advances have been made in developing general-purpose embodied agent in environments like Minecraft through the adoption of LLM-augmented hierarchical approaches. Despite their promise, low-level controllers often become performance bottlenecks due to repeated execution failures. We argue that a key limitation is not only the lack of episodic memory, but also the decoupling of \textit{what-where-when} memory from \textit{which-why} reasoning.

Full text archived locally
✦ AI Summary · Claude Sonnet


    Computer Science > Artificial Intelligence [Submitted on 11 Jun 2026] WISE: A Long-Horizon Agent in Minecraft with Why-Which Reasoning Renmin Cheng, Changhao Chen (The Hong Kong University of Science and Technology (Guangzhou)) Rapid advances have been made in developing general-purpose embodied agent in environments like Minecraft through the adoption of LLM-augmented hierarchical approaches. Despite their promise, low-level controllers often become performance bottlenecks due to repeated execution failures. We argue that a key limitation is not only the lack of episodic memory, but also the decoupling of \textit{what-where-when} memory from \textit{which-why} reasoning. To address this, we propose \textbf{WISE} (Which-Why Informed Semantic Explorer), a long-horizon agent framework with an enhanced low-level controller equipped with a Causal Event Graph that augments episodic memory with explicit causal structure linking observations to task relevance. Unlike prior work such as MrSteve, which relies on feature similarity for retrieval, WISE enables robust recall under viewpoint changes and supports opportunistic task reordering through causal reasoning. Building on this memory, we propose an Opportunistic Task Scheduler that dynamically re-prioritizes subtasks when causally relevant opportunities are detected. We further equip WISE with a multi-scale progressive exploration strategy to provide spatially comprehensive observations for downstream reasoning. Experiments show that WISE largely improves task success and efficiency on long-horizon sparse tasks, particularly in settings requiring adaptive decision-making. Subjects: Artificial Intelligence (cs.AI) Cite as: arXiv:2606.12852 [cs.AI]   (or arXiv:2606.12852v1 [cs.AI] for this version)   https://doi.org/10.48550/arXiv.2606.12852 Focus to learn more Submission history From: Renmin Cheng [view email] [v1] Thu, 11 Jun 2026 03:35:02 UTC (12,260 KB) Access Paper: HTML (experimental) view license Current browse context: cs.AI < prev   |   next > new | recent | 2026-06 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)
    💬 Team Notes
    Article Info
    Source
    arXiv AI
    Category
    ◬ AI & Machine Learning
    Published
    Jun 12, 2026
    Archived
    Jun 12, 2026
    Full Text
    ✓ Saved locally
    Open Original ↗