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

• URL: http://arxiv.org/abs/2606.12852v1
• Date: Thu, 11 Jun 2026 03:35:02 GMT
• Title: WISE: A Long-Horizon Agent in Minecraft with Why-Which Reasoning
• Abstract summary: We propose WISE, a long-horizon agent framework with an enhanced low-level controller equipped with a Causal Event Graph.<n>WISE augments episodic memory with explicit causal structure linking observations to task relevance.<n>Experiments show that WISE largely improves task success and efficiency on long-horizon sparse tasks.
• Score: 6.545488752368577
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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. 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.

Related papers

• Spatial Reasoning in LLM Game Agents: Impact of Causal Context and Multi-Step Planning [56.67877550139192]
  We conduct experiments across varying model scales, reasoning modes, and planning horizons.<n>We introduce a focused GVGAI benchmark consisting of three custom games with five difficulty levels to isolate spatial navigation.<n>Our results show that while larger models with an enabled thinking mode identify their positions more accurately, overall performance in coordinate matching remains limited for smaller models.
  arXiv  Detail & Related papers  (2026-07-22T12:10:45Z)
• Organize then Retrieve: Hierarchical Memory Navigation for Efficient Agents [29.28371047415946]
  HORMA is a hierarchical organize-and-Retrieve Memory Agent for large language models.<n>It decomposes working memory into two stages: structured memory construction and navigation-based retrieval.<n>It consistently achieves better efficiency-performance trade-offs and generalizes effectively to unseen tasks.
  arXiv  Detail & Related papers  (2026-06-10T05:49:14Z)
• ActiveMem: Distributed Active Memory for Long-Horizon LLM Reasoning [46.225019133047965]
  Memory is essential for enabling large language model (LLM) agents to handle long-horizon reasoning tasks.<n>We propose ActiveMem, a framework that decouples agent memory from the core reasoning process.<n>Experiments on BrowseComp-Plus and GAIA show that ActiveMem achieves state-of-the-art accuracy with significantly reduced overhead.
  arXiv  Detail & Related papers  (2026-06-09T08:03:38Z)
• Memory is Reconstructed, Not Retrieved: Graph Memory for LLM Agents [51.30250860677378]
  We propose MRAgent, a framework that combines an associative memory graph with an active reconstruction mechanism.<n>Running on a Cue-Tag-Content graph, our active reconstruction mechanism integrates reasoning directly into memory access.<n>Experiments on the LoCoMo benchmark and LongMemEval benchmark demonstrate significant improvements over strong baselines.
  arXiv  Detail & Related papers  (2026-06-04T11:29:46Z)
• SAM: State-Adaptive Memory for Long-Horizon Reasoning Agent [51.274445160155864]
  Long-horizon agentic reasoning requires large language models to act over long interaction histories containing thoughts, tool calls, observations, and partial conclusions.<n>Existing approaches address this difficulty by truncating the interaction history, compressing it into shorter surrogates, or retrieving selected parts of it for reuse.<n>We propose State-Adaptive Memory, a standalone framework that consolidates ongoing interaction into compact memory cues while preserving raw trajectory pages for intent-driven recall.
  arXiv  Detail & Related papers  (2026-05-23T08:37:16Z)
• Structurally Aligned Subtask-Level Memory for Software Engineering Agents [15.239652771593663]
  Large Language Models (LLMs) have demonstrated significant potential as autonomous software engineering (SWE) agents.<n>Recent work has explored augmenting these agents with memory mechanisms to support long-horizon reasoning.<n>We propose Structurally Aligned Subtask-Level Memory to align memory storage, retrieval, and updating with the agent's functional decomposition.
  arXiv  Detail & Related papers  (2026-02-25T06:13:25Z)
• INHerit-SG: Incremental Hierarchical Semantic Scene Graphs with RAG-Style Retrieval [32.38739911399099]
  INHerit-SG is a semantic scene graph that supports interpretable human-intent reasoning in complex environments.<n>An event-triggered map update mechanism reorganizes the graph only when meaningful semantic events occur.<n>This explicit interpretability improves the success rate and reliability of complex retrievals, enabling the system to adapt to a broader spectrum of human interaction tasks.
  arXiv  Detail & Related papers  (2026-02-13T14:45:55Z)
• AgentLongBench: A Controllable Long Benchmark For Long-Contexts Agents via Environment Rollouts [78.33143446024485]
  We introduce textbfAgentLongBench, which evaluates agents through simulated environment rollouts based on Lateral Thinking Puzzles.<n>This framework generates rigorous interaction trajectories across knowledge-intensive and knowledge-free scenarios.
  arXiv  Detail & Related papers  (2026-01-28T16:05:44Z)
• AMA: Adaptive Memory via Multi-Agent Collaboration [54.490349689939166]
  We propose Adaptive Memory via Multi-Agent Collaboration (AMA), a novel framework that leverages coordinated agents to manage memory across multiple granularities.<n>AMA significantly outperforms state-of-the-art baselines while reducing token consumption by approximately 80% compared to full-context methods.
  arXiv  Detail & Related papers  (2026-01-28T08:09:49Z)
• Beyond Fact Retrieval: Episodic Memory for RAG with Generative Semantic Workspaces [5.110309385104824]
  Large Language Models (LLMs) face fundamental challenges in long-context reasoning.<n>Current solutions fail to build the space-time-anchored narrative representations required for tracking entities through episodic events.<n>We propose the textbfGenerative Semantic Workspace (GSW), a neuro-inspired generative memory framework.
  arXiv  Detail & Related papers  (2025-11-10T19:59:34Z)
• UltraHorizon: Benchmarking Agent Capabilities in Ultra Long-Horizon Scenarios [63.67884284105684]
  We introduce textbfUltraHorizon, a novel benchmark that measures the foundational capabilities essential for complex real-world challenges.<n>Agents are designed in long-horizon discovery tasks where they must iteratively uncover hidden rules.<n>Our experiments reveal that LLM-agents consistently underperform in these settings, whereas human participants achieve higher scores.
  arXiv  Detail & Related papers  (2025-09-26T02:04:00Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.