AtomTree：基于 LLM 的状态感知具身指令遵循分层框架
AtomTree: A Hierarchical Framework for State-Aware Embodied Instruction Following with LLMs
AI 导读
研究 AtomTree 提出一种基于 LLM 的状态感知任务规划分层框架，增量构建子目标与动作树，由 LLM 在每步根据当前符号状态决定继续分解或输出可执行低层动作。框架配备轻量记忆模块总结过往结果，动作受阻时触发分层回溯重规划，从最新状态重新生成子树计划。在 ALFRED benchmark 零样本评测中，AtomTree 超越了此前的 LLM 规划器。
正文 · 原文
Abstract:Embodied instruction following in interactive environments requires agents to interpret natural language commands and complete long-horizon tasks. Existing planners either rely on large labeled trajectories, or use few-shot and zero-shot LLM prompting that produces a whole plan in a single serial reasoning process. These approaches depend on linguistic common sense, commit to a plan from the initial instruction, and only update after failures, which weakens robustness and state awareness. We present AtomTree, a hierarchical framework for state-aware task planning with LLMs. AtomTree incrementally builds a tree of subgoals and actions, where the LLM decides at each step, from the current symbolic state, whether to further decompose or to output a grounded low-level action. A lightweight memory module summarizes past outcomes for reuse in later decisions. When a low-level action stalls, AtomTree triggers hierarchical backtracking replanning to return to the parent node and regenerate the subtree plan from the latest state, preventing continued drift along an incorrect trajectory. In zero-shot evaluation on the ALFRED benchmark, AtomTree outperforms prior LLM-based planners. Project page: this https URL.
| Comments: | Accepted at IROS 2026 |
| Subjects: | Robotics (cs.RO); Artificial Intelligence (cs.AI); Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.38744 [cs.RO] |
| (or arXiv:2610.38744v1 [cs.RO] for this version) | |
| https://doi.org/10.48550/arXiv.2610.38744 arXiv-issued DOI via DataCite |
Submission history
From: Tommy Sha [view email]
[v1]
Wed, 28 Oct 2026 19:30:40 UTC (2,832 KB)
来源：arXiv cs.AI · arxiv.org