AtomTree
A hierarchical, state-aware framework for LLM-based embodied planning that achieves robust planning through the incremental construction of a tree of subgoals and actions.
Timeline (last 90 days)
AtomTree is a hierarchical framework for LLM-driven embodied planning that incrementally builds a tree of subgoals and actions and makes decisions based on the current symbolic state.
AtomTree introduces a lightweight memory module that summarizes the execution results of past subgoals and reuses them in subsequent decisions, without storing raw trajectories.
When low-level action execution stalls, AtomTree triggers hierarchical backtracking replanning: it returns to the parent node and regenerates the subtree plan based on the latest state.
In zero-shot evaluation on the ALFRED benchmark, AtomTree outperforms prior LLM-based planners.
AtomTree's incremental decision-making strikes a compromise between open-loop and closed-loop planning: it retains the LLM's reasoning ability while introducing closed-loop feedback through state awareness and backtracking replanning, balancing robustness and efficiency.
All Facts (5)
AtomTree is a hierarchical framework for LLM-driven embodied planning that incrementally builds a tree of subgoals and actions and makes decisions based on the current symbolic state.
50%UnverifiedAtomTree introduces a lightweight memory module that summarizes the execution results of past subgoals and reuses them in subsequent decisions, without storing raw trajectories.
50%UnverifiedWhen low-level action execution stalls, AtomTree triggers hierarchical backtracking replanning: it returns to the parent node and regenerates the subtree plan based on the latest state.
50%UnverifiedIn zero-shot evaluation on the ALFRED benchmark, AtomTree outperforms prior LLM-based planners.
50%UnverifiedAtomTree's incremental decision-making strikes a compromise between open-loop and closed-loop planning: it retains the LLM's reasoning ability while introducing closed-loop feedback through state awareness and backtracking replanning, balancing robustness and efficiency.
50%