ReAcTree: Hierarchical LLM Agent Trees with Control Flow for Long-Horizon Task Planning
This addresses the challenge of planning for autonomous agents in complex environments, representing a strong specific gain rather than a foundational advancement.
The paper tackles the problem of complex, long-horizon task planning for embodied autonomous agents by proposing ReAcTree, a hierarchical method that decomposes goals into subgoals using dynamically constructed agent trees with control flow and memory systems, resulting in a 61% goal success rate on WAH-NL, nearly doubling the baseline's performance.
Recent advancements in large language models (LLMs) have enabled significant progress in decision-making and task planning for embodied autonomous agents. However, most existing methods still struggle with complex, long-horizon tasks because they rely on a monolithic trajectory that entangles all past decisions and observations, attempting to solve the entire task in a single unified process. To address this limitation, we propose ReAcTree, a hierarchical task-planning method that decomposes a complex goal into more manageable subgoals within a dynamically constructed agent tree. Each subgoal is handled by an LLM agent node capable of reasoning, acting, and further expanding the tree, while control flow nodes coordinate the execution strategies of agent nodes. In addition, we integrate two complementary memory systems: each agent node retrieves goal-specific, subgoal-level examples from episodic memory and shares environment-specific observations through working memory. Experiments on the WAH-NL and ALFRED datasets demonstrate that ReAcTree consistently outperforms strong task-planning baselines such as ReAct across diverse LLMs. Notably, on WAH-NL, ReAcTree achieves a 61% goal success rate with Qwen 2.5 72B, nearly doubling ReAct's 31%.