SGG-ReflAct (Sub-Goal Guided Re flAct), a reasoning backbone that integrates sub-goals generated through a single path LLM planner into the reflection process, and BeamSGG-ReflAct, which replaces the single-path planner with a beam search based LLM planner for structured plan exploration.
Abstract
Recent advances in reasoning backbones have empowered large language model (LLM)agentstotackle complex, multi-step tasks. However, as reasoning horizons grow, inconsistent internal beliefs induce intermediate errors that cause agents to drift from their goals. This limitation also persists in REFLACT, which reflects only on the end-goal at each step without explicitly considering intermediate sub goals. To address this problem, we propose SGG-ReflAct (Sub-Goal Guided Re flAct), a reasoning backbone that integrates sub-goals generated through a single path LLM planner into the reflection process. We further extend this framework to BeamSGG-ReflAct, which replaces the single-path planner with a beam search based LLM planner for structured plan exploration. We run experiments on ALF World, ScienceWorld, and Jericho with multiple LLM models. SGG-ReflAct out performs REFLACT in nearly all settings, achieving best success rate gains of 14.9 percentage points on ALFWorld and 8.0 percentage points on ScienceWorld with Llama-3.1-8B-Instruct. Our experimental analysis shows that SGG-ReflAct re duces hallucinated actions and achieves its largest gains on procedurally ordered tasks. Furthermore, experimental results with BeamSGG-ReflAct show that the backbone's effectiveness depends on plan quality: explicitly specifying the re quired operations recovers gains that plan searching alone cannot achieve. These results demonstrate that SGG-ReflAct offers a practical and highly effective rea soning backbone, enabling LLM agents to achieve reliable performance in com plex, long-horizon tasks through easy integration.
Enabling robotic agents to perform complex long-horizon tasks has been a long-standing goal in robotics and artificial intelligence (AI). Existing Large Language Models (LLMs)-based symbolic planners auto-generate Planning Domain Definition Language (PDDL) specifications to bridge language and formal reasoning, but the...
Chang-Zhi Wang, Ting-Hao Yi, Zhen-Zhen Huang et al.· IEEE Robotics and Automation...· 0 citations
Improvements show that an explicit graph world model harness can substantially improve the reliability and efficiency of long-horizon embodied planning across compact and frontier hosted LLM capabilities.
Rui-Yang Wang, Hao-Lun Hsu, S. Mehta et al.· arXiv.org· 0 citations
Long-horizon agentic tasks demand strong reasoning and efficient execution across successive interactions with dynamic environments. A common approach decouples high-level planning from low-level execution through separate planner and actor roles. To investigate coordination failures in these tasks, we prompt both agen...
Heng-Zhuang Li, Yi-Kai Zhang, Yu Wang et al.· 0 citations
An LLM-guided planning framework ADM-Planner with attention-enhanced dynamic memory shows that selective state maintenance with ADM, rather than prompt history alone, is a practical basis for long-horizon planning in changing environments.
Jia-Ping Xiao, Ping-Yuan Ji, Mir Feroskhan· 0 citations
NavMCP is introduced, an agentic scaffolding framework that couples a VLM reasoning agent with an NFM executor for long-horizon exploration that achieves state-of-the-art results on HM-EQA, MT-HM3D, and EXPRESS-Bench.
Zi-Xing Lei, Geng-Ze Zhou, Xiong-Hui Chen et al.· 0 citations
Hierarchical planning frameworks combine skills from multiple robot control policies for long-horizon task execution, where determining when to terminate the current skill and advance to the next subtask is essential. Existing approaches often rely on pre-designed completion signal checkers that are hard to obtain in r...
Jinbang Huang, Yuan Hu, Zhi-Yuan Li et al.· arXiv.org· 1 citation