Skip to content
Preprint

ADM-Planner: LLM-Guided Long-Horizon Planning for Mobile Manipulators with Attention-Enhanced Dynamic Memory

Sep 2026 · 0 citations · 19 references
Computer Science

TL;DR

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.

Abstract

Large language models can decompose mobile-manipulation goals into long action sequences, but the resulting plans remain reliable only while their world context is current. A fixed scene description becomes stale when objects are discovered, moved, or completed while retaining every observation instead produces a growing history with redundant and conflicting state. To resolve this tension, we present an LLM-guided planning framework ADM-Planner with attention-enhanced dynamic memory (ADM). Persistent workspace knowledge is separated from object-centric state, asynchronous observations and action outcomes update that state, and a bounded retriever exposes only the entries that can affect the next decision. The LLM replans when an update invalidates the remaining plan. Across 1,500 task-simulator episodes, the proposed ADM achieved 100% full-task success in the 14-container noisy dynamic setting, compared with 62% for static memory and 97% for unfiltered dynamic memory, while reducing the context-size proxy by 95.8% relative to the latter. In a six-episode live GPT-5 Mini planner, both dynamic memory variants completed every mission, while ADM reduced provider-reported input tokens by 14.4% and mean planner calls from 7.0 to 6.0. A separate 60-trial PyBullet study retained 100% success for ADM, compared with 50% for static memory. Finally, the mobile manipulator with ADM-Planner completed various missions in indoor and outdoor physical experiments while incorporating targets revealed after execution began. The results show that selective state maintenance with ADM, rather than prompt history alone, is a practical basis for long-horizon planning in changing environments. Project page: https://xjp99v5.github.io/ADM-Planner

View source

Similar papers

Preprint Sep 2026

Safe Task Planning with Long-Term Graph Memory for Embodied Agents

A novel safe task-planning framework, SafeMem, which constructs and maintains a long-term semantic graph memory of the open and dynamic environment, and substantially improves safe success rates compared to state-of-the-art VLM-driven task planners.

Si-Yuan Li, Tai-Yan Lang, Ao Yan et al. · 1 citation
Preprint Sep 2026

X-Planner: Event-Structured Task Planning for Embodied Intelligence

This work presents X-Planner, a planning front-end that addresses both the supervision and representation of embodied reasoning, and describes planning-text quality and downstream execution.

Howard Lu, Shalfun Li, P. Pan et al. · 0 citations

FRAMES: Failure Recovery And Monitoring of Embodied Skills for Humanoid Loco-Manipulation

Large language model (LLM) planners can decompose natural-language instructions and select reusable robot skills, but choosing the correct skill does not guarantee successful physical execution. This gap is especially important in humanoid loco-manipulation, where errors during approach, grasping, transport, or placeme...

Ajay Vikram Periasami, Xin Luo, Hao-Yu Li et al. · 1 citation
Sep 2026

NavProbe: Evidence-Grounded Reasoning with Active Memory Retrieval for Zero-Shot Navigation

Long-horizon navigation requires an agent to revise its intermediate objectives as evidence accumulates. Full visual histories are costly to process, while compact summaries may omit details needed to reconsider earlier decisions. We introduce NavProbe, a hierarchical zero-shot navigation agent that couples a dynamic s...

Jing-Yang Liu, Su-Jia Yao, Jia-Yuan Gu et al. · 0 citations
#artificial intelligence Preprint Sep 2026

2AM: Grounding Agent-Side Memory as Guidance for Steerable Action Models in Long-Horizon Manipulation

2AM shows that task memory can remain Agent-side and shows that Action Model capability depends not only on what the policy has learned, but on how precisely the Agent can steer it, and isolates this question through a deliberately constrained design.

Yu-Tong Hu, Feng Chen, Xue-Zhi Cao et al. · 2 citations · ⚡2

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.