Skip to content
Preprint

EventSync: Event-Driven Memory Updates for History-Dependent Manipulation

Oct 2026 · 0 citations · 40 references
Computer Science

Abstract

History-dependent robotic manipulation requires task context and interaction history, as the current observation alone is insufficient to determine the next action. Hierarchical frameworks use task memory for high-level subgoal reasoning and low-level policies for execution. However, memory updates require accurate completion assessment: similar observations may correspond to different execution phases, and prematurely recording completion can mislead subsequent subgoal reasoning. We present EventSync, a hierarchical framework that coordinates task reasoning and action execution through event-driven memory updates. A vision-language model generates subgoals from task plans and interaction history, while a vision-language-action model executes them. A lightweight Event Monitor combines visual observations with end-effector trajectories to determine whether the current subgoal is complete. The framework records the current subgoal in its completed-subgoal history and triggers subsequent reasoning only after obtaining completion evidence. With visual history in the executor, EventSync achieves 64.5% overall success on RoboMME, exceeding the best baseline reported in the benchmark by 20.0 percentage points. Further analysis shows that this update mechanism helps build a reliable completed-subgoal history. Experiments on four real-robot tasks with different memory requirements validate the framework's effectiveness in real-world robotic manipulation.

View source

Similar papers

Preprint Oct 2026

Proactive Robot Assistance via Event-Driven Reasoning over State Changes

An event-driven framework that monitors workspace state changes with an event monitor and, upon event completion, extracts stabilized pre/post snapshots that characterize the resulting state transition achieves performance comparable to variants given user instructions.

Feng-Kai Liu, Hao Su, Hao-Zhuang Chi et al. · 1 citation
Sep 2026

NavHarness: Adaptive Goals for Agentic Vision-Language Navigation

Vision-Language Navigation (VLN) requires embodied agents to generate actions based on instructions and observations. General-purpose multimodal agents offer a promising basis for this task, but selecting plausible local actions does not ensure that execution remains consistent with the intended route, particularly in...

Hao-Xiang Shi, Zai-Jing Li, Mu-He Ding et al. · 0 citations
Preprint Nov 2026

Remember What Changes the Odds: Critic-Gated Event Memory for Long-Horizon Manipulation

In long-horizon manipulation, a robot may need to take different actions under identical observations, depending on task progress and the outcomes of earlier attempts. We refer to this ambiguity as decision aliasing. Resolving it requires the policy to maintain memory of its execution history. To reduce the cost of pro...

Xuan-Zhuo Liu, Chuan-Kang Li, Mao-Qing Yao et al. · 0 citations
Preprint Oct 2026

EvoMem-VLA: State-Evolution Memory for Long-Horizon Robot Manipulation

Most vision-language-action (VLA) models rely on current observations and lose task-relevant evidence once it leaves view, limiting performance on long-horizon, memory-dependent tasks. Existing efforts incorporate compressed historical features or sparse visual keyframes. However, isolated snapshots can leave the polic...

Yu-Heng Na, Zhi-De Zhong, Jun-Jie He et al. · 1 citation
Preprint Oct 2026

From VLM Planners to Robotic Agents: Self-Evolving Harnesses for History-Dependent Manipulation

Vision-language-action (VLA) models achieve strong performance across embodied manipulation tasks by unifying visual understanding, language conditioning, and action generation. However, long-horizon tasks can involve non-Markovian dependencies: successful decisions may require retaining task progress and past interact...

Ting-Wen Du, Hao-Yu Guo, Han-Xue Zhang et al. · 1 citation
Review Nov 2026

AgenticJevNav: Agentic Object Search and Navigation via Event-Driven Verification

Agentic navigation must maintain goals and adapt actions from incomplete evidence despite execution failures and delayed inference. We present AgenticJevNav, which links goal-directed planning, evidence memory, event-triggered verification, and bounded execution. The Agent plans from RGB, odometry, memory, and feedback...

Shu-Ning Zhang, Shu-Li Zhang, Yun-Heng Wang et al. · 0 citations

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