Towards Neuro-Symbolic Procedural Reasoning for Long-Horizon Vision-Language-Action Manipulation

Towards Neuro-Symbolic Procedural Reasoning for Long-Horizon Vision-Language-Action Manipulation

|Authors: Vivek Chavan, Yahuan Shi, Oliver Heimann, Kevin Haninger, Jörg Krüger

|Venue: arXiv preprint | Year: 2026

|arXiv: 2609.05369v1

Abstract

Vision-language-action (VLA) models can execute short manipulation skills, but remain brittle in long-horizon procedures requiring persistent task state, dependency-aware reasoning, conditional decisions, and reliable grounding. We investigate a neuro-symbolic framework that combines learned VLA control with explicit task graphs and multimodal procedural memory. Task graphs encode action dependencies, valid transitions, and branch conditions, while memory maintains the active step, completed actions, textual context, and task-relevant visual evidence. Together, these structures guide object selection, destination grounding, subgoal dispatch, and verification of expected state transitions. Human demonstrations provide additional spatial and temporal guidance through gaze or saliency cues. To isolate their effect on policy learning, our initial study bypasses cross-view gaze transfer and directly annotates pseudo-gaze in robot-view teleoperation videos. The resulting guidance is used during VLA fine-tuning and inference. We study two long-horizon manipulation domains, workspace clearing and surgical-instrument handling, which require ordered execution, visually grounded decisions, and conditional branching. We evaluate correct-object and destination selection, subtask completion, task progress, step-order consistency, complete-task success, and procedural or execution mistakes. This work positions structured symbolic reasoning and demonstration-derived visual guidance as complementary mechanisms for reliable long-horizon VLA manipulation.

Key Contributions

• Vision-language-action (VLA) models can execute short manipulation skills, but remain brittle in …
• We investigate a neuro-symbolic framework that combines learned VLA control with explicit task gr…
• Task graphs encode action dependencies, valid transitions, and branch conditions, while memory ma…
• Together, these structures guide object selection, destination grounding, subgoal dispatch, and v…
• Human demonstrations provide additional spatial and temporal guidance through gaze or saliency cues

Topics

• manipulation
• vision
• vla
• reinforcement-learning
• control
• learning-from-demonstration

Code & Data

No code repository linked in paper metadata.

BibTeX

@article{Chavan2026_260905369v1,
  title     = {Towards Neuro-Symbolic Procedural Reasoning for Long-Horizon Vision-Language-Action Manipulation},
  author    = {Vivek Chavan and Yahuan Shi and Oliver Heimann and Kevin Haninger and Jörg Krüger},
  year      = {2026},
  eprint    = {2609.05369v1},
  archivePrefix = {arXiv},
  primaryClass  = {cs.RO},
  url       = {https://arxiv.org/abs/2609.05369v1}
}