Beyond Flat Policies: Hierarchical Post-Training for Embodied Agents in Robotic Manipulation

• URL: http://arxiv.org/abs/2608.05999v1
• Date: Thu, 06 Aug 2026 13:07:56 GMT
• Title: Beyond Flat Policies: Hierarchical Post-Training for Embodied Agents in Robotic Manipulation
• Abstract summary: Vision-language-action (VLA) models have demonstrated remarkable capabilities in robotic manipulation by leveraging pretrained vision-language models.<n>Existing post-training methods predominantly optimize VLA models as flat policies, making it difficult to explicitly model task progression and perform robust long-horizon manipulation.<n>We propose Hierarchical Robotic Control (HiRoC), a hierarchical post-training framework that decouples high-level task planning from low-level action execution.
• Score: 34.87301719899886
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Vision-language-action (VLA) models have demonstrated remarkable capabilities in robotic manipulation by leveraging pretrained vision-language models. However, existing post-training methods predominantly optimize VLA models as flat policies, making it difficult to explicitly model task progression and perform robust long-horizon manipulation. Although hierarchical approaches introduce task decomposition, they mainly rely on supervised learning from offline demonstrations and cannot effectively improve execution through online interaction. To address this limitation, we propose Hierarchical Robotic Control (HiRoC), a hierarchical post-training framework that decouples high-level task planning from low-level action execution. The planner decomposes complex tasks into executable subgoals to provide explicit semantic guidance, while the executor continuously improves subgoal-conditioned action generation through reinforcement learning. To enable effective collaboration between the two modules, we further align the executor with planner-generated subgoals before reinforcement learning, mitigating the distribution misalignment between planning and execution. Extensive experiments across diverse robotic manipulation benchmarks demonstrate that HiRoC consistently outperforms strong baselines. Comprehensive analyses further validate the effectiveness of hierarchical post-training and the contribution of each key component.

Related papers

• EASy: Towards Efficient LLM-Based Agentic System [54.10819421625103]
  We propose EASy, a trainable agentic framework that jointly optimize task performance and computational efficiency through reinforcement learning.<n> EASy equips an LLM-based orchestrator with explicit knowledge of the capability and cost profiles of heterogeneous executors, enabling context-sensitive coordination beyond performance-only routing.<n>It further introduces a milestone-plan-act workflow that decomposes complex tasks into manageable milestones, constructs dependency-aware execution graphs, assigns suitable executors, and parallelizes independent steps while adapting subsequent decisions to intermediate outcomes.
  arXiv  Detail & Related papers  (2026-08-05T08:50:36Z)
• A Closed-Loop Multi-Agent Framework for Robust Multi-Robot Manipulation [37.78546236286294]
  Large Language Models (LLMs) offer the reasoning capabilities to decompose objectives into actionable plans.<n>We propose a hierarchical closed-loop agentic framework to ensure robust multi-robot manipulation.<n>Our system consists of three specialized agents: the Planning Agent decomposes instructions into allocated sub-tasks, the Manipulation Agent for each robot executes actions via adaptive tool use, and the Verification Agent closes the loop by monitoring physical outcomes and feeding back semantic corrections.
  arXiv  Detail & Related papers  (2026-07-08T04:23:41Z)
• Afford-VLA: Action-Aligned Visual Planning via Internalized Affordance [108.46436073194546]
  We argue that effective planning should be local, visually grounded, internally generated, and directly aligned with action.<n>We propose Afford-VLA, a unified framework that internalizes task-conditioned affordance as an explicit visual planning interface within VLA models.
  arXiv  Detail & Related papers  (2026-05-22T20:43:47Z)
• SADP: Subgoal-Aware Diffusion Policy for Explainable Robots Learned from Foundation Model Generated Demonstrations [0.0]
  Subgoal-Aware Diffusion Policy (SADP) structures policy execution around human-interpretable subgoals.<n>A lightweight auxiliary head predicts subgoal completion states, allowing the robot to expose its current execution stage.<n>Experiments in RLBench simulations and real-world evaluations on a UR5e robot demonstrate that SADP achieves higher task success rates.
  arXiv  Detail & Related papers  (2026-05-16T08:18:47Z)
• PRTS: A Primitive Reasoning and Tasking System via Contrastive Representations [66.94988600664574]
  We present textbfPRTS (textbfPrimitive textbfReasoning and textbfTasking textbfSystem), a VLA foundation model that reformulates pretraining through Goal-Conditioned Reinforcement Learning.
  arXiv  Detail & Related papers  (2026-04-30T06:14:02Z)
• Self-Guided Plan Extraction for Instruction-Following Tasks with Goal-Conditional Reinforcement Learning [49.0945829107309]
  SuperIgor enables a language model to generate and refine high-level plans through a self-learning mechanism.<n>Our approach involves iterative co-training: an RL agent is trained to follow the generated plans, while the language model adapts and modifies these plans based on RL feedback and preferences.<n>Results show that SuperIgor agents adhere to instructions more strictly than baseline methods, while also demonstrating strong generalization to previously unseen instructions.
  arXiv  Detail & Related papers  (2026-04-22T14:19:23Z)
• RoboAgent: Chaining Basic Capabilities for Embodied Task Planning [46.248451288196435]
  This paper focuses on embodied task planning, where an agent acquires visual observations from the environment and executes atomic actions to accomplish a given task.<n>We propose RoboAgent, a capability-driven planning pipeline in which the model actively invokes different sub-capabilities.<n>We use a multi-stage paradigm that consists of: (1) behavior cloning with expert plans, (2) DAgger training using trajectories collected by the model, and (3) reinforcement learning guided by an expert policy.
  arXiv  Detail & Related papers  (2026-04-09T04:01:27Z)
• ROSClaw: A Hierarchical Semantic-Physical Framework for Heterogeneous Multi-Agent Collaboration [9.434833852972353]
  ROSClaw is an agent framework for heterogeneous robots that integrates policy learning and task execution within a unified vision-language model (VLM) controller.<n>By establishing an autonomous closedloop framework, ROSClaw minimizes the reliance on robot-specific development.
  arXiv  Detail & Related papers  (2026-04-06T13:16:24Z)
• AtomVLA: Scalable Post-Training for Robotic Manipulation via Predictive Latent World Models [9.608633915316252]
  Vision-Language-Action (VLA) models demonstrate remarkable potential for generalizable robotic manipulation.<n>Current paradigms rely on coarse, high-level task instructions during supervised fine-tuning.<n>We propose method, the first subtask-aware VLA framework integrated with a scalable offline post-training pipeline.
  arXiv  Detail & Related papers  (2026-03-09T15:52:48Z)
• Reshaping Action Error Distributions for Reliable Vision-Language-Action Models [69.38615670891038]
  In robotic manipulation, vision-language-action (VLA) models have emerged as a promising paradigm for learning generalizable and scalable robot policies.<n>We focus on continuous-action VLA models and move beyond conventional MSE-based regression by reshaping action error distributions during training.<n>We evaluate our approaches across standard, few-shot, and noisy settings on multiple representative VLA architectures.
  arXiv  Detail & Related papers  (2026-02-04T05:37:09Z)
• Planning to Practice: Efficient Online Fine-Tuning by Composing Goals in Latent Space [76.46113138484947]
  General-purpose robots require diverse repertoires of behaviors to complete challenging tasks in real-world unstructured environments. To address this issue, goal-conditioned reinforcement learning aims to acquire policies that can reach goals for a wide range of tasks on command. We propose Planning to Practice, a method that makes it practical to train goal-conditioned policies for long-horizon tasks.
  arXiv  Detail & Related papers  (2022-05-17T06:58:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.