Learning Robust Execution in Robotic Manipulation with Agentic Reinforcement Learning

• URL: http://arxiv.org/abs/2607.13818v1
• Date: Wed, 15 Jul 2026 13:25:52 GMT
• Title: Learning Robust Execution in Robotic Manipulation with Agentic Reinforcement Learning
• Abstract summary: We propose an agentic reinforcement learning framework that learns to restore effective execution through high-level decision-making.<n>Under execution degradation, it triggers appropriate recovery mechanisms to restore the robot to previously visited nominal states.<n>We evaluate the proposed method on the LIBERO benchmark, achieving up to a 13.7% improvement in success rate.
• Score: 17.169000876264796
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Robotic manipulation poses fundamental challenges due to uncertainty, long-horizon execution, and compounding errors, which can easily destabilize execution and lead to task failure. Although recent vision-language-action (VLA) models exhibit strong generalization, they typically lack explicit mechanisms to assess execution stability and to recover when execution deviates from its nominal behavior. In this paper, we propose: (1) two complementary metrics to assess execution quality at runtime, and (2) an agentic reinforcement learning framework that learns to restore effective execution through high-level decision-making rather than directly learning low-level actions. In this framework, an agentic policy reasons over recent execution history and selects among a small set of execution modes to regulate the execution process. Under execution degradation, it triggers appropriate recovery mechanisms to restore the robot to previously visited nominal states, enabling the task to continue. We evaluate the proposed method on the LIBERO benchmark, achieving up to a 13.7% improvement in success rate under standard settings and up to a 39.2% improvement under disturbance settings, demonstrating substantially enhanced execution robustness.

Related papers

• To Run or Not to Run: Analyzing the Cost-Effectiveness of Code Execution in LLM-Based Program Repair [18.653708704742353]
  Executions can be time-consuming and expensive, yet their impact on program repair agents remains underexplored.<n>Code execution is used across all agents and models analyzed, with an average of 8.8 test runs per task.<n>Current agents apply execution indiscriminately, paying its cost on instances where it provides little benefit.
  arXiv  Detail & Related papers  (2026-06-25T12:49:59Z)
• Benchmarking Vision-Language-Action Models on SO-101: Failure and Recovery Analysis [9.340058165047717]
  Vision-Language-Action (VLA) models have demonstrated strong generalization in robotic manipulation.<n>We present a standardized real-world benchmark for evaluating representative VLA and imitation learning policies on the low-cost SO-101 robotic platform.
  arXiv  Detail & Related papers  (2026-06-07T23:39:03Z)
• RePO-VLA: Recovery-Driven Policy Optimization for Vision-Language-Action Models [90.39703013636868]
  RePO-VLA is a recovery-driven policy optimization framework.<n>It assigns distinct roles to success, recovery, and failure trajectories.<n>It raises adversarial success from 20% to 75% on average and up to 80% in scaled real-world trials.
  arXiv  Detail & Related papers  (2026-05-10T08:24:05Z)
• Harnessing Embodied Agents: Runtime Governance for Policy-Constrained Execution [14.412476605788482]
  Embodied agents are evolving from passive reasoning systems into active executors that interact with tools, robots, and physical environments.<n>Existing approaches embed safety and recovery inside the agent loop, making execution control difficult to standardize, audit and adapt.<n>We propose a framework for policy-constrained execution that separates agent cognition from execution oversight.
  arXiv  Detail & Related papers  (2026-04-09T05:35:08Z)
• When Should a Robot Think? Resource-Aware Reasoning via Reinforcement Learning for Embodied Robotic Decision-Making [68.12864562049957]
  Embodied robotic systems increasingly rely on large language model (LLM)-based agents to support high-level reasoning.<n>This raises a fundamental question for embodied agents: when should the agent reason, and when should it act?<n>We propose RARRL (Resource-Aware Reasoning via Reinforcement Learning), a hierarchical framework for resource-aware orchestration of embodied agents.
  arXiv  Detail & Related papers  (2026-03-17T15:38:50Z)
• See, Plan, Rewind: Progress-Aware Vision-Language-Action Models for Robust Robotic Manipulation [59.07792608884117]
  We introduce See, Plan, Rewind (SPR), a progress-aware vision-language-action framework.<n>SPR operates through a continuous core cycle, Seeing the current state and upcoming milestone, Planning a trajectory towards the next 2D waypoint, and Rewinding to a recoverable state upon failure.<n>SPR achieves state-of-the-art robustness with the smallest performance drop, surpassing OpenVLA-OFT and UniVLA.
  arXiv  Detail & Related papers  (2026-03-10T07:22:51Z)
• Verified Critical Step Optimization for LLM Agents [67.05296684575445]
  Critical Step Optimization focuses preference learning on verified critical steps.<n>Method starts from failed policy trajectories rather than expert demonstrations.<n>Experiments on GAIA-Text-103 and XBench-DeepSearch show that CSO achieves 37% and 26% relative improvement over the SFT baseline.
  arXiv  Detail & Related papers  (2026-02-03T11:41:02Z)
• Conditional Multi-Stage Failure Recovery for Embodied Agents [17.95974193288372]
  We introduce a conditional multistage failure recovery framework that employs zero-shot chain prompting.<n>We evaluate our method on the TfD benchmark of the TEACH dataset and achieve state-of-the-art performance.
  arXiv  Detail & Related papers  (2025-07-08T14:23:41Z)
• Devil's Advocate: Anticipatory Reflection for LLM Agents [53.897557605550325]
  Our approach prompts LLM agents to decompose a given task into manageable subtasks. We implement a three-fold introspective intervention:. Anticipatory reflection on potential failures and alternative remedy before action execution. Post-action alignment with subtask objectives and backtracking with remedy to ensure utmost effort in plan execution.
  arXiv  Detail & Related papers  (2024-05-25T19:20:15Z)
• Persistent Reinforcement Learning via Subgoal Curricula [114.83989499740193]
  Value-accelerated Persistent Reinforcement Learning (VaPRL) generates a curriculum of initial states. VaPRL reduces the interventions required by three orders of magnitude compared to episodic reinforcement learning.
  arXiv  Detail & Related papers  (2021-07-27T16:39:45Z)

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.