FAR: Failure-Aware Retry for Test-Time Recovery and Continual Policy Improvement

• URL: http://arxiv.org/abs/2607.01111v1
• Date: Wed, 01 Jul 2026 16:01:54 GMT
• Title: FAR: Failure-Aware Retry for Test-Time Recovery and Continual Policy Improvement
• Abstract summary: Failure-Aware Retry (FAR) is a framework that enables robots to learn from previous failures at test time, adapt their behavior accordingly, and eventually complete the task autonomously.<n>FAR substantially improves success rates and robustness, with average gains of 17.6% over the standard diffusion policy in simulation and 11.7% in the real world.
• Score: 10.94594187411586
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Robot policies inevitably encounter failures when deployed in real environments. Naive retries often repeat the same mistakes, while many existing recovery methods rely on human intervention. In this paper, we propose Failure-Aware Retry (FAR), a framework that enables robots to learn from previous failures at test time, adapt their behavior accordingly, and eventually complete the task autonomously. FAR combines Failure-Contrastive Preference Adaptation, which constructs preference learning data from failures to steer the policy away from previously unsuccessful behaviors, with lightweight action perturbations during retries to encourage local exploration. We further incorporate successful recovery trajectories into a training loop for continual policy improvement. Experiments in both simulation and real-world manipulation tasks show that FAR substantially improves success rates and robustness, with average gains of 17.6% over the standard diffusion policy in simulation and 11.7% in the real world. In addition, FAR significantly improves data efficiency under both reset and timestep budgets during continual policy improvement by exploiting informative failure cases.

Related papers

• REVOLVE: An Automated Closed-Loop Framework for Evolving Robot Manipulation with Minimal Human Intervention [17.399763167916195]
  We present REVOLVE, an automated closed-loop framework for evolving robot manipulation with minimal human intervention.<n>Built on a unified software platform, REVOLVE integrates data collection, policy training and deployment, failure recovery, and continual learning into a single closed-loop workflow.
  arXiv  Detail & Related papers  (2026-09-13T16:08:03Z)
• Imagining Recovery: Inference-Time Counterfactual Realignment for Vision-Language-Action Models [10.832654624297135]
  Vision-language-action (VLA) models are fragile to online disruptions.<n>We propose Counterfactual Realignment (CoRe), a training-free framework that recovers a frozen VLA at inference time without failure data.
  arXiv  Detail & Related papers  (2026-08-14T18:49:46Z)
• RL Forgets! Towards Continual Policy Optimization [57.4336338996653]
  Continual post-training is becoming a central paradigm for adapting vision-language models to evolving tasks.<n>Recent work has increasingly favored reinforcement learning over supervised fine-tuning, driven by the belief that reinforcement learning is inherently less prone to forgetting.<n>We propose Continual Policy Optimization (CPO), a replay-free framework grounded in a prior-task behavioral KL objective.
  arXiv  Detail & Related papers  (2026-07-05T15:46:11Z)
• Learning from Mistakes: Rollout-Retrieval Lifelong Policy Learning for Autonomous Driving [18.991437941136876]
  This paper studies autonomous driving policy improvement from a lifelong learning perspective.<n>We propose Rollout-Retrieval Lifelong Policy Learning (R$2$LPL), a policy learning framework that retrieves corrective targets from recoverable policy-induced mistakes.<n>We evaluate R$2$LPL on large-scale closed-loop nuPlan benchmarks.
  arXiv  Detail & Related papers  (2026-06-29T16:37:50Z)
• Improving Robotic Generalist Policies via Flow Reversal Steering [92.97477771370428]
  Generalist policies can learn a wide range of skills from diverse robot datasets.<n>In order to solve or improve on challenging new tasks, we need a way to infer and invoke the appropriate actions from the policy's rich behavioral prior.<n>We propose Flow Reversal Steering (FRS): a method that takes suboptimal but reasonable'' actions, finds their latent noises by passing them through the flow policy in reverse, and maps them to nearby generalist action modes.
  arXiv  Detail & Related papers  (2026-06-11T17:59:45Z)
• 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)
• SPARR: Simulation-based Policies with Asymmetric Real-world Residuals for Assembly [13.3674466451862]
  We propose a hybrid approach that combines a simulation-trained base policy with a real-world residual policy.<n>Our method achieves near-perfect success rates across diverse two-part assembly tasks.
  arXiv  Detail & Related papers  (2026-02-26T17:26:13Z)
• FlowCorrect: Efficient Interactive Correction of Generative Flow Policies for Robotic Manipulation [0.7666240799116112]
  FlowCorrect is a modular interactive imitation learning approach that enables deployment-time adaptation of flow-matching manipulation policies.<n>We evaluate on a real-world robot across four tabletop tasks: pick-and-place, pouring, cup uprighting, and insertion.<n>With a low correction budget, FlowCorrect achieves an 80% success rate on previously failed cases.
  arXiv  Detail & Related papers  (2026-02-25T16:06:49Z)
• Failure-Aware RL: Reliable Offline-to-Online Reinforcement Learning with Self-Recovery for Real-World Manipulation [48.26705293834693]
  Failure-Aware Offline-to-Online Reinforcement Learning (FARL) is a new paradigm minimizing failures during real-world reinforcement learning.<n>We propose an algorithm that integrates a world-model-based safety critic and a recovery policy trained offline to prevent failures during online exploration.
  arXiv  Detail & Related papers  (2026-01-12T18:53:11Z)
• Human-in-the-loop Online Rejection Sampling for Robotic Manipulation [55.99788088622936]
  Hi-ORS stabilizes value estimation by filtering out negatively rewarded samples during online fine-tuning.<n>Hi-ORS fine-tunes a pi-base policy to master contact-rich manipulation in just 1.5 hours of real-world training.
  arXiv  Detail & Related papers  (2025-10-30T11:53:08Z)
• Fast Adaptation with Behavioral Foundation Models [82.34700481726951]
  Unsupervised zero-shot reinforcement learning has emerged as a powerful paradigm for pretraining behavioral foundation models.<n>Despite promising results, zero-shot policies are often suboptimal due to errors induced by the unsupervised training process.<n>We propose fast adaptation strategies that search in the low-dimensional task-embedding space of the pre-trained BFM to rapidly improve the performance of its zero-shot policies.
  arXiv  Detail & Related papers  (2025-04-10T16:14:17Z)
• Back to the Manifold: Recovering from Out-of-Distribution States [20.36024602311382]
  We propose a recovery policy that brings the agent back to the training manifold whenever it steps out of the in-distribution states. We demonstrate the effectiveness of the proposed method through several manipulation experiments on a real robotic platform.
  arXiv  Detail & Related papers  (2022-07-18T15:10:58Z)

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.