FIT-MAC: A Closed-Loop Multi-Agent Framework for Robust Vision-Language-Action Models

Long-horizon robot manipulation with Vision-Language-Action (VLA) policies remains vulnerable to execution-time deviations, as final task success provides little information for diagnosing and correcting failures caused by action noise, object displacement, or goal misalignment. We introduce a stage-aware failure verification and Prompt Recovery framework that enables closed-loop correction of a fixed VLA policy without parameter updates or privileged simulator states. The framework introduces an observable-history-based Learned Verifier that jointly estimates manipulation progress and execution risk by temporally modeling multi-view visual observations, proprioceptive states, and executed actions. To provide interpretable task understanding, we represent manipulation execution through semantic progress stages, including approach, alignment, grasp, transport, and placement, and identify stage-specific failure patterns. Upon detecting abnormal execution, the framework preserves the original instruction and generates a stage-conditioned recovery prompt, allowing the same frozen VLA policy to produce corrective actions. Extensive multi-round evaluations on LIBERO and LIBERO Plus demonstrate that the proposed approach substantially improves closed-loop reliability under diverse perturbations. Without access to privileged object or goal coordinates, the Learned Verifier achieves recovery performance close to that of the privileged rule-based verifier in the evaluated settings. These results show that observable visual-proprioceptive-action history is sufficient to infer latent task states and enable practical failure recovery for existing VLA policies.

Vision-Language-Action (VLA) models demonstrate strong perfor-1 mance on language-conditioned robotic manipulation within their training dis-2 tribution, yet their generalization capabilities remain fundamentally limited. They3 lack the robustness required to handle perturbations, frequently failing when con-4 fronted with lighting changes, altered camera viewpoints, or small initial-state5 variations. We propose PROBEACT, a training-free runtime intervention frame-6 work that detects and recovers from grasping and placement failures in pre-7 trained VLA policies without modifying their weights or requiring additional8 demonstrations. PROBEACT combines three components: (i) a lightweight multi-9 target hidden-state probe that predicts the 3D positions of task-relevant objects10 from intermediate VLA features, with Hungarian-matched identity tracking for11 multi-object scenes; (ii) an object-agnostic kinematic state machine that detects12 grasp, transport, and placement failures using only gripper-internal signals and13 end-effector kinematics; and (iii) a hierarchical Control Barrier Function (CBF)14 filter that encodes repeated-failure locations as soft safe-set constraints, mini-15 mally correcting VLA actions while preserving baseline behavior. As a plug-and-16 play, training-free intervention loop, PROBEACT is orthogonal to existing train-17 ing pipelines. Evaluated on the LIBERO-plus benchmark, our framework acts as18 a universal safety net, improving the success rate of the OpenVLA-OFT model19 from 69.6% to 74.1%, while demonstrating broad applicability to both base and20 fine-tuned VLA policies.

Vision-Language-Action (VLA) models remain brittle in long-horizon, contact-rich manipulation because success-only imitation provides little supervision for execution drift, while failed rollouts are often discarded. We introduce RePO-VLA, a recovery-driven policy optimization framework that assigns distinct roles to success, recovery, and failure trajectories. RePO-VLA first applies Recovery-Aware Initialization (RAI), slicing recovery segments and resetting history so corrective actions depend on the current adverse state rather than the preceding failure. It then learns a Progress-Aware Semantic Value Function (PAS-VF), aligning spatiotemporal trajectory features with instructions and successful references. The resulting labels salvage useful failure prefixes via reliability decay, while low-value labels mark drift and terminal breakdowns, teaching differences among nominal, failed, and corrective actions. The data engine turns adverse states into planner-generated or human-collected corrective rollouts, teaching recovery to the success manifold. Value-Conditioned Refinement (VCR) trains the policy to prefer high-progress actions. At deployment, a fixed high value ($v=1.0$) biases actions toward the learned success manifold without online failure detectors or heuristic retries. We introduce FRBench, with standardized error injection and recovery-focused evaluation. Across simulated and real-world bimanual tasks, RePO-VLA improves robustness, raising adversarial success from 20% to 75% on average and up to 80% in scaled real-world trials.