Newest papers

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

Jiatong Li, Jisheng Dang, Qiangqiang Ma, Bimei Wang, Jingwen Zhao, Wenjun Ma, Juncheng Li, Hong Peng, Bin Hu · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.28109 · cited by 0 works (OpenAlex) · open-access PDF

Korean

비전 언어 행동 (VLA) 모델은 표준 로봇 조작 벤치마크에서 강력한 성능을 달성했습니다. 그러나, 그들의 신뢰성은 임무 조건이 표준 설정에서 차이가 있을 때 상당히 떨어질 수 있습니다. 객체 위치 및 작업 지침의 혼란은 완전한 작업 실패로 이어질 수 있습니다. 기존 VLA 정책은 일반적으로 이러한 실패 모드를 구별하고 적절한 복구 전략을 선택하는 명확한 실행 시간 메커니즘이 부족합니다. 첫째, 플래너 에이전트는이 문제를 체계적으로 완화하기 위해 FIT-MAC를 제안합니다. 실패 인식, 닫힌 루프 멀티 에이전트 제어 프레임 워크는 추론 시간에 VLA 정책의 강도성을 향상시킵니다. F

Machine translation (Meta M2M100); the English original follows.

Abstract

Vision-language-action (VLA) models have achieved strong performance on standard robotic manipulation benchmarks. However, their reliability can degrade substantially when task conditions deviate from the nominal setting. Perturbations in object positions and task instructions may lead to complete task failure. Existing VLA policies generally lack an explicit runtime mechanism for distinguishing these failure modes and selecting an appropriate recovery strategy. To systematically mitigate this issue, we propose FIT-MAC, a failure-aware, closed-loop multi-agent control framework for improving the robustness of VLA policies at inference time. FIT-MAC augments a VLA policy with an inference-time control layer. First, the Planner Agent parses the language instruction into a structured task specification that captures the manipulation goal and spatial constraints, and the Grounder Agent resolves each instruction-level reference to a visual target. Next, the Verifier Agent tracks phase-specific execution progress, distinguishes target-binding errors from local execution failures, and determines whether intervention is warranted. The Correction Agent then routes permitted interventions to target rebinding or bounded grasping or placement recovery, depending on the failure type. When no intervention is required, the pretrained VLA remains the default action generator. Extensive experiments on LIBERO-PRO demonstrate that FIT-MAC improves robustness across multiple VLA backbones, consistently increasing success rates and achieving state-of-the-art performance under diverse perturbations.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Computer science, Robustness (evolution), Planner, Inference, Task (project management), Artificial intelligence

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange