面向长时程具身智能体：VLAs-as-Tools 与工具对齐的 VLA 模型

View PDF HTML (experimental)

Abstract:Vision-language-action (VLA) models are effective robot action executors, but they remain limited on long-horizon tasks due to the dual burden of extended closed-loop planning and diverse physical operations. We therefore propose VLAs-as-Tools, a strategy that distributes this burden across a high-level vision language model (VLM) agent for temporal reasoning and a family of specialized VLA tools for diverse local physical operations. The VLM handles scene analysis, global planning, and recovery, while each VLA tool executes a bounded subtask. To tightly couple agent planning with VLA tool execution in long-horizon tasks, we introduce a VLA tool-family interface that exposes explicit tool selection and in-execution progress feedback, enabling efficient event-triggered agent replanning without continuous agent polling. To obtain diverse specialized VLA tools that faithfully follow agent invocations, we further propose Tool-Aligned Post-Training (TAPT), which constructs invocation-aligned training units for instruction following and adopts tool-family residual adapters for efficient tool specialization. Across five simulated benchmarks, VLAs-as-Tools improves the success rate of pi05 by 8.9 percentage points on average and enhances invocation fidelity by 15.0 points in Non-biased Rate. On three real-world Franka tasks, it improves success rate from 16.7% to 58.3% under matched data and compute. Code will be released.

Subjects:	Robotics (cs.RO); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV)
Cite as:	arXiv:2605.13119 [cs.RO]
	(or arXiv:2605.13119v2 [cs.RO] for this version)
	https://doi.org/10.48550/arXiv.2605.13119 arXiv-issued DOI via DataCite

Submission history

From: Changxing Liu [view email]
[v1] Wed, 13 May 2026 07:40:34 UTC (2,555 KB)
[v2] Mon, 12 Oct 2026 18:03:31 UTC (6,124 KB)