arXiv cs.AI· Tuan Duong Trinh, Basim Azam, Mohammed Ishaq Ansari, Mohammed Yaqoob Ansari, Naveed Akhtar·· 9 天前AI 评分27
推理链作为视觉-语言-动作策略的控制面：DeepThinkVLA 在 LIBERO-Goal 上的反事实干预研究
Altered Thoughts, Altered Actions: Reasoning Chain as Control Surface for a Vision-Language-Action Policy
AI 导读
研究以确定性实体替换分别对指令和推理链进行修复与破坏双向测量，发现破坏推理链的代价集中在语言单独决定目标的 LIBERO-Goal 任务上。用 DeepThinkVLA 做反事实干预，让策略接收被破坏的指令但替换为干净指令下生成的推理链，挽回了 47.8 pp 的损失成功率，全部 10 个任务均朝预测方向移动，但仍比干净运行低 38.0 pp。
正文 · 原文
Abstract:Vision-language-action policies map camera images and natural-language instructions to a robot's motor actions. Some of these policies are designed to reason in text before acting, generating a reasoning chain and decoding actions conditioned on that chain. The works introducing this design offer the reasoning chain as an oversight interface: text a person can read and edit to correct the policy. What an edited reasoning chain does to the policy's motor actions, whether it repairs them or corrupts them, has so far been measured only in part. We measure both directions, repair and corruption, with our deterministic entity swap applied to the instruction the policy receives and to the reasoning chain it generates. A forty-task observed backdrop across all four LIBERO simulation suites reveals that the cost of corrupting the reasoning chain concentrates where language alone determines the goal. There, on LIBERO-Goal, we run the counterfactual intervention with DeepThinkVLA, chosen because its reasoning chain is exposed as plain text. The policy receives a corrupted instruction, but its reasoning chain is replaced by the one it generates when that instruction is clean. This counterfactually correct reasoning chain recovers 47.8 pp of the lost success, our pre-registered confirmatory test. Had the chain merely restated what the camera image already determines, the replacement could have changed nothing. Instead, all 10 tasks move in the predicted direction, though success falls short of the clean runs by 38.0 pp, a gap we had predicted at 5-15 pp. The reasoning chain is therefore a working control surface: text written into it moves the robot, repairing behaviour when the text is right and corrupting it when the text is wrong. Whether to expose such a control surface is a deployment tradeoff, and part of it can now be measured.
| Comments: | Accepted at the VLM4RWD workshop, NeurIPS 2026 |
| Subjects: | Robotics (cs.RO); Artificial Intelligence (cs.AI); Machine Learning (cs.LG) |
| MSC classes: | 68T40 |
| ACM classes: | I.2.9; I.2.6 |
| Cite as: | arXiv:2603.12717 [cs.RO] |
| (or arXiv:2603.12717v3 [cs.RO] for this version) | |
| https://doi.org/10.48550/arXiv.2603.12717 arXiv-issued DOI via DataCite |
Submission history
From: Tuan Duong Trinh [view email]
[v1]
Fri, 13 Mar 2026 07:02:51 UTC (168 KB)
[v2]
Tue, 29 Sep 2026 08:05:36 UTC (2,470 KB)
[v3]
Thu, 8 Oct 2026 06:15:00 UTC (2,474 KB)
来源：arXiv cs.AI · arxiv.org