DeepThinkVLA: Enhancing Reasoning Capability of Vision-Language-Action Models

arXiv:2511.15669v2 Announce Type: replace Abstract: Does Chain-of-Thought (CoT) reasoning genuinely improve Vision-Language-Action (VLA) models, or does it merely add overhead? Existing CoT-VLA systems report limited and inconsistent gains, yet no prior work has rigorously diagnosed when and why CoT helps robots act. Through systematic experiments, we identify two necessary conditions that must be jointly satisfied for CoT to be effective in VLA: (1) Decoding Alignment -- CoT and actions must be generated with modality-appropriate mechanisms; forcing both through a single autoregressive decoder is not merely suboptimal but actively harmful, degrading performance by 4.2 percentage points; (2) Causal Alignment -- CoT must be causally linked to task success via outcome-based optimization; without it, supervised CoT is indistinguishable from no reasoning at all under distribution shift, exhibiting a 32.0,pp performance drop nearly identical to the 31.6,pp drop of a reasoning-free baseline. Guided by these findings, we build DeepThinkVLA: a hybrid-attention decoder satisfies Condition1 by pairing causal attention for language with bidirectional attention for parallel action decoding, while a two-stage SFT-then-RL pipeline satisfies Condition2 by aligning the full reasoning--action chain with sparse task-success rewards. DeepThinkVLA achieves 97.0% success on LIBERO, 79.0% robustness on LIBERO-Plus (vs. 61.6% for pi_0-FAST), and 59.3% success on RoboTwin~2.0, exceeding the strongest baseline by 21.7 points. Furthermore, we validate the practical effectiveness of our approach through real-world robot experiments. Code available at https://github.com/OpenBMB/DeepThinkVLA

Related

• Do Not Step Into the Same River Twice: Learning to Reason from Trial and Error
• Can Explicit Physical Feasibility Benefit VLA Learning? An Empirical Study
• Does RLVR Extend Reasoning Boundaries? Investigating Capability Expansion in Vision-Language Models
• Better Eyes, Better Thoughts: Why Vision Chain-of-Thought Fails in Medicine
• Data-Efficient RLVR via Off-Policy Influence Guidance

Source: arXiv cs.LG | 2026-04-21