analiza aiqbench
Logic-VLA introduces a formal-requirement-aware framework that integrates Signal Temporal Logic (STL) specifications directly into vision-language-action models for robotics. By conditioning policies on syntactic graphs of temporal logic, the system significantly improves adherence to safety-critical spatiotemporal constraints while maintaining high success rates in nominal tasks. This approach demonstrates that a single VLA architecture can dynamically adapt to varying formal requirements without needing separate policies for each specification.
Logic-VLA: A Temporal Logic Conditioned Vision-Language-Action Model
arXiv:2608.20556v1 Announce Type: new Abstract: Vision-language-action (VLA) models can follow natural-language (NL) task instructions, but such instructions may not precisely specify safety-critical or spatiotemporal requirements on the resulting behavior. We introduce Logic-VLA, a formal-requirement-aware VLA that conditions on Signal Temporal Logic (STL) specifications supplied at inference time. Logic-VLA uses a syntax-graph-based STL encoder pre-trained to capture temporal logic semantics. Policy adaptation proceeds in two stages: STL-conditioned supervised fine-tuning on satisfying demonstrations is followed by trajectory-level preference optimization over matched satisfying-violating rollout pairs using a flow-matching surrogate for Identity Preference Optimization. This formulation improves formal requirement satisfaction while preserving the nominal NL task. We evaluate Logic-VLA in closed-loop quadcopter navigation simulation across randomized photorealistic environments and test generalization to STL formulas unseen during training. Across the evaluation benchmarks, Logic-VLA improves STL satisfaction rate over an STL-blind base policy by 24.8 to 40.7 percentage points (pp) while reducing nominal NL task success by at most 1.8 pp, showing that a single VLA can adapt its behavior to varying formal requirements without requiring a separate policy for each specification.
Abstract:Vision-language-action (VLA) models can follow natural-language (NL) task instructions, but such instructions may not precisely specify safety-critical or spatiotemporal requirements on the resulting behavior. We introduce Logic-VLA, a formal-requirement-aware VLA that conditions on Signal Temporal Logic (STL) specifications supplied at inference time. Logic-VLA uses a syntax-graph-based STL encoder pre-trained to capture temporal logic semantics. Policy adaptation proceeds in two stages: STL-conditioned supervised fine-tuning on satisfying demonstrations is followed by trajectory-level preference optimization over matched satisfying-violating rollout pairs using a flow-matching surrogate for Identity Preference Optimization. This formulation improves formal requirement satisfaction while preserving the nominal NL task. We evaluate Logic-VLA in closed-loop quadcopter navigation simulation across randomized photorealistic environments and test generalization to STL formulas unseen during training. Across the evaluation benchmarks, Logic-VLA improves STL satisfaction rate over an STL-blind base policy by 24.8 to 40.7 percentage points (pp) while reducing nominal NL task success by at most 1.8 pp, showing that a single VLA can adapt its behavior to varying formal requirements without requiring a separate policy for each specification.
Robotics (cs.RO); Logic in Computer Science (cs.LO); Systems and Control (eess.SY)
arXiv:2608.20556 [cs.RO]
(or arXiv:2608.20556v1 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2608.20556 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 273 cuvinte
Subiecte conexe
Explicit Language Memory for Long-Horizon Planning in Vision-Language-Action Models
arXiv · 6 aug. 2026
STeP: Signal Temporal Logic for Precise Specifications for Action Generation with Vision Language Models
arXiv · 22 iul. 2026
Article: The AI Productivity Paradox in Test Automation: Moving beyond Structural Validation to Perception and Intent
InfoQ · 1 iun. 2026
Vision-TL-Action: Neuro-Symbolic Trajectory Generation from Visual Observations and Temporal Logic
arXiv · 30 iul. 2026