# Logic-VLA: A Temporal Logic Conditioned Vision-Language-Action Model

arXiv: https://arxiv.org/abs/2608.20556 · HTML: https://mlsanity.com/paper/2608.20556/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Aerial and drone VLA, one of 13 directions in Vision-language-action models.
- Builds on 32 of its 38 references that are in the map.
- First posted on arXiv 20 Aug 2026.

## Placed in

- Vision-language-action models / [Aerial and drone VLA](https://mlsanity.com/vla/aerial-and-drone-vla/)

## Builds on (most cited first, 30 of 32)

- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023)
- [OpenVLA: An Open-Source Vision-Language-Action Model](https://mlsanity.com/paper/2406.09246/) (2024)
- [π0.5: a Vision-Language-Action Model with Open-World Generalization](https://mlsanity.com/paper/2504.16054/) (2025)
- [SimPO: Simple Preference Optimization with a Reference-Free Reward](https://mlsanity.com/paper/2405.14734/) (2024)
- [A General Theoretical Paradigm to Understand Learning from Human Preferences](https://mlsanity.com/paper/2310.12036/) (2023)
- [GRAPE: Generalizing Robot Policy via Preference Alignment](https://mlsanity.com/paper/2411.19309/) (2024)
- [Flow Matching Policy Gradients](https://mlsanity.com/paper/2507.21053/) (2025)
- [SafeVLA: Towards Safety Alignment of Vision-Language-Action Model via Constrained Learning](https://mlsanity.com/paper/2503.03480/) (2025)
- [A Survey of Direct Preference Optimization](https://mlsanity.com/paper/2503.11701/) (2025)
- [Safety Guardrails for LLM-Enabled Robots](https://mlsanity.com/paper/2503.07885/) (2025)
- [VLSA: Vision-Language-Action Models with Plug-and-Play Safety Constraint Layer](https://mlsanity.com/paper/2512.11891/) (2025)
- [VLA-AN: An Efficient and Onboard Vision-Language-Action Framework for Aerial Navigation in Complex Environments](https://mlsanity.com/paper/2512.15258/) (2025)
- [Robust Temporal Logic Model Predictive Control](https://mlsanity.com/paper/1511.00347/) (2015)
- [RTAMT: Online Robustness Monitors from STL](https://mlsanity.com/paper/2005.11827/) (2020)
- [Learning from Demonstrations using Signal Temporal Logic](https://mlsanity.com/paper/2102.07730/) (2021)
- [FDPP: Fine-tune Diffusion Policy with Human Preference](https://mlsanity.com/paper/2501.08259/) (2025)
- [Vision-Language-Action Safety: Threats, Challenges, Evaluations, and Mechanisms](https://mlsanity.com/paper/2604.23775/) (2026)
- [Temporal Logic Specification-Conditioned Decision Transformer for Offline Safe Reinforcement Learning](https://mlsanity.com/paper/2402.17217/) (2024)
- [TeLoGraF: Temporal Logic Planning via Graph-encoded Flow Matching](https://mlsanity.com/paper/2505.00562/) (2025)
- [SafeVLA-Bench: A Benchmark for the Success-Safety Gap in Vision-Language-Action Models](https://mlsanity.com/paper/2606.00773/) (2026)
- [Diverse Controllable Diffusion Policy with Signal Temporal Logic](https://mlsanity.com/paper/2503.02924/) (2025)
- [FlowPRO: Reward-Free Reinforced Fine-Tuning of Flow-Matching VLAs via Proximalized Preference Optimization](https://mlsanity.com/paper/2606.05468/) (2026)
- [Maximizing Alignment with Minimal Feedback: Efficiently Learning Rewards for Visuomotor Robot Policy Alignment](https://mlsanity.com/paper/2412.04835/) (2024)
- [From Words to Safety: Language-Conditioned Safety Filtering for Robot Navigation](https://mlsanity.com/paper/2511.05889/) (2025)
- [Neuro-Symbolic Safety Guidance for Vision-Language-Action Models via Constrained Flow Matching](https://mlsanity.com/paper/2607.01378/) (2026)
- [Bridging Perception and Planning: Towards End-to-End Planning for Signal Temporal Logic Tasks](https://mlsanity.com/paper/2509.12813/) (2025)
- [Temporal Logic Guidance for Action-Only Diffusion Policies with World Models](https://mlsanity.com/paper/2606.22729/) (2026)
- [STeP: Signal Temporal Logic for Precise Specifications for Action Generation with Vision Language Models](https://mlsanity.com/paper/2607.18580/) (2026)
- [Sampling-Based Planning Under STL Specifications: A Forward Invariance Approach](https://mlsanity.com/paper/2506.10739/) (2025)

## Abstract (arXiv)

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.