# hint2: Hierarchical World Models for Inference-Time Temporal Logic Guidance

arXiv: https://arxiv.org/abs/2608.13678 · HTML: https://mlsanity.com/paper/2608.13678/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Embodied and robot world models, one of 11 directions in World models.
- Builds on 18 of its 58 references that are in the map.
- First posted on arXiv 13 Aug 2026.

## Placed in

- World models / [Embodied and robot world models](https://mlsanity.com/wm/embodied-and-robot-world-models/)

## Builds on (most cited first, 18 of 18)

- [OpenVLA: An Open-Source Vision-Language-Action Model](https://mlsanity.com/paper/2406.09246/) (2024)
- [π0: A Vision-Language-Action Flow Model for General Robot Control](https://mlsanity.com/paper/2410.24164/) (2024)
- [Mastering Diverse Domains through World Models](https://mlsanity.com/paper/2301.04104/) (2023)
- [What Matters in Learning from Offline Human Demonstrations for Robot Manipulation](https://mlsanity.com/paper/2108.03298/) (2021)
- [Reinforcement Learning and Control as Probabilistic Inference: Tutorial and Review](https://mlsanity.com/paper/1805.00909/) (2018)
- [World Action Models are Zero-shot Policies](https://mlsanity.com/paper/2602.15922/) (2026)
- [Learning to Generalize Across Long-Horizon Tasks from Human Demonstrations](https://mlsanity.com/paper/2003.06085/) (2020)
- [FLOWER: Democratizing Generalist Robot Policies with Efficient Vision-Language-Action Flow Policies](https://mlsanity.com/paper/2509.04996/) (2025)
- [Logically-Constrained Reinforcement Learning](https://mlsanity.com/paper/1801.08099/) (2018)
- [Long-VLA: Unleashing Long-Horizon Capability of Vision Language Action Model for Robot Manipulation](https://mlsanity.com/paper/2508.19958/) (2025)
- [Hierarchical Planning with Latent World Models](https://mlsanity.com/paper/2604.03208/) (2026)
- [VLSA: Vision-Language-Action Models with Plug-and-Play Safety Constraint Layer](https://mlsanity.com/paper/2512.11891/) (2025)
- [Model-based Reinforcement Learning from Signal Temporal Logic Specifications](https://mlsanity.com/paper/2011.04950/) (2020)
- [Constraint-Aware Diffusion Guidance for Robotics: Real-Time Obstacle Avoidance for Autonomous Racing](https://mlsanity.com/paper/2505.13131/) (2025)
- [TeLoGraF: Temporal Logic Planning via Graph-encoded Flow Matching](https://mlsanity.com/paper/2505.00562/) (2025)
- [H-WM: Robotic Task and Motion Planning Guided by Hierarchical World Model](https://mlsanity.com/paper/2602.11291/) (2026)
- [Logically Constrained Robotics Transformers for Enhanced Perception-Action Planning](https://mlsanity.com/paper/2408.05336/) (2024)
- [Temporal Logic Guidance for Action-Only Diffusion Policies with World Models](https://mlsanity.com/paper/2606.22729/) (2026)

## Built on by (most cited first, 1 of 1)

- [Jaxolotl: A Unified High-Performance Benchmark Suite for LTL-Based Multi-Task RL](https://mlsanity.com/paper/2609.38065/) (2026)

## Abstract (arXiv)

Executing Linear Temporal Logic (LTL) instructions with learned robot policies faces two practical challenges: demonstrations may cover individual behaviors without containing the temporal compositions requested at deployment, and semantic success predicates often provide little useful motor guidance through quantitative robustness. We address these challenges by separating behavior learning from temporal composition. From the same offline demonstrations, we train an unconditioned multimodal diffusion policy and a semantic predictor that estimates which semantic outcomes are likely to follow a proposed action sequence. These predictions provide a learned guidance signal without requiring hand-designed robustness measures for semantic task objectives. At deployment, an LTL automaton tracks instruction progress and scores the policy's proposed actions according to their predicted semantic outcomes. Neither learned component receives the specification during training, allowing demonstrated behaviors to be reused in longer, previously unseen temporal compositions without retraining. For additional runtime safety constraints with informative continuous margins, an optional robustness-based controller locally refines the selected actions. Experiments in a navigation environment, CALVIN manipulation, and on a real robot demonstrate reliable execution of complex temporal instructions and additional safety constraints, with substantial improvements over temporal-logic baselines.