# Diverse Planning with Simulators via Linear Temporal Logic

arXiv: https://arxiv.org/abs/2510.17418 · HTML: https://mlsanity.com/paper/2510.17418/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 41 references that are in the map.
- First posted on arXiv 20 Oct 2025.

## Builds on (most cited first, 9 of 9)

- [PDDLGym: Gym Environments from PDDL Problems](https://mlsanity.com/paper/2002.06432/) (2020)
- [The Emerging Landscape of Explainable AI Planning and Decision Making](https://mlsanity.com/paper/2002.11697/) (2020)
- [Autonomous Penetration Testing using Reinforcement Learning](https://mlsanity.com/paper/1905.05965/) (2019)
- [DreamGarden: A Designer Assistant for Growing Games from a Single Prompt](https://mlsanity.com/paper/2410.01791/) (2024)
- [From Robotic Process Automation to Intelligent Process Automation: Emerging Trends](https://mlsanity.com/paper/2007.13257/) (2020)
- [Measuring Diversity of Game Scenarios](https://mlsanity.com/paper/2404.15192/) (2024)
- [Diverse, Top-k, and Top-Quality Planning Over Simulators](https://mlsanity.com/paper/2308.13147/) (2023)
- [Behaviour Planning: A Toolkit for Diverse Planning](https://mlsanity.com/paper/2405.04300/) (2024)
- [Climate Adaptation with Reinforcement Learning: Experiments with Flooding and Transportation in Copenhagen](https://mlsanity.com/paper/2409.18574/) (2024)

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

- [From Stories to Cities to Games: A Qualitative Evaluation of Behaviour Planning](https://mlsanity.com/paper/2601.04911/) (2026)

## Abstract (arXiv)

Autonomous agents rely on automated planning algorithms to achieve their objectives. Simulation-based planning offers a significant advantage over declarative models in modelling complex environments. However, relying solely on a planner that produces a single plan may not be practical, as the generated plans may not always satisfy the agent's preferences. To address this limitation, we introduce textttFBI_textttLTL, a diverse planner explicitly designed for simulation-based planning problems. textttFBI_textttLTL utilises Linear Temporal Logic (LTL) to define semantic diversity criteria, enabling agents to specify what constitutes meaningfully different plans. By integrating these LTL-based diversity models directly into the search process, textttFBI_textttLTL ensures the generation of semantically diverse plans, addressing a critical limitation of existing diverse planning approaches that may produce syntactically different but semantically identical solutions. Extensive evaluations on various benchmarks consistently demonstrate that textttFBI_textttLTL generates more diverse plans compared to a baseline approach. This work establishes the feasibility of semantically-guided diverse planning in simulation-based environments, paving the way for innovative approaches in realistic, non-symbolic domains where traditional model-based approaches fail.