Diverse Planning with Simulators via Linear Temporal Logic

2025-10-20

AI Summary

Autonomous agents in simulation-based planning often produce semantically redundant plans, lacking explicit modeling of behavioral-level diversity. Method: This paper proposes FBI_LTL, the first framework to employ Linear Temporal Logic (LTL) for formally specifying semantic diversity constraints—ensuring generated policies are meaningfully distinguishable at the behavioral-intent level, not merely syntactically varied. FBI_LTL integrates LTL-defined diversity constraints directly into simulation-based search, enabling semantics-driven diverse planning. Results: Experiments across multiple benchmark tasks demonstrate that FBI_LTL consistently generates planning sequences with significantly higher semantic diversity while preserving feasibility and robustness, outperforming mainstream baselines. These results validate its effectiveness and practicality in non-symbolic, real-world scenarios.

Technology Category

• Humans and AI: Human-Aware Planning and Behavior Prediction
• Multiagent Systems: Multiagent Planning
• Planning, Routing, and Scheduling: Planning with Language Models

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Agentic search
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

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 $ exttt{FBI}_ exttt{LTL}$, a diverse planner explicitly designed for simulation-based planning problems. $ exttt{FBI}_ exttt{LTL}$ 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, $ exttt{FBI}_ exttt{LTL}$ 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 $ exttt{FBI}_ exttt{LTL}$ 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.

Problem

• Generating diverse plans for autonomous agents in simulations
• Using Linear Temporal Logic to define semantic diversity criteria
• Overcoming limitations of syntactically different but identical solutions

Innovation

• Uses Linear Temporal Logic for diversity criteria
• Integrates semantic diversity into search process
• Generates diverse plans in simulation-based environments