SemML: Enhancing Automata-Theoretic LTL Synthesis with Machine Learning

2025-01-29

AI Summary

To address performance bottlenecks in LTL reactive synthesis arising from complex specifications, this paper proposes an automated method integrating semantic annotation with machine learning to enable efficient online guidance in parity game solving. Our approach is the first to leverage semantic information from LTL-to-automaton translation to construct a guidance oracle jointly driven by supervised and reinforcement learning, thereby bridging the gap between semantic-aware learning and practical LTL synthesis. The method unifies semantic annotation, an optimized parity game algorithm, and an automaton-based synthesis framework. Evaluated on the SYNTCOMP benchmark, our tool solves more instances and significantly outperforms Strix on large-scale problems, securing the 2025 SYNTCOMP LTL realizability track championship.

Technology Category

• Machine Learning: Neuro-Symbolic Learning
• Constraint Satisfaction and Optimization: Satisfiability Modulo Theories
• Natural Language Processing: Code Generation / Program Synthesis from Natural Language

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Economics, Online Markets and Human Computation: Humans versus LLMs for data annotation and labeling
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Synthesizing a reactive system from specifications given in linear temporal logic (LTL) is a classical problem, finding its applications in safety-critical systems design. We present our tool SemML, which won this year's LTL realizability tracks of SYNTCOMP, after years of domination by Strix. While both tools are based on the automata-theoretic approach, ours relies heavily on (i) Semantic labelling, additional information of logical nature, coming from recent LTL-to-automata translations and decorating the resulting parity game, and (ii) Machine Learning approaches turning this information into a guidance oracle for on-the-fly exploration of the parity game (whence the name SemML). Our tool fills the missing gaps of previous suggestions to use such an oracle and provides an efficeint implementation with additional algorithmic improvements. We evaluate SemML both on the entire set of SYNTCOMP as well as a synthetic data set, compare it to Strix, and analyze the advantages and limitations. As SemML solves more instances on SYNTCOMP and does so significantly faster on larger instances, this demonstrates for the first time that machine-learning-aided approaches can out-perform state-of-the-art tools in real LTL synthesis.

Problem

• LTL synthesis
• efficiency
• complex rule handling

Innovation

• SemML
• Machine Learning
• LTL Synthesis