arXiv:2605.06483v1 Announce Type: new
Abstract: Signal Temporal Logic (STL) is an expressive formal language for specifying spatio-temporal requirements over real-valued, real-time signals. It has been widely used for the verification and synthesis of autonomous systems and cyber-physical systems. In practice, however, users often express their requirements in natural language rather than in structured STL formulas, making natural-language-to-STL translation a critical yet challenging task. Manual specification requires temporal-logic expertise and cannot scale, while prompting commercial LLM APIs incurs substantial token costs and may expose sensitive system requirements to third-party services, raising privacy concerns for industrial deployment. To address these challenges, we present textscReasonSTL, a tool-augmented framework that adapts local open-source language models for natural-language-to-STL generation. textscReasonSTL decomposes the translation process into explicit reasoning, deterministic tool calls, and structured formula construction. We further introduce process-rewarded training to supervise both tool-use trajectories and final formulas, together with textscSTL-Bench, a bilingual, computation-aware benchmark grounded in real-world signals. Experiments show that a 4B model trained with textscReasonSTL achieves state-of-the-art performance in both automatic metrics and human evaluations, demonstrating that textscReasonSTL provides a transparent, low-cost, and privacy-preserving alternative for formal specification drafting.
Crisis support teams’ technological openness and learning attitudes toward the AI based virtual patient system crisis support VR
BackgroundAgainst the backdrop of escalating global humanitarian crises, innovative didactic simulations are becoming increasingly important. A promising alternative to traditional classroom-based didactics for learning psychological