Large Language Models as Falsifiers for Cyber-Physical Systems

arXiv:2609.20752 · eess.SY, cs.AI, cs.LO, cs.SE, cs.SY · Submitted 2026-09-17 · Read on arXiv

eess.SY, cs.AI, cs.LO, cs.SE, cs.SY

Submitted: 2026-09-17

Updated: 2026-09-17

Comments: 22 pages, 5 figures, 3 tables

Code: https://github.com/aliabigdeli/llm-falsifier

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Robustness — 81× in this paper · explained in 5 episodes
• Benchmark — 36× in this paper · explained in 2 episodes
• Verification — 22× in this paper · explained in 2 episodes
• Hybrid System — 16× in this paper · explained in 2 episodes
• Trace — 16× in this paper · explained in 2 episodes
• Automatic Transmission — 10× in this paper
• Ablation — 8× in this paper · explained in 1 episode
• Bayesian Optimization — 8× in this paper · explained in 3 episodes
• Falsification Rate — 7× in this paper
• Signal Temporal Logic — 6× in this paper
• Ablation study — 5× in this paper · explained in 1 episode
• Ablation Studies — 3× in this paper · explained in 1 episode
• Neural Network Controller — 3× in this paper
• Sample Efficiency — 3× in this paper · explained in 4 episodes
• Signal Temporal Logic (STL) — 3× in this paper · explained in 4 episodes
• Abstraction — 2× in this paper · explained in 1 episode
• American Control Conference — 2× in this paper
• Chasing Cars — 2× in this paper
• Explainability — 2× in this paper · explained in 3 episodes
• Formal Methods — 2× in this paper · explained in 3 episodes
• Large Language Models (LLMs) — 2× in this paper · explained in 6 episodes
• Reasoning Traces — 2× in this paper · explained in 3 episodes
• Reinforcement Learning — 2× in this paper · explained in 4 episodes
• System Identification — 2× in this paper · explained in 3 episodes
• Active Automata Learning — 1× in this paper · explained in 1 episode
• Alignment — 1× in this paper · explained in 1 episode
• Causal Reasoning — 1× in this paper · explained in 2 episodes
• Closed-Loop Control — 1× in this paper · explained in 2 episodes
• Core — 1× in this paper · explained in 2 episodes
• Distillation — 1× in this paper · explained in 2 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• Hybrid Approach — 1× in this paper · explained in 4 episodes
• In-Context Learning — 1× in this paper · explained in 4 episodes
• In-Context Learning (ICL) — 1× in this paper · explained in 5 episodes
• Multi-Agent System — 1× in this paper · explained in 6 episodes
• Semantic Alignment — 1× in this paper · explained in 3 episodes
• Steam Condenser with Recurrent Neural Network Controller — 1× in this paper

Sources

• gpt-oss-120b & gpt-oss-20b Model Card
• In-context Reinforcement Learning with Algorithm Distillation
• LLMs Are In-Context Bandit Reinforcement Learners
• Can Language Models Falsify? Evaluating Algorithmic Reasoning with Counterexample Creation

Related papers

• One Request, Multiple Experts: LLM Orchestrates Domain Specific Models via Adaptive Task Routing
• A Geometric Decision Procedure for STL Feasibility and Repair
• Submodular Multi-Agent Policy Learning for Online Distributed Task Allocation in Open Multi-Agent Systems
• Policy-Level Recursive Self-Improvement for Embodied AI with a Criticality World Model
• Minimal Experiments for Robust Stabilization: Information, Spectral Geometry, and Duration
• Decentralized Power-Optimal Coordination for Spacecraft Swarms Using Time-Varying Magnetorquer Actuation