Time-series Diagnostic Reasoning with Knowledge Injection

Zelin He, Boran Han, Xiyuan Zhang, Shuai Zhang, Qi Zhu, Haoyang Fang, Danielle C. Maddix, Abdul Fatir Ansari, Haotian Lin, Akash Chandrayan, Abhinav Pradhan, Bernie Wang, Matthew Reimherr

Abstract: Time‐series diagnostic reasoning is essential for many applications, yet existing solutions face a persistent gap: general reasoning large language models (GRLMs) possess strong reasoning skills but lack the domain-specific knowledge to understand complex time-series patterns. Conversely, fine-tuned time-series large language models (TSLMs) understand these patterns but lack the capacity to generalize reasoning for more complicated questions. To bridge this gap, we propose a hybrid knowledge-injection framework that injects TSLM-generated insights directly into GRLM's reasoning trace, thereby achieving strong time-series reasoning with in-domain knowledge. As collecting data for knowledge injection fine-tuning is costly, we further leverage a reinforcement learning-based approach with verifiable rewards (RLVR) to elicit knowledge-rich traces without human supervision, then transfer such an in-domain thinking trace into GRLM for efficient knowledge injection. We further release SensorTSR, a multivariate time-series-based diagnostic reasoning benchmark collected from real-world industrial operations. Across SensorTSR and other public datasets, our method consistently surpasses TSLMs by 9.1\%–26.1\% and GRLMs by 7.9\%–22.4\%, delivering robust, context-aware time-series diagnostic insights.

Submission Number: 1906