SOURCE-LINKED INTELLIGENCE

TraceBench: Controlled Evaluation of LLM Agents for Time-Series Root-Cause Attribution

arXiv · AI, language, vision and robotics · article · Aug 27, 2026 · UTC

LLM agents are increasingly applied to anomaly detection and root-cause analysis in time-series observations collected from real-world systems; however, their performance on these tasks has not been systematically evaluated under controlled conditions. We introduce TraceBench, a simulation-based framework for generating controlled root-cause attribution tasks. In each generated task, an agent receives time-series observations produced by simulating a physical dynamical system and must determine whether a system parameter was altered during the simulation and, if so, which one. Using TraceBench

Read original source ↗ Open in workspace

recordType

paper

region

Global