Agentic AI for 15-Minute Single Day-Ahead Coupling Market Analytics in Central and Eastern Europe

The shift to 15-minute Market Time Units (MTU) in the Single Day-Ahead Coupling (SDAC) increases temporal granularity but complicates the interpretation of intra-hour electricity price spikes and rapid ramps. This paper examines whether architectural decomposition improves the reliability of Large Language Model (LLM)-based diagnostics in price-only settings. We compare a proposed agentic workflow, featuring structured context extraction, spike/ramp detection, hypothesis generation, consistency checks and explicit uncertainty calibration, against a monolithic LLM baseline. The paper contributes: (i) a reproducible benchmark for 15-minute diagnostic question answering in day-ahead markets, (ii) an agentic architecture tailored to structured time-series reasoning with explicit uncertainty handling, (iii) empirical evidence that decomposition and verification improve evidence grounding and trustworthiness in market analytics. The evaluation includes 150 benchmark cases from six Central and Eastern European bidding zones (Bulgaria, Czechia, Hungary, Poland, Romania, Slovakia), comprising 47 spike and 103 ramp cases. Using identical inputs, we assess automatic reliability metrics and human ratings. The agentic workflow improves reliability (∆ = +0.164, 95% CI [+0.132, +0.195]) and significantly increases calibrated price-only disclaimers (∆ = +0.560), while reducing unsupported exogenous assertions (∆ = −0.387). Human evaluation confirms higher overall quality (+0.74), helpfulness (+1.06), and correctness (+0.94), with a 65.5% pairwise win rate. Results demonstrate that structured decomposition and verification enhance grounding, calibration and trustworthiness in high-frequency electricity market diagnostics.