3 papers
cs.AI2026
From Monolithic to Modular: Segment-level Automatic Prompt Optimization
Nikita Kulin, Viktor Zhuravlev, Artur Khairullin +4
Automatic Prompt Optimization (APO) often rewrites prompts monolithically, which can improve one behavior while degrading others. We present SAPO, a segment-level APO method that d…
cs.CY2025
A Modular LLM-Agent System for Transparent Multi-Parameter Weather Interpretation
Daniil Sukhorukov, Andrei Zakharov, Nikita Glazkov +6
Weather forecasting is not only a predictive task but an interpretive scientific process requiring explanation, contextualization, and hypothesis generation. This paper introduces…
cs.AI2025
Hierarchical AI-Meteorologist: LLM-Agent System for Multi-Scale and Explainable Weather Forecast Reporting
Daniil Sukhorukov, Andrei Zakharov, Nikita Glazkov +6
We present the Hierarchical AI-Meteorologist, an LLM-agent system that generates explainable weather reports using a hierarchical forecast reasoning and weather keyword generation.…