LLMs can construct powerful representations and streamline sample-efficient supervised learning

ArXi:2603.11679v1 Announce Type: new As real-world datasets become increasingly complex and heterogeneous, supervised learning is often bottlenecked by input representation design. Modeling multimodal data for downstream tasks, such as time-series, free text, and structured records, often requires non-trivial domain-specific engineering. We propose an agentic pipeline to streamline this process.