Ido Levy

Teaching agents *what* unstated information to hunt down—rather than just *when* to act—enables small models to beat 15× larger baselines at multi-hop task completion while asking fewer questions.

Ditch slow, expensive LLM calls in your agentic systems: TabAgent slashes latency by 95% and cost by up to 91% by swapping generative decision-making for a compact, trained classifier.