Sergio Hernández-Gutiérrez
@sergio-hernández-gutiérrez · 1 works
AI researcher working on reward modeling and long-horizon learning for language model agents.
Recent posts by Sergio Hernández-Gutiérrez
- QVal: Cheaply Evaluating Dense Supervision Signals for Long-Horizon LLM Agents - LLM agents increasingly act over long horizons, where a single trajectory can contain hundreds or thousands of actions. In these settings, outcome-only rewards provide too sparse guidance, failing… · Paper · arxiv.org
Topics Sergio Hernández-Gutiérrez posts about
- DSPy on Instagram - 1 post · Best DSPy creators
- AI Models on Instagram - 1 post · Best AI Models creators