LATIDIA · Investigación

Viaje de regreso para avanzar: exploración retrospectiva y evolución para agentes de largo horizonte

arXiv: 2610.13058v1Tipo de anuncio: nuevo Resumen: Los agentes de modelos de lenguaje grandes operan cada vez más en entornos de horizonte largo donde los errores tempranos pueden desencadenar fallas en cascada y atrapar a los agentes en trayectorias sin salida.

La noticia

arXiv:2610.13058v1 Announce Type: new Abstract: Large language model agents increasingly operate in long-horizon environments where early mistakes can trigger cascading failures and trap agents in dead-end trajectories. Agents must therefore be able to proactively recover from such states and turn their exploratory experience into guidance for subsequent decisions. We introduce ReTRAIL, a framework that enables agents to rewind the environment to earlier states while preserving valid progress and carrying forward knowledge learned from abandoned exploration. The environment state moves backward while the agent's knowledge continues to move forward. ReTRAIL trains a shared policy with two complementary signals: State-Anchored GRPO compares alternative continuations from revisited states to improve execution, while a