LATIDIA · Robótica

REINS: Un sistema de agentes autoevolutivos para la planificación de trayectorias en tiempo real.

arXiv: 2611.10748v1Tipo de anuncio: nuevo Resumen: Los arneses de agente -- andamios de tiempo de ejecución que envuelven el bucle de razonamiento de un LLM con envío de herramientas, verificación y memoria persistente -- se han convertido en el sustrato estándar para dep

La noticia

arXiv:2611.10748v1 Announce Type: new Abstract: Agent harnesses -- runtime scaffolds that wrap an LLM's reasoning loop with tool dispatch, verification, and persistent memory -- have become the standard substrate for deploying LLMs as autonomous agents, as demonstrated by Claude Code and Codex in software engineering. In trajectory planning, however, this paradigm has not taken hold: existing LLM-based trajectory planning methods either keep the LLM in the decision loop, exceeding the millisecond-level control budget, or offload it to offline rules or training-time supervision -- leaving the runtime planner non-evolving. Intermediate hybrids still lack the verification-and-consolidation loop that makes harnesses reliable. We ask: what runtime harness would let an LLM planner meet