AI RESEARCH
BrainMem: Brain-Inspired Evolving Memory for Embodied Agent Task Planning
arXiv CS.CV
•
ArXi:2604.16331v1 Announce Type: cross Embodied task planning requires agents to execute long-horizon, goal-directed actions in complex 3D environments, where success depends on both immediate perception and accumulated experience across tasks. However, most existing LLM-based planners are stateless and reactive, operating without persistent memory and therefore repeating errors and struggling with spatial or temporal dependencies. We propose BrainMem(Brain-Inspired Evolving Memory), a