2022
Inner Monologue: Embodied Reasoning through Planning with Language Models
Giving robots an inner voice — language models that plan, replan, and talk themselves through a task.
“We propose Inner Monologue, which incorporates language models into embodied agents to enable reasoning through planning and feedback.”
Think out loud, then act
The agent generates an internal narrative: what it intends, what it observes, what went wrong. Language becomes the scratchpad for closed-loop control, not just user-facing chat.
Feedback closes the loop
Success detectors, scene descriptions, and human hints feed back into the monologue. The model replans without a full reset. This is closer to how people recover from failed grasps than one-shot command execution.
With SayCan
Read alongside SayCan: SayCan grounds skill selection in affordances; Inner Monologue adds temporal reasoning and recovery. Both treat the LLM as a planner, not a remote control.
← previous · 2022
Do As I Can, Not As I Say: Grounding Language in Robotic Affordances
next · 2022 →
Training Language Models to Follow Instructions with Human Feedback