Skip to main content
Paperroboticsv1.0

Inner Monologue: Embodied Reasoning through Planning with Language Models

by Google / Everyday Robots · free · Last verified 2026-03-17

Inner Monologue incorporates closed-loop language feedback from the environment—scene descriptions, success detectors, and human feedback—into robotic planning, enabling robots to re-plan dynamically when steps fail. The paper shows that rich language-based feedback loops significantly improve task success rates over open-loop LLM planners.

https://arxiv.org/abs/2207.05608
B
BAbove Average
Adoption: BQuality: AFreshness: B+Citations: B+Engagement: F

Specifications

License
Open Access
Pricing
free
Capabilities
closed-loop-planning, dynamic-re-planning, feedback-integration, language-reasoning
Integrations
Use Cases
robotic-manipulation, adaptive-task-execution, failure-recovery
API Available
No
Tags
robotics, reasoning, planning, language-models, closed-loop
Added
2026-03-17
Completeness
100%

Index Score

61
Adoption
65
Quality
85
Freshness
72
Citations
72
Engagement
0

Put AI to work for your business

Deploy this paper alongside autonomous AaaS agents that handle tasks end-to-end — no babysitting required.

Explore the full AI ecosystem on Agents as a Service