Score: 2

QuickLAP: Quick Language-Action Preference Learning for Autonomous Driving Agents

Published: November 22, 2025 | arXiv ID: 2511.17855v1

By: Jordan Abi Nader , David Lee , Nathaniel Dennler and more

BigTech Affiliations: Massachusetts Institute of Technology

Potential Business Impact:

Robots learn faster from what you do and say.

Business Areas:
Natural Language Processing Artificial Intelligence, Data and Analytics, Software

Robots must learn from both what people do and what they say, but either modality alone is often incomplete: physical corrections are grounded but ambiguous in intent, while language expresses high-level goals but lacks physical grounding. We introduce QuickLAP: Quick Language-Action Preference learning, a Bayesian framework that fuses physical and language feedback to infer reward functions in real time. Our key insight is to treat language as a probabilistic observation over the user's latent preferences, clarifying which reward features matter and how physical corrections should be interpreted. QuickLAP uses Large Language Models (LLMs) to extract reward feature attention masks and preference shifts from free-form utterances, which it integrates with physical feedback in a closed-form update rule. This enables fast, real-time, and robust reward learning that handles ambiguous feedback. In a semi-autonomous driving simulator, QuickLAP reduces reward learning error by over 70% compared to physical-only and heuristic multimodal baselines. A 15-participant user study further validates our approach: participants found QuickLAP significantly more understandable and collaborative, and preferred its learned behavior over baselines. Code is available at https://github.com/MIT-CLEAR-Lab/QuickLAP.

Country of Origin
🇺🇸 United States

Repos / Data Links

Page Count
14 pages

Category
Computer Science:
Artificial Intelligence