# Bayesian Active Learning for Intent Disambiguation in Interactive Robot Planning

arXiv: https://arxiv.org/abs/2609.34270 · HTML: https://mlsanity.com/paper/2609.34270/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 29 references that are in the map.
- First posted on arXiv 28 Sep 2026.

## Builds on (most cited first, 23 of 23)

- [Do As I Can, Not As I Say: Grounding Language in Robotic Affordances](https://mlsanity.com/paper/2204.01691/) (2022)
- [Code as Policies: Language Model Programs for Embodied Control](https://mlsanity.com/paper/2209.07753/) (2022)
- [LLM+P: Empowering Large Language Models with Optimal Planning Proficiency](https://mlsanity.com/paper/2304.11477/) (2023)
- [LLMs Get Lost In Multi-Turn Conversation](https://mlsanity.com/paper/2505.06120/) (2025)
- [Robots That Ask For Help: Uncertainty Alignment for Large Language Model Planners](https://mlsanity.com/paper/2307.01928/) (2023)
- [Control Barrier Function Based Quadratic Programs for Safety Critical Systems](https://mlsanity.com/paper/1609.06408/) (2016)
- [Grammar Variational Autoencoder](https://mlsanity.com/paper/1703.01925/) (2017)
- [On the Self-Verification Limitations of Large Language Models on Reasoning and Planning Tasks](https://mlsanity.com/paper/2402.08115/) (2024)
- [Reward-rational (implicit) choice: A unifying formalism for reward learning](https://mlsanity.com/paper/2002.04833/) (2020)
- [AutoTAMP: Autoregressive Task and Motion Planning with LLMs as Translators and Checkers](https://mlsanity.com/paper/2306.06531/) (2023)
- [NL2TL: Transforming Natural Languages to Temporal Logics using Large Language Models](https://mlsanity.com/paper/2305.07766/) (2023)
- [Overconfidence is Key: Verbalized Uncertainty Evaluation in Large Language and Vision-Language Models](https://mlsanity.com/paper/2405.02917/) (2024)
- [Grounding Complex Natural Language Commands for Temporal Tasks in Unseen Environments](https://mlsanity.com/paper/2302.11649/) (2023)
- [Planning Anything with Rigor: General-Purpose Zero-Shot Planning with LLM-based Formalized Programming](https://mlsanity.com/paper/2410.12112/) (2024)
- [InterPreT: Interactive Predicate Learning from Language Feedback for Generalizable Task Planning](https://mlsanity.com/paper/2405.19758/) (2024)
- [Multi-agent Motion Planning from Signal Temporal Logic Specifications](https://mlsanity.com/paper/2201.05247/) (2022)
- [Preference-Conditioned Language-Guided Abstraction](https://mlsanity.com/paper/2402.03081/) (2024)
- [TeLoGraF: Temporal Logic Planning via Graph-encoded Flow Matching](https://mlsanity.com/paper/2505.00562/) (2025)
- [AmbiK: Dataset of Ambiguous Tasks in Kitchen Environment](https://mlsanity.com/paper/2506.04089/) (2025)
- [Adaptive Language-Guided Abstraction from Contrastive Explanations](https://mlsanity.com/paper/2409.08212/) (2024)
- [MAPLE: A Framework for Active Preference Learning Guided by Large Language Models](https://mlsanity.com/paper/2412.07207/) (2024)
- [Simulation to Rules: A Dual-VLM Framework for Formal Visual Planning](https://mlsanity.com/paper/2510.03182/) (2025)
- [Masked IRL: LLM-Guided Reward Disambiguation from Demonstrations and Language](https://mlsanity.com/paper/2511.14565/) (2025)

## Abstract (arXiv)

Interactive robot planning requires robots to infer and execute human intentions from natural language instructions that are often ambiguous, incomplete, or underspecified. Although large language models (LLMs) provide a powerful interface for clarification, relying on the generative model to drive an multi-turn conversation can introduce systematic failures. We propose a Bayesian framework that treats clarification as an active learning problem over grounded Signal Temporal Logic (STL) task specifications. Our method uses LLMs to initialize candidate formal specifications and translate informative contrasts into natural-language clarification questions, while Bayesian optimization maintains uncertainty estimation over user intent and selects queries that maximize information gain. After convergence, the inferred STL specification is passed to a formal planner to synthesize a verifiable robot trajectory. Across four simulated and real-world task domains, our approach generally achieves higher task satisfaction and requires fewer clarification rounds than LLM baselines, while helping smaller models close the performance gap against larger reasoning models.