![[2410.13957] Goal Inference from Open-Ended Dialog](https://arxiv.org/static/browse/0.3.4/images/arxiv-logo-fb.png){kind=logo}
[2410.13957] Goal Inference from Open-Ended Dialog
Summary
The paper discusses a method for embodied AI agents to infer user goals from open-ended dialogues using Large Language Models (LLMs), emphasizing goal extraction and uncertainty quantification.
Why It Matters
As AI agents become more integrated into daily tasks, understanding user goals through natural language is crucial for enhancing user experience and efficiency. This research addresses the challenge of accurately interpreting user intentions in dynamic conversations, which is vital for the development of responsive AI systems.
Key Takeaways
- Embodied AI agents can learn user goals from natural language dialogues.
- Quantifying uncertainty in goal inference enhances decision-making.
- The proposed online method offers efficiency compared to traditional offline methods like RLHF.
- Bayesian inference is utilized to manage complex goal representations.
- The approach is validated in practical scenarios like grocery shopping and robotics.
Computer Science > Artificial Intelligence arXiv:2410.13957 (cs) [Submitted on 17 Oct 2024 (v1), last revised 19 Feb 2026 (this version, v2)] Title:Goal Inference from Open-Ended Dialog Authors:Rachel Ma, Jingyi Qu, Andreea Bobu, Dylan Hadfield-Menell View a PDF of the paper titled Goal Inference from Open-Ended Dialog, by Rachel Ma and 3 other authors View PDF HTML (experimental) Abstract:Embodied AI Agents are quickly becoming important and common tools in society. These embodied agents should be able to learn about and accomplish a wide range of user goals and preferences efficiently and robustly. Large Language Models (LLMs) are often used as they allow for opportunities for rich and open-ended dialog type interaction between the human and agent to accomplish tasks according to human preferences. In this thesis, we argue that for embodied agents that deal with open-ended dialog during task assistance: 1) AI Agents should extract goals from conversations in the form of Natural Language (NL) to be better at capturing human preferences as it is intuitive for humans to communicate their preferences on tasks to agents through natural language. 2) AI Agents should quantify/maintain uncertainty about these goals to ensure that actions are being taken according to goals that the agent is extremely certain about. We present an online method for embodied agents to learn and accomplish diverse user goals. While offline methods like RLHF can represent various goals but require lar...