Skip to content

Read-only version: For security reasons, the Research Information System (FIS) has been temporarily replaced by this read-only version. All public content and full texts remain available; login, editing, submission and statistics are not available. Questions: fis@uni-bamberg.de

Home › Publications › Script-Based Dialog Policy Planning for LLM-Powered Conversational Agents : A Basic Architecture for an "AI Therapist"

Publication

Script-Based Dialog Policy Planning for LLM-Powered Conversational Agents : A Basic Architecture for an "AI Therapist"

Wasenmüller, Robert; Hilbert, Kevin; Benzmüller, Christoph (2024): Script-Based Dialog Policy Planning for LLM-Powered Conversational Agents : A Basic Architecture for an „AI Therapist“, in: arXiv, doi: 10.48550/arxiv.2412.15242.

Details

Faculty/Chair
Faculty/Professorship
Author
Wasenmüller, Robert
Hilbert, Kevin
Publisher Information
arXiv
Year of publication
2024
Pages
9
Language
English
DOI
Abstract

Large Language Model (LLM)-Powered Conversational Agents have the potential to provide users with scaled behavioral healthcare support, and potentially even deliver full-scale "AI therapy'" in the future. While such agents can already conduct fluent and proactive emotional support conversations, they inherently lack the ability to (a) consistently and reliably act by predefined rules to align their conversation with an overarching therapeutic concept and (b) make their decision paths inspectable for risk management and clinical evaluation -- both essential requirements for an "AI Therapist".

In this work, we introduce a novel paradigm for dialog policy planning in conversational agents enabling them to (a) act according to an expert-written "script" that outlines the therapeutic approach and (b) explicitly transition through a finite set of states over the course of the conversation. The script acts as a deterministic component, constraining the LLM's behavior in desirable ways and establishing a basic architecture for an AI Therapist.

We implement two variants of Script-Based Dialog Policy Planning using different prompting techniques and synthesize a total of 100 conversations with LLM-simulated patients. The results demonstrate the feasibility of this new technology and provide insights into the efficiency and effectiveness of different implementation variants.

Keywords
Large Language Model (LLM)
Type
Preprint
URI
Activation date
2025-01-09

Permalink: https://fis.uni-bamberg.de/handle/uniba/105541 · Data as JSON · Cite: BibTeX · RIS

Data as of: 2026-11-15

Restricted read-only access: login, editing and submission are temporarily disabled.