Publications
With our publications we cover the most diverse research areas that arise in the field of man, task and technology. In addition to traditional Business Information Systems topics such as knowledge management and business process management, you will also find articles on current topics such as blended learning, cloud computing or smart grids. Use this overview to get an impression of the range and possibilities of research in Business Information Systems at the University of Duisburg-Essen.
Type of Publication: Article in Collected Edition
AGEL-Comp: A Neuro-Symbolic Framework for Compositional Generalization in Interactive Agents
- Author(s):
- Shahid, Mahnoor; Rothe, Hannes
- Title of Anthology:
- IntelliSys 2026
- Location(s):
- Amsterdam
- Publication Date:
- 2026
- Digital Object Identifier (DOI):
- doi:10.48550/arXiv.2604.26522
- Link to complete version:
- https://arxiv.org/abs/2604.26522
- Citation:
- Download BibTeX
Abstract
Large Language Model (LLM)-based agents exhibit systemic failures in compositional generalization, limiting their robustness in interactive environments. This work introduces AGEL-Comp, a neuro-symbolic AI agent architecture designed to address this challenge by grounding actions of the agent. AGEL-Comp integrates three core innovations: (1) a dynamic Causal Program Graph (CPG) as a world model, representing procedural and causal knowledge as a directed hypergraph; (2) an Inductive Logic Programming (ILP) engine that synthesizes new Horn clauses from experiential feedback, grounding symbolic knowledge through interaction; and (3) a hybrid reasoning core where an LLM proposes a set of candidate sub-goals that are verified for logical consistency by a Neural Theorem Prover (NTP). Together, these components operationalize a deduction--abduction learning cycle: enabling the agent to deduce plans and abductively expand its symbolic world model, while a neural adaptation phase keeps its reasoning engine aligned with new knowledge. We propose an evaluation protocol within the \texttt{Retro Quest} simulation environment to probe for compositional generalization scenarios to evaluate our AGEL agent. Our findings clearly indicate the better performance of our AGEL model over pure LLM-based models. Our framework presents a principled path toward agents that build an explicit, interpretable, and compositionally structured understanding of their world.