AGEL-Comp: A Neuro-Symbolic Framework for Compositional Generalization in Interactive Agents

TL;DR

AGEL-Comp is a neuro-symbolic AI framework that enhances compositional generalization in interactive agents by integrating a dynamic world model, symbolic reasoning, and neural verification.

Contribution

This work introduces AGEL-Comp, a novel neuro-symbolic architecture combining a causal program graph, ILP, and neural theorem proving for improved agent reasoning.

Findings

AGEL-Comp outperforms pure LLM-based models in compositional generalization tasks.

The framework enables agents to build interpretable, structured world models.

Evaluation in Retro Quest shows significant performance improvements.

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.