AGEL-Comp: A Neuro-Symbolic Framework for Compositional Generalization in Interactive Agents
This work tackles the problem of compositional generalization in interactive AI agents, which is a known bottleneck for LLM-based systems, but the improvements are demonstrated only in a specific simulation environment.
AGEL-Comp addresses compositional generalization failures in LLM-based agents by integrating a dynamic Causal Program Graph, Inductive Logic Programming, and a hybrid reasoning core. The framework outperforms pure LLM-based models in the Retro Quest simulation environment.
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.