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

• URL: http://arxiv.org/abs/2604.26522v1
• Date: Wed, 29 Apr 2026 10:42:02 GMT
• Title: AGEL-Comp: A Neuro-Symbolic Framework for Compositional Generalization in Interactive Agents
• Abstract summary: Large Language Model (LLM)-based agents exhibit systemic failures in compositional generalization, limiting their robustness in interactive environments.<n>This work introduces AGEL-Comp, a neuro-symbolic AI agent architecture designed to address this challenge by grounding actions of the agent.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• KAST-BAR: Knowledge-Anchored Semantically-Dynamic Topology Brain Autoregressive Modeling for Universal Neural Interpretation [5.377333017300534]
  We propose a Knowledge-Anchored Semantically-Dynamic Topology Brain Autoregressive Model (KAST-BAR)<n>KAST-BAR dynamically aligns physiological representations derived from multi-level brain topology with an expert-level semantic space.<n>By large-scale pre-training on 21 diverse datasets, KAST-BAR effectively integrates expert-level medical knowledge into EEG signal representations.
  arXiv  Detail & Related papers  (2026-05-13T08:02:59Z)
• Beyond the Academic Monoculture: A Unified Framework and Industrial Perspective for Attributed Graph Clustering [75.50670592447219]
  Attributed Graph Clustering (AGC) is a fundamental unsupervised task that partitions nodes into cohesive groups by jointly modeling structural topology and node attributes.<n>This survey provides a comprehensive, industrially grounded review of AGC from three complementary perspectives.
  arXiv  Detail & Related papers  (2026-03-21T14:15:34Z)
• Toward Formalizing LLM-Based Agent Designs through Structural Context Modeling and Semantic Dynamics Analysis [13.919694566467053]
  We argue that this fragmentation stems from the absence of an analyzable, self-consistent formal model that enables characterization and comparison of LLM agents.<n>To address this gap, we propose the texttt Structural Context Model, a formal model for analyzing and comparing LLM agents from the perspective of context structure.<n>We demonstrate the effectiveness of the complete framework on dynamic variants of the monkey-banana problem, where agents engineered using our approach achieve up to a 32 percentage points improvement in success rate.
  arXiv  Detail & Related papers  (2026-02-09T05:15:11Z)
• Agentic Reasoning for Large Language Models [122.81018455095999]
  Reasoning is a fundamental cognitive process underlying inference, problem-solving, and decision-making.<n>Large language models (LLMs) demonstrate strong reasoning capabilities in closed-world settings, but struggle in open-ended and dynamic environments.<n>Agentic reasoning marks a paradigm shift by reframing LLMs as autonomous agents that plan, act, and learn through continual interaction.
  arXiv  Detail & Related papers  (2026-01-18T18:58:23Z)
• Beyond Pipelines: A Survey of the Paradigm Shift toward Model-Native Agentic AI [27.209787026732972]
  The rapid evolution of agentic AI marks a new phase in artificial intelligence.<n>This survey traces the paradigm shift in building agentic AI.<n>It examines how each capability has evolved from externally scripted modules to end-to-end learned behaviors.
  arXiv  Detail & Related papers  (2025-10-19T05:23:43Z)
• The Landscape of Agentic Reinforcement Learning for LLMs: A Survey [103.32591749156416]
  The emergence of agentic reinforcement learning (Agentic RL) marks a paradigm shift from conventional reinforcement learning applied to large language models (LLM RL)<n>This survey formalizes this conceptual shift by contrasting the degenerate single-step Markov Decision Processes (MDPs) of LLM-RL with the temporally extended, partially observable Markov decision processes (POMDPs) that define Agentic RL.
  arXiv  Detail & Related papers  (2025-09-02T17:46:26Z)
• Topological Structure Learning Should Be A Research Priority for LLM-Based Multi-Agent Systems [69.95482609893236]
  Large Language Model-based Multi-Agent Systems (MASs) have emerged as a powerful paradigm for tackling complex tasks through collaborative intelligence.<n>We call for a paradigm shift toward emphtopology-aware MASs that explicitly model and dynamically optimize the structure of inter-agent interactions.
  arXiv  Detail & Related papers  (2025-05-28T15:20:09Z)
• Controlled Agentic Planning & Reasoning for Mechanism Synthesis [18.8323743697237]
  This work presents a dual-agent acllm-based reasoning framework for automated planar mechanism synthesis.<n>From a natural-language task description, the system composes symbolic constraints and equations, generates and parametrises simulation code, and iteratively refines designs via critic-driven feedback.
  arXiv  Detail & Related papers  (2025-05-23T08:16:32Z)
• Modeling Unseen Environments with Language-guided Composable Causal Components in Reinforcement Learning [15.594198876509628]
  We introduce World Modeling with Compositional Causal Components (WM3C)<n>This framework enhances reinforcement learning by learning and leveraging causal components.<n>Our approach integrates language as a compositional modality to decompose the latent space into meaningful components.
  arXiv  Detail & Related papers  (2025-05-13T09:08:28Z)
• Entropy-Regularized Token-Level Policy Optimization for Language Agent Reinforcement [67.1393112206885]
  Large Language Models (LLMs) have shown promise as intelligent agents in interactive decision-making tasks. We introduce Entropy-Regularized Token-level Policy Optimization (ETPO), an entropy-augmented RL method tailored for optimizing LLMs at the token level. We assess the effectiveness of ETPO within a simulated environment that models data science code generation as a series of multi-step interactive tasks.
  arXiv  Detail & Related papers  (2024-02-09T07:45:26Z)
• Synergistic Integration of Large Language Models and Cognitive Architectures for Robust AI: An Exploratory Analysis [12.9222727028798]
  This paper explores the integration of two AI subdisciplines employed in the development of artificial agents that exhibit intelligent behavior: Large Language Models (LLMs) and Cognitive Architectures (CAs) We present three integration approaches, each grounded in theoretical models and supported by preliminary empirical evidence. These approaches aim to harness the strengths of both LLMs and CAs, while mitigating their weaknesses, thereby advancing the development of more robust AI systems.
  arXiv  Detail & Related papers  (2023-08-18T21:42:47Z)
• elBERto: Self-supervised Commonsense Learning for Question Answering [131.51059870970616]
  We propose a Self-supervised Bidirectional Representation Learning of Commonsense framework, which is compatible with off-the-shelf QA model architectures. The framework comprises five self-supervised tasks to force the model to fully exploit the additional training signals from contexts containing rich commonsense. elBERto achieves substantial improvements on out-of-paragraph and no-effect questions where simple lexical similarity comparison does not help.
  arXiv  Detail & Related papers  (2022-03-17T16:23:45Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.