Object-Centric Environment Modeling for Agentic Tasks

2026-07-03Artificial Intelligence

Artificial Intelligence
AI summary

The authors propose a way for AI language model agents to better understand and interact with their environment by organizing their experiences as object-focused computer programs. Their method, called Object-Centric Environment Modeling (OCM), keeps two connected sets of knowledge: one about objects and their properties, and another about how to interact with them using reusable procedures. After each interaction, the system updates and checks these knowledge bases to improve accuracy and efficiency. Their experiments show that this approach helps agents perform better and avoid mistakes.

large language modelsobject-centric modelingenvironment modelingexecutable knowledgeprocedural knowledgeonline learningagent interactioncode verificationprogressive knowledge disclosure
Authors
Yiyang Li, Tianyi Ma, Zehong Wang, Yijun Ma, Yanfang Ye
Abstract
Large language model (LLM) agents can improve through accumulated experience, but free-form textual memories become difficult to maintain, validate, and reuse as interactions grow. Recent symbolic approaches learn executable skills or programmatic world models, yet often store local procedures or assume simplified dynamics. We propose Object-Centric Environment Modeling (OCM), which organizes experience into an executable object-centric environment model. OCM maintains two connected code bases: object knowledge, which defines environment entities and mechanisms as Python classes, and procedure knowledge, which records reusable interaction patterns that must import and use the object model. OCM works in an online setting: after each episode, OCM reflects on the trajectory, updates both knowledge bases, and verifies that all procedures execute against the updated object model. During future interaction, the agent uses progressive knowledge disclosure to inspect compact code signatures first and read source code only when needed. Experiments show that OCM achieves the best average rank across benchmarks and reduces invalid actions, demonstrating that agents can benefit from building object-centric environment models.