Object-Centric Environment Modeling for Agentic Tasks
Quick Answer
This paper shows that The Object-Centric Environment Modeling (OCM) framework enhances LLM agents by structuring experience into executable object-centric models, improving interaction efficiency and reducing invalid actions.
Quick Take
OCM maintains two interconnected knowledge bases and updates them after each episode, leading to superior performance across benchmarks.
Key Points
- OCM organizes agent experience into an executable object-centric model.
- It maintains object knowledge as Python classes and reusable interaction patterns.
- After each episode, OCM updates knowledge bases and verifies procedure execution.
- Experiments show OCM achieves the best average rank across benchmarks.
- OCM reduces invalid actions, demonstrating improved agent performance.
Paper Resources
📖 Reader Mode
~2 min readAbstract: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.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2607.02846 [cs.AI] |
| (or arXiv:2607.02846v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2607.02846 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Yiyang Li [view email]
[v1]
Fri, 3 Jul 2026 00:49:45 UTC (1,550 KB)
— Originally published at arxiv.org
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.AI
See more →HOBA: Hierarchical On-Policy Bidding Agents for Adaptive Online Advertising
HOBA (Hierarchical On-policy Bidding Agents) is a novel hierarchical reinforcement learning framework that enhances online advertising bidding systems by improving adaptability and reducing hyperparameter tuning costs. It utilizes a for hyperparameter inference, a SARSA agent for expert model selection, and a dynamic expert pool for bid execution, achieving a +3.6% increase in target cost during large-scale deployment and outperforming state-of-the-art baselines on AuctionNet.