Object-Centric Environment Modeling for Agentic Tasks

• URL: http://arxiv.org/abs/2607.02846v1
• Date: Fri, 03 Jul 2026 00:49:45 GMT
• Title: Object-Centric Environment Modeling for Agentic Tasks
• Abstract summary: We propose Object-Centric Environment Modeling (OCM), which organizes experience into an executable object-centric environment model.<n>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.<n>OCM achieves the best average rank across benchmarks and reduces invalid actions, demonstrating that agents can benefit from building object-centric environment models.
• Score: 24.702874059340576
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks [43.36285223987099]
  We introduce UniClawBench, the first capability-driven benchmark to evaluate proactive agents in dynamic, real-world settings.<n>UniClawBench is built around five executor model capabilities: Skill Usage, Exploration, Long-Context Reasoning, Multimodal Understanding, and Cross-Platform Coordination.<n>Unlike previous benchmarks that rely on static, pre-recorded answers, our benchmark evaluates agents in live Docker containers using fine-grained, step-by-step completion checkpoints.
  arXiv  Detail & Related papers  (2026-07-09T17:59:32Z)
• Bridging the Agent-World Gap: Text World Models for LLM-based Agents [83.8237017249529]
  Large language model (LLM)-based agents are increasingly used in interactive textual environments.<n>Many remain largely reactive, mapping observations to actions without an explicit model of how these environments are structured and evolve.<n>This motivates text world models (TWMs): transition models over textual states that, given a state and a candidate action, predict the resulting webpage, terminal output, API response, or user reply.<n>We systematically review text world models for LLM-based agents, organized around a formal framework and the agent lifecycle.
  arXiv  Detail & Related papers  (2026-06-08T04:58:52Z)
• Learning POMDP World Models from Observations with Language-Model Priors [52.11151769796862]
  Partially-observable Markov decision processes (POMDPs) provide a flexible modeling class for internal world models.<n>We ask whether language-model priors can reduce costly interaction by leveraging prior knowledge.<n>We show that emphPinductor matches the performance and sample efficiency of LLM-based POMDP learning methods.
  arXiv  Detail & Related papers  (2026-05-13T16:18:15Z)
• Agent World Model: Infinity Synthetic Environments for Agentic Reinforcement Learning [62.499592503950026]
  Large language model (LLM) have empowered autonomous agents to perform complex tasks that require multi-turn interactions with tools and environments.<n>We propose Agent World Model (AWM), a fully synthetic environment generation pipeline.<n>We scale to 1,000 environments covering everyday scenarios, in which agents can interact with rich toolsets.
  arXiv  Detail & Related papers  (2026-02-10T18:55:41Z)
• Code-in-the-Loop Forensics: Agentic Tool Use for Image Forgery Detection [59.04089915447622]
  ForenAgent is an interactive IFD framework that enables MLLMs to autonomously generate, execute, and refine Python-based low-level tools around the detection objective.<n>Inspired by human reasoning, we design a dynamic reasoning loop comprising global perception, local focusing, iterative probing, and holistic adjudication.<n>Experiments show that ForenAgent exhibits emergent tool-use competence and reflective reasoning on challenging IFD tasks.
  arXiv  Detail & Related papers  (2025-12-18T08:38:44Z)
• Learning Interactive World Model for Object-Centric Reinforcement Learning [27.710001478315288]
  We introduce a unified framework that learns structured representations of both objects and their interactions within a world model.<n>FIOC-WM captures environment dynamics with disentangled and modular representations of object interactions.<n>On simulated robotic and embodied-AI benchmarks, FIOC-WM improves policy-learning sample efficiency and generalization over world-model baselines.
  arXiv  Detail & Related papers  (2025-11-04T03:35:58Z)
• MLE-Dojo: Interactive Environments for Empowering LLM Agents in Machine Learning Engineering [57.156093929365255]
  Gym-style framework for systematically reinforcement learning, evaluating, and improving autonomous large language model (LLM) agents.<n>MLE-Dojo covers diverse, open-ended MLE tasks carefully curated to reflect realistic engineering scenarios.<n>Its fully executable environment supports comprehensive agent training via both supervised fine-tuning and reinforcement learning.
  arXiv  Detail & Related papers  (2025-05-12T17:35:43Z)
• Localizing Active Objects from Egocentric Vision with Symbolic World Knowledge [62.981429762309226]
  The ability to actively ground task instructions from an egocentric view is crucial for AI agents to accomplish tasks or assist humans virtually. We propose to improve phrase grounding models' ability on localizing the active objects by: learning the role of objects undergoing change and extracting them accurately from the instructions. We evaluate our framework on Ego4D and Epic-Kitchens datasets.
  arXiv  Detail & Related papers  (2023-10-23T16:14:05Z)
• CGMI: Configurable General Multi-Agent Interaction Framework [0.0]
  General Multi-Agent Interaction (CGMI) framework designed to replicate human interactions in real-world scenarios. We propose a tree-structured methodology for the assignment, detection, and maintenance of agent personality. We have also integrated general agents to augment the virtual environment's realism.
  arXiv  Detail & Related papers  (2023-08-24T02:03:29Z)

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.