Tag
The author describes how AI agents can read outdated documents due to lack of lifecycle awareness, and proposes an open specification called OCOM that adds metadata like identity, ownership, lifecycle, and evidence to objects to ensure agents access current information.
Introduces Object-Centric Environment Modeling (OCM), a method that organizes LLM agent experience into two executable code bases (object knowledge and procedure knowledge) to improve reuse, verification, and reduce invalid actions in interactive environments.
OPINE-World introduces an LLM agent that learns an object-centric programmatic world model online through interaction, using ontology-error-prioritized exploration and cooperating hypothesis-test agents, achieving strong results on ARC-AGI-3.
This paper proposes EHHN, an event-driven heterogeneous hypergraph network for object-centric next activity prediction in service processes, achieving state-of-the-art accuracy and memory efficiency on four benchmarks.
An object-centric residual reinforcement learning framework enhances zero-shot sim-to-real transfer for vision-language-action models, improving success rates from 42% to 76% on manipulation tasks without real-world training.
COMET is a model-based reinforcement learning algorithm that combines a frozen object-centric encoder with a transformer-based world model and Monte Carlo Tree Search, using causal attention to focus on task-relevant objects, achieving higher scores on visual RL benchmarks.