RoleWorld: Knowledge Transfer in World Modeling with Functional Role Abstractions

Key points

• World models enable large language model (LLM) agents to anticipate action effects and make informed decisions.1
• For generalization, it is desirable for such world models to transfer efficiently to new environments with similar interaction structure and underlying dynamics.1
• Recent approaches encode world dynamics as symbolic rules or executable programs, whose compositional structure in principle affords transfer, but still organize such knowledge around environment-specific objects.1
• Experiments on MARS benchmark show that RoleWorld enables robust generalization across environments with significantly altered object behavior, suggesting that functional role abstractions can serve as an effective component for knowledge transfer in world modeling.1

Sources (1)

• [1]RoleWorld: Knowledge Transfer in World Modeling with Functional Role Abstractions
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 9, 07:58 AM

  To address this limitation, we introduce RoleWorld, a symbolic world modeling approach which uses reusable prototypes and environment-specific parameter values as functional role abstractions to represent how objects behave in interactions.

  World models enable large language model (LLM) agents to anticipate action effects and make informed decisions.

Extractive summary: sentences quoted from the sources.