From Traces to Agentic Worlds: Agentic Language World Models for Interactive Environment Simulation

Key points

• Realistic environment replicas are increasingly valuable for training and evaluating LLM agents, yet the original systems may be inaccessible or impractical to reproduce.1
• We instantiate this paradigm with Trace2Env, a learning-free framework for settings where the original system is unavailable but historical interaction traces remain accessible.1
• Across nine environments, Trace2Env improves both next-observation fidelity and long-horizon interaction consistency over conventional prompt-based LWMs. In multi-turn interaction, task agent actions generated against Trace2Env remain valid more often when replayed in the real environment, indicating that its simulated dynamics better preserve the consequences of earlier actions across successive turns.1
• These results establish agentic language world modeling as an alternative direction for building realistic environment replicas without reconstructing the original executable system.1

Sources (1)

• [1]From Traces to Agentic Worlds: Agentic Language World Models for Interactive Environment Simulation
  Hugging Face Daily Papers · Oct 5, 12:00 AM

  We explore agentic language world modeling: rather than rebuilding an executable environment, a world model agent serves as the environment for a task agent and supports faithful and stateful simulation.

  Realistic environment replicas are increasingly valuable for training and evaluating LLM agents, yet the original systems may be inaccessible or impractical to reproduce.

Extractive summary: sentences quoted from the sources.