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

arXiv:2610.06100 · cs.CL · Submitted 2026-10-05 · Read on arXiv

cs.CL

Submitted: 2026-10-05

Updated: 2026-10-05

Code: https://github.com/ruyue0001/trace2env

Terminology

• Trace — 1× in this paper · explained in 2 episodes
• World Model — 1× in this paper · explained in 7 episodes

Sources

• Beyond Next-Observation Prediction: Agent-Authored World Modeling for Sequential Decision Making
• Beyond State Consistency: Behavior Consistency in Text-Based World Models
• CoMAP: Co-Evolving World Models and Agent Policies for LLM Agents
• SkillGen: Verified Inference-Time Agent Skill Synthesis
• Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills
• From Memory to Skills: Evidence-Grounded Co-Evolution Governance for Long-Horizon LLM Agents
• Terminal-Universe: Turning Agent Trajectories into Scalable Terminal Environments
• TraceCompiler: Skill-Guided Mining and Compilation of LLM Agent Traces into Mostly Deterministic Workflows
• Self-Evolving World Models for LLM Agent Planning
• Qwen-AgentWorld: Language World Models for General Agents

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering