Self-Evolving World Models for LLM Agent Planning
- Published
- Source
- arXiv
- Paper number
- 533
- Field
- AI / General
- arXiv ID
- 2606.30639
Key points
- We present a self-evolving world model that changes only deployment-time context without parameter updates.
- Episodic memory uses retrieval-based simulation of real action transitions.
- Semantic memory extracts persistent heuristic rules from prediction-observation mismatches.
- Selective foresight filters low-confidence predictions before integrating them into the agent's reasoning context.
- It achieves the best predictive accuracy across all three backbones on ALFWorld and ScienceWorld.
- Oracle experiments show that noisy foresight harms action accuracy, proving the importance of confidence filtering.
Paper links
External research summaries. These are not HDATF publications or measured product results.