WorldEvolver uses episodic memory, semantic memory, and selective foresight to self-evolve world models at test time, achieving top prediction accuracy and agent success on ALFWorld and ScienceWorld benchmarks.
arXiv preprint arXiv:2602.06130 , year=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Self-Evolving World Models for LLM Agent Planning
WorldEvolver uses episodic memory, semantic memory, and selective foresight to self-evolve world models at test time, achieving top prediction accuracy and agent success on ALFWorld and ScienceWorld benchmarks.