A systematic review of text world models as transition predictors for LLM agents, organized by foundations, construction methods, applications in planning/training, and evaluation.
Proceedings of the ACM Web Conference 2026 , pages =
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Bridging the Agent-World Gap: Text World Models for LLM-based Agents
A systematic review of text world models as transition predictors for LLM agents, organized by foundations, construction methods, applications in planning/training, and evaluation.