Grounded Iterative Language Planning: How Parameterized World Models Reduce Hallucination Propagation in LLM Agents
An agent-based world model calls an LLM API and reasons flexibly in language, but its errors appear as hallucinated state changes that are hard to score with ordinary regression losses. A parameterized world model is a trained transition predictor; its errors are easier to measure with quantities such as NodeMSE, delta accuracy, and validity accuracy, but it is usually weaker as a standalone planner. We compare these two families on four graph-structured planning benchmarks and introduce operational hallucination metrics for the agent-based case.
- ▪An agent-based world model calls an LLM API and reasons flexibly in language, but its errors appear as hallucinated state changes that are hard to score with ordinary regression losses.
- ▪A parameterized world model is a trained transition predictor; its errors are easier to measure with quantities such as NodeMSE, delta accuracy, and validity accuracy, but it is usually weaker as a standalone planner.
- ▪We compare these two families on four graph-structured planning benchmarks and introduce operational hallucination metrics for the agent-based case.
Opening excerpt (first ~120 words) tap to expand
Computer Science > Artificial Intelligence arXiv:2606.27806 (cs) [Submitted on 26 Jun 2026] Title:Grounded Iterative Language Planning: How Parameterized World Models Reduce Hallucination Propagation in LLM Agents Authors:Xinyuan Song, Zekun Cai View a PDF of the paper titled Grounded Iterative Language Planning: How Parameterized World Models Reduce Hallucination Propagation in LLM Agents, by Xinyuan Song and 1 other authors View PDF HTML (experimental) Abstract:World models for language agents come in two useful forms. An agent-based world model calls an LLM API and reasons flexibly in language, but its errors appear as hallucinated state changes that are hard to score with ordinary regression losses.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at arXiv.org.
Discussion
0 commentsMore from arXiv.org
