{"slug": "grounded-iterative-language-planning-how-parameterized-world-models-reduce-in", "title": "Grounded Iterative Language Planning: How Parameterized World Models Reduce Hallucination Propagation in LLM Agents", "summary": "Researchers introduced Grounded Iterative Language Planning (GILP), a hybrid method combining a small parameterized world model with LLM-based agent reasoning, reducing hallucinated-state rates from 0.176 to 0.035 on graph-structured planning benchmarks and boosting success rates from 0.668 to 0.838 with only 22% extra LLM calls.", "body_md": "arXiv:2606.27806v1 Announce Type: new\nAbstract: 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. 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. The comparison motivates \\textbf{Grounded Iterative Language Planning} (GILP), which trains only a small parameterized backbone and combines it with API-based agent reasoning. The backbone supplies valid actions, predicted state deltas, risk, and value; the LLM drafts an action and imagined delta; and a consistency gate asks for revision when the two disagree. On real GPT-4o-mini calls, GILP reduces hallucinated-state rate from 0.176 to 0.035. In calibrated simulator ablations, it raises success from 0.668 to 0.838 while adding only ~22% extra LLM calls.", "url": "https://wpnews.pro/news/grounded-iterative-language-planning-how-parameterized-world-models-reduce-in", "canonical_source": "https://arxiv.org/abs/2606.27806", "published_at": "2026-06-29 04:00:00+00:00", "updated_at": "2026-06-29 04:11:13.318343+00:00", "lang": "en", "topics": ["large-language-models", "ai-agents", "machine-learning", "ai-research"], "entities": ["GPT-4o-mini", "OpenAI"], "alternates": {"html": "https://wpnews.pro/news/grounded-iterative-language-planning-how-parameterized-world-models-reduce-in", "markdown": "https://wpnews.pro/news/grounded-iterative-language-planning-how-parameterized-world-models-reduce-in.md", "text": "https://wpnews.pro/news/grounded-iterative-language-planning-how-parameterized-world-models-reduce-in.txt", "jsonld": "https://wpnews.pro/news/grounded-iterative-language-planning-how-parameterized-world-models-reduce-in.jsonld"}}