Ask the World Before Acting: Budgeted Environment Probing for World-Model Calibration

arXiv 2026 29.6 method

TLDR

Introduces budgeted environment probing to calibrate language agents' world models before action, with type-stratified analysis and controlled experiments.

Reasoning

Strengths include a novel framing of environment interaction as a calibration resource and a structured analysis of procedural vs. spatial beliefs. Weaknesses are the limited scope to structured belief tables and lack of evidence for real-world generalization or complex environments.

Read-first score

Read-first score 29.6, weighted from topical fit, citation, graph, method, reproducibility, and recency signals. Original total remains 27.

Recency 6%

100

Uses a gentle age decay so recent papers surface without erasing older foundations. 2026

Methodology quality 18%

Screens visible abstract and analysis fields for experiment, dataset, baseline, metric, and limitation evidence. markers=analysis,experiment

Topical relevance 29%

38.6

Uses existing LLM keyword relevance scores normalized to 0-100. world model,world simulator,generative world model,interactive world model,video world model,world dynamics prediction,model-based reinforcement learning world model

Reproducibility 18%

Screens links and visible text for paper, code, dataset, artifact, and repository signals. pdf=True; code=False; dataset=False; markers=none

Citation impact 18%

Uses OpenAlex-shaped citation metadata as a bibliometric attention signal, separate from paper quality. cited_by_count=0

Citation velocity 12%

Citation velocity estimates citations per publication-year to reduce old-paper bias. velocity=0.00

Field roles

Frontier

Rank sensitivity

Stability: volatile; rank range: 114.

Keyword Scores

world model

interactive world model

world dynamics prediction

model-based reinforcement learning world model

world simulator

generative world model

video world model

Resources

Paper