Introduces budgeted environment probing for structured belief tables in long-horizon agents, with type-stratified analysis showing reduced terminal world-model error when probes follow task structure.
arXiv preprint arXiv:2510.01531 , 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
-
Ask the World Before Acting: Budgeted Environment Probing for World-Model Calibration
Introduces budgeted environment probing for structured belief tables in long-horizon agents, with type-stratified analysis showing reduced terminal world-model error when probes follow task structure.