Ask the World Before Acting: Environment Probing for Calibrated Agent World Models
Language agents acting over long horizons must maintain beliefs about tool states, object locations, graph edges, and subgoal dependencies. When these beliefs drift, failures can be fixed neither by longer reasoning traces nor by ordinary self-reflection, since the missing evidence lies in the environment. We formulate environment probing as a budgeted decision problem for structured agent world models: before acting, the agent may query the current value of one belief field, update its table, and pay one interaction step. We introduce EnvProbe, a simple scoring policy that combines task criticality, staleness, verbalized uncertainty, and dependency role. A type-stratified analysis separa...
| Authors | Xinyuan Song, Zekun Cai |
|---|---|
| Primary category | cs.AI |
| Published | 30 June 2026 |
| Last updated at source | 5 July 2026 |
Connected in the knowledge graph
- caiovicentino1/Ekbasis-27BModel · cited by
Models and datasets referencing this paper
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.