# Evidence Ledger

ACED-Bench separates natural-language scientific scenarios from hidden probabilistic graphical models so agents must choose observational or interventional experiments within a four-turn budget and commit to causal answers, producing wide spread across models and agent designs on 180 hard tasks while strong agents near ceiling on a 150-question qualification check.

ACED-Bench separates natural-language scientific scenarios from hidden probabilistic graphical models so agents must choose observational or interventional experiments within a four-turn budget and commit to causal answers, producing wide spread across models and agent designs on 180 hard tasks while strong agents near ceiling on a 150-question qualification check.

The authors introduce SafeActBench, 656 cases across six operational domains and five protocols, using a provenance-bound Evidence Ledger and a deterministic trajectory evaluator to check whether tool-using agents establish required evidence before acting; across ten model–harness configurations, strong static action assessment coexists with much weaker interactive execution, failures often begin with incomplete investigation or premature action, single-action execution is usually reliable once evidence is established, and multi-action workflows additionally expose unresolved prerequisites and incomplete execution.

The authors introduce SafeActBench, 656 cases across six operational domains and five protocols, using a provenance-bound Evidence Ledger and a deterministic trajectory evaluator to check whether tool-using agents establish required evidence before acting; across ten model–harness configurations, strong static action assessment coexists with much weaker interactive execution, failures often begin with incomplete investigation or premature action, single-action execution is usually reliable once evidence is established, and multi-action workflows additionally expose unresolved prerequisites and incomplete execution.