From Evidence to Action: How Tool-Using Agents Fail

Excerpt

arXiv:2610.07753v1 Announce Type: new Abstract: Tool-using agents make consequential changes to external state, yet correct outcomes do not guarantee that their actions were supported by evidence established beforehand. We study where this evidence-to-action chain breaks as agents move from deciding whether to act to executing single actions and dependent workflows. Across ten model-harness configurations, strong static action assessment can coexist with much weaker interactive execution. Failur