Industry
New research: long-running agents often fail by stopping too early, not because the model can't make progress. We tested 5 harness designs a…
New research: long-running agents often fail by stopping too early, not because the model can't make progress. We tested 5 harness designs across 8 long-horizon coding tasks. Our new orchestration har
New research: long-running agents often fail by stopping too early, not because the model can't make progress. We tested 5 harness designs across 8 long-horizon coding tasks. Our new orchestration harness, Zenith, wins 5/8 at 43% the cost of the strongest baseline.
Source: Emad Mostaque (X) | 2026-05-08