DENSE turns agent traces into feedback without outcome labels
DENSE lets agents reuse evidence from earlier attempts without needing a post-hoc success label or expert annotation, improving reruns while using fewer recipient tokens. It builds nested shortcut trees that compress repeated attempts, preserve local progress and recovery evidence, and expand unresolved requirements for a fresh attempt. On Terminal-Bench 2.1, it had the highest strict pass rate among tested non-privileged feedback methods across four recipient models, raising pass rates by 7.12 to 15.64 percentage points while reducing observed recipient tokens by 19.0% to 43.6%.