developer tools
Multi-Agent Repair Keeps the Work That Still Counts
Dittany preserves validated intermediate contributions while repairing unmet conditions, reaching 84.76 percent task accuracy across 9,000 tasks.
Summary
Dittany preserves validated intermediate contributions while repairing unmet conditions, reaching 84.76 percent task accuracy across 9,000 tasks.
A multi-agent run can fail its final requirement even when several intermediate results remain useful. Dittany derives expected contributions and acceptance conditions from the task and method specifications, links them in a contribution graph, and checks which outputs still satisfy their role. It then attempts action-level correction when available inputs suffice or graph-level recovery when dependencies must change. Across 30 applications, six frameworks and 9,000 tasks, the paper reports 88.28 percent failure-detection precision, 79.18 percent recall and 84.76 percent task accuracy—26.74 points above native execution and 21.28 above the strongest tested recovery baseline. Deployment token use remained 17.92 percent above native execution.
Why it matters
Dittany preserves validated intermediate contributions while repairing unmet conditions, reaching 84.76 percent task accuracy across 9,000 tasks.
Limits and context
- A multi-agent run can fail its final requirement even when several intermediate results remain useful.
Key claims
Dittany preserves validated intermediate contributions while repairing unmet conditions, reaching 84.76 percent task accuracy across 9,000 tasks.
Qualification: A multi-agent run can fail its final requirement even when several intermediate results remain useful.
Evidence: source-2026-11-02-007
Sources
- arXiv preprint 2610.42144, original v1arXiv · primary research
Corrections
No corrections have been recorded for this story.