A target-blind agent-generated test suite with a consensus-and-validator certification chain found 906 verified accepted-but-buggy submissions on AtCoder and led all baselines on post-cutoff Codeforces problems.
Codet: Code generation with generated tests
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.SE 1years
2026 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Coding Agents as Test-Suite Auditors: Finding What Official Suites Miss While Approaching What They Catch
A target-blind agent-generated test suite with a consensus-and-validator certification chain found 906 verified accepted-but-buggy submissions on AtCoder and led all baselines on post-cutoff Codeforces problems.