cs.AINov 13, 2026

Generated Evaluation Suites as Diversity-Driven Search for Real Agent Regressions

Authors: Pulkit Yadav

Organizations: Independent Researcher

Abstract

Generating an evaluation suite from an agent's specification is diversity-driven search: a generator fills a descriptor space (requirements ×\times personas ×\times scenario kinds), and the suite it emits is an archive, then scored like a benchmark by its mean pass rate, which throws away the search's product. We inject 7 controlled defects into a τ2τ^2-bench agent across two domains. Coverage yields a ceiling: if a defect's traced footprint holds bb scenarios that pass at baseline, it can itself contribute at most b/Nb/N to a suite of NN. For 4 of 5 traceable defects that ceiling lies at or below the detection threshold θ=0.10θ= 0.10, so no within-footprint effect can move the suite past it; in both domains the tool-removal defect destroys every covered scenario it can (exactly its ceiling) while the suite-level pass rate moves the other way. Defects split into two regimes: trace-aligned ones, where per-cell scoring recovers the tool-removal defect in full and reveals a second as a significant improvement, and trace-orthogonal ones, whose footprint is behavioural: forced escalation is detected in retail at a traced coverage of exactly zero. Diversity along the generator's own axes helps only where it aligns: at fixed suite size a happy-path-only suite detects nothing, while a kind-diverse one detects the orchestration defect in 5 of 20 draws. Evaluation archives should be scored per cell and should publish coverage as a first-class property.

Figures & tables

Appendix figures & tables5 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Groundability, Not Scale Alone: When Weak Reviewers Can Audit Strong Coding Agents

    Oct 1, 2026Junyu Guo, Shangding Gu, Ming Jin +1AI Agent AuditingCode Generation Evaluation

  2. CoverSynth: Coverage-Guided Generation of Retrieval Evaluation Sets

    Oct 11, 2026Anahita Sharma, Apaar Shanker, Rishav Chakravarti +6Synthetic Benchmark GenerationIR Evaluation