diff --git a/README.md b/README.md
index e28be17..c4c2429 100644
--- a/README.md
+++ b/README.md
@@ -86,6 +86,7 @@ Academic and community-maintained collections.
 - [LiveBench](https://livebench.ai/) — ICLR 2025 Spotlight. Continuously updated LLM benchmark
 - [Terminal-Bench](https://arxiv.org/abs/2506) — Benchmarking agents on hard, realistic CLI tasks (arXiv 2026)
 - [SWE-PolyBench](https://github.com/) — Multi-language benchmark for repository-level evaluation of coding agents
+- [Agent QA](https://github.com/vostride/agent-qa) — Application-level web/mobile regression checks for software produced by coding agents; retains failure evidence but does not score agent trajectories
 
 ---