AIChilles: Automatically Uncovering Hidden Weaknesses in AI-Evolved Systems

[Submitted on 14 Jun 2026 (v1), last revised 24 Jun 2026 (this version, v2)]

View PDF HTML (experimental)

Abstract:The computer systems community has recently seen growing interest in AI-driven system evolution, where AI agents iteratively rewrite systems. Frameworks such as AdaEvolve and Engram report 12-60% score improvements over human-designed algorithms. While these results are promising, there are practical concerns if these AI-evolved programs can perform worse on unseen workloads and exhibit scalability regressions. Given the speed and scale of AI-generated code, we need automated mechanisms to uncover such identify hidden weaknesses in AI-evolved systems programs. To this end, we develop AIChilles that takes as input a baseline program $P$ and an AI-evolved program $P’$, AIChilles searches for valid workloads where $P’$ regresses relative to $P$ in correctness, runtime, memory usage, or output quality. To tackle the diversity in system applications, weakness types and potential bugs, AIChilles combines deterministic workload-parameter extraction, agent-based constraint inference, differential oracles, and code-frequency coverage to discover diverse failures. Across five system applications and 30 AI-evolved programs, AIChilles finds 49 distinct hidden weaknesses. We also show that explicitly including AIChilles in the AI-driven development lifecycle can mitigate several of these weaknesses.

Submission history

From: Yajie Zhou [view email]
[v1] Sun, 14 Jun 2026 14:24:25 UTC (524 KB)
[v2] Wed, 24 Jun 2026 16:25:01 UTC (524 KB)