Aria: A General Code Agent + Verification Harness Proves All 4,257 Core Iris Lemmas Fully Automatically
A new arXiv paper introduces Aria, which pairs an off-the-shelf code agent (Claude Code on Claude Opus 4.7, driven non-interactively via claude -p) with a declarative verification harness (HHL) instead of a specialized theorem-proving scaffold. Running unattended with zero expert intervention, it proves all 4,257 lemmas of Iris's four core modules, 217 RustBelt lemmas, all 318 reglang lemmas (where prior LLM provers manage ~1 in 8), and 72 not-yet-ported iris-lean lemmas (90.3% first-attempt) — the first time an entire expert-grade concurrent separation-logic library was proved automatically and in full. The lesson for builders: a general agent that reads context and decides its own next step, wrapped in a soundness-checking harness, beats confining models to narrow tactic-prediction roles.
Source
↳ Follow the thread