Zhuo Zhang(@i2huer):Something to share: we built a benchmark for evaluating agentic reverse engineering. - instead of grading intermediate outputs, e.g., recovered types/names - we evaluate agents e2e on deterministic goals, e.g., JTAG a firmware to enable its debug mode.

Zhuo Zhang

@i2huer

Assistant Professor @ColumbiaCompSci 👉 Binary Analysis 🐱‍💻 ➕ Web3 🦇🔊 👉 Building & in free time ❄️

参加 March 2017

467 フォロー中 2.3K ファン

Zhuo Zhang@i2huer

2026.08.14 02:46

Something to share: we built a benchmark for evaluating agentic reverse engineering. - instead of grading intermediate outputs, e.g., recovered types/names - we evaluate agents e2e on deterministic goals, e.g., JTAG a firmware to enable its debug mode.