Is Agentic AI Ready for Real-World Hardware Engineering? A Deep Dive with Phoenix-bench

TL;DR

This paper evaluates the transferability of agentic AI systems from software to hardware engineering using a new benchmark, Phoenix-bench, revealing fundamental task differences and the importance of targeted feedback.

Contribution

Introduces Phoenix-bench, a comprehensive hardware engineering benchmark, and provides a systematic evaluation of various agentic AI models highlighting key challenges.

Findings

Hardware bugs propagate differently than software bugs, affecting agent performance.

Failures are concentrated in design control-flow, FSM bugs, and cross-hierarchy signal tracking.

Test case feedback significantly improves bug localization and fixing accuracy.

Abstract

We ask whether agentic AI systems built for software engineering transfer to realistic hardware engineering. Existing hardware LLM benchmarks isolate sub-tasks but none jointly requires repository navigation, hierarchy-aware localization, Electronic Design Automation (EDA) executable verification, and maintenance-style patching. We introduce \textbf{Phoenix-bench}, a synchronized corpus of 511 verified Verilator instances from 114 GitHub repositories, each shipped with the developer patch, design-flow labels, fail-to-pass and pass-to-pass testbenches, and a Docker-pinned EDA environment so resolved-rate differences reflect agent behavior rather than toolchain availability. Using Phoenix-bench we run a uniform evaluation of four commercial agents and eight open-source agentic structures across four LLM backbones, plus two diagnostic interventions (file-level oracle localization and one round of testbench-log feedback). Three findings emerge. (i)~Software and hardware are fundamentally different engineering tasks: the same agent loses 37\% to 58\% from SWE-bench Verified to Phoenix-bench because hardware bugs propagate across parallel instantiated modules through signal flow rather than along a software-style call graph, and software-tuned agents stop at the symptom file instead of tracing back through the instantiation chain. (ii)~Failures concentrate on design control-flow / finite state machine (FSM) bugs, verification testbench bugs, and hard cases that demand cross-hierarchy signal-flow tracking and coordinated multi-file edits. (iii)~Localization granularity matters far more than localization itself: a perfect file-level oracle yields only $+1.4$\% because the agent then breaks files that did not need editing, while a single round of test case feedback lifts resolved rate by $42$\% to $45$\% because the test case tells \emph{where} the bug is and \emph{what} the fix has to look like.