Do AI Agents Understand Computer Architecture?

arXiv:2609.19387 · cs.AI, cs.AR · Submitted 2026-09-16 · Read on arXiv

cs.AI, cs.AR

Submitted: 2026-09-16

Updated: 2026-09-16

Comments: 10 pages, 3 figures, 3 tables

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Actor — 39× in this paper · explained in 3 episodes
• Core — 7× in this paper · explained in 2 episodes
• Decode — 5× in this paper · explained in 2 episodes
• AI Agents — 4× in this paper · explained in 2 episodes
• Ablation — 2× in this paper · explained in 1 episode
• Physical Constraints — 2× in this paper · explained in 7 episodes
• Regret — 2× in this paper · explained in 3 episodes
• Archetype — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 3 episodes

Sources

• Are Language Models Up to Sequential Optimization Problems? From Evaluation to a Hegelian-Inspired Enhancement
• Can Reasoning Models Reason about Hardware? An Agentic HLS Perspective
• gem5 Co-Pilot: AI Assistant Agent for Architectural Design Space Exploration
• ArchEval: Measuring AI Agents as Computer Architects
• MicroEvo: Knowledge-Guided LLM Sampling for Efficient Microarchitecture Design Space Exploration
• CAKE: Compiler-Agent Co-Design for Frontier Kernel Evolution
• LUMINA: LLM-Guided GPU Architecture Exploration via Bottleneck Analysis

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
• VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection