AgentDSE: Reasoning-Augmented Architectural Design Space Exploration
For computer architects, AgentDSE dramatically reduces the cost of design space exploration by replacing black-box optimization with interpretable, reasoning-driven search.
AgentDSE uses an LLM coding agent to automate architectural reasoning in design space exploration, achieving competitive or better design quality with up to 100x fewer simulator evaluations across DNN accelerator mapping, HW/SW co-design, and CPU cache optimization.
Traditional architectural design space exploration (DSE) is highly inefficient, typically requiring tens of thousands of simulator evaluations across various optimization methods. This inefficiency arises because conventional methods treat the simulator as a black-box oracle. In contrast, human architects effectively guide exploration by reasoning through physical constraints, performance bottlenecks, data reuse, and workload structures. To bridge this gap, we introduce AgentDSE, a simulator-in-the-loop methodology driven by a general-purpose large language model (LLM) coding agent. AgentDSE automates this architectural-reasoning loop without requiring model fine-tuning, precomputed design databases, or domain-specific optimizer code. Across deep neural network (DNN) accelerator mapping, hardware/software co-design, and CPU cache-hierarchy optimization, AgentDSE achieves competitive or better design quality with up to two orders of magnitude fewer evaluations. AgentDSE also produces inspectable traces that surface architectural hypotheses, performance cliffs, implicit priors, and simulator artifacts, making every search decision traceable rather than buried in optimizer state.