CHICO-Agent: An LLM Agent for the Cross-layer Optimization of 2.5D and 3D Chiplet-based Systems
It addresses the complex co-design problem in chiplet-based systems for hardware designers, but the improvement over a simple baseline is incremental.
CHICO-Agent is an LLM-driven optimization framework for 2.5D/3D chiplet systems that finds lower-cost configurations compared to simulated annealing, providing an interpretable audit trail for designers.
The rapid growth of large language models (LLMs) and AI workloads has pushed monolithic silicon to its reticle and economic limits, accelerating the adoption of 2.5D/3D chiplet systems. However, these systems increase design complexity by requiring co-design across multiple levels of the computing stack, including application, architecture, chip, and package. The resulting design space is highly combinatorial, with trade-offs among latency, energy, area, and cost. To address this challenge, we propose CHICO-Agent, an LLM-driven optimization framework for 2.5D/3D chiplet-based systems. CHICO-Agent maintains a persistent knowledge base to capture parameter-outcome trends and coordinates exploration through an admin-field multi-agent workflow. Compared with a simulated-annealing baseline, CHICO-Agent finds lower-cost configurations and provides an interpretable audit trail for designers.