CHICO-Agent: An LLM Agent for the Cross-layer Optimization of 2.5D and 3D Chiplet-based Systems

2026-04-20

AI Summary

Designing 2.5D/3D chiplet systems requires cross-layer co-optimization across application, architecture, die, and package levels to balance latency, energy, area, and cost—a challenge compounded by high-dimensional combinatorial complexity. To address this, this work proposes CHICO-Agent, the first framework to integrate large language model (LLM) agents into chiplet cross-layer optimization. CHICO-Agent employs a manager-domain multi-agent collaboration mechanism coupled with a persistent knowledge base to enable interpretable automated design exploration and auditable decision tracing. Experimental results demonstrate that CHICO-Agent discovers configurations with lower system cost compared to simulated annealing baselines while providing clear provenance of the optimization trajectory.

Technology Category

• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Multiagent Systems: Mechanism Design
• Search and Optimization: Learning to Search

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Search and Retrieval-Augmented AI: Agentic search

Abstract

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.

Problem

• chiplet
• cross-layer optimization
• design complexity
• 2.5D/3D integration
• computing stack co-design

Innovation

• LLM agent
• chiplet-based systems
• cross-layer optimization
• multi-agent workflow
• design space exploration