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.

翻译：大语言模型（LLM）与人工智能工作负载的飞速发展已将单体硅芯片推至其光罩与经济极限，从而加速了2.5D/3D芯粒系统的应用。然而，这类系统要求跨计算栈（涵盖应用、架构、芯片与封装）多层级协同设计，显著增加了设计复杂度。由此产生的设计空间具有高度组合性，需在延迟、能耗、面积与成本之间进行权衡。为应对这一挑战，我们提出CHICO-Agent——一种面向2.5D/3D芯粒系统的LLM驱动优化框架。该框架维护一个持久化知识库以捕捉参数与结果间的趋势，并通过管理员-领域多智能体工作流协调探索过程。与模拟退火基线相比，CHICO-Agent能发现成本更低的配置，并为设计人员提供可解释的审计追踪。