Towards Optimal Circuit Generation: Multi-Agent Collaboration Meets Collective Intelligence
Large language models (LLMs) have transformed code generation, yet their application in hardware design produces gate counts 38\%--1075\% higher than human designs. We present CircuitMind, a multi-agent framework that achieves human-competitive efficiency through three key innovations: syntax locking (constraining generation to basic logic gates), retrieval-augmented generation (enabling knowledge-driven design), and dual-reward optimization (balancing correctness with efficiency). To evaluate our approach, we introduce TC-Bench, the first gate-level benchmark harnessing collective intelligence from the TuringComplete ecosystem -- a competitive circuit design platform with hundreds of thousands of players. Experiments show CircuitMind enables 55.6\% of model implementations to match or exceed top-tier human experts in composite efficiency metrics. Most remarkably, our framework elevates the 14B Phi-4 model to outperform both GPT-4o mini and Gemini 2.0 Flash, achieving efficiency comparable to the top 25\% of human experts without requiring specialized training. These innovations establish a new paradigm for hardware optimization where collaborative AI systems leverage collective human expertise to achieve optimal circuit designs. Our model, data, and code are open-source at https://github.com/BUAA-CLab/CircuitMind.
Code (1)
Tasks
Code GenerationRetrieval-augmented GenerationSimilar Papers 제목 키워드 기반
HCQA: Hybrid Classical-Quantum Agent for Generating Optimal Quantum Sensor Circuits
This study proposes an HCQA for designing optimal Quantum Sensor Circuits (QSCs) to address complex quantum physics problems. The HCQA integrates computational intelligence techniques by leveraging a Deep Q-Network (DQN)…
AaLLM: An End-to-End Analog Circuit Design Framework from Topology Generation to Sizing Using Large Language Models
Analog circuit design is a time-consuming, iterative process in a nonlinear and high-dimensional design space that relies heavily on expert intuition. Among recent developments, LLMs have introduced a promising approach …
QUASAR: Quantum Assembly Code Generation Using Tool-Augmented LLMs via Agentic RL
Designing and optimizing task-specific quantum circuits are crucial to leverage the advantage of quantum computing. Recent large language model (LLM)-based quantum circuit generation has emerged as a promising automatic …
Reinforcement LearningCode GenerationOptimal-Agent-Selection: State-Aware Routing Framework for Efficient Multi-Agent Collaboration
The emergence of multi-agent systems powered by large language models (LLMs) has unlocked new frontiers in complex task-solving, enabling diverse agents to integrate unique expertise, collaborate flexibly, and address ch…
A collaboration of multi-agent model using an interactive interface
Multi-agent reinforcement learning algorithms scarcely attend to noisy environments, in which agents are inhibited from achieving optimal policy training and making correct decisions. This work investigates the effect of…
Multi-agent Reinforcement Learning