# Divergent Thoughts toward One Goal: LLM-based Multi-Agent Collaboration System for Electronic Design Automation

arXiv: https://arxiv.org/abs/2502.10857 · HTML: https://mlsanity.com/paper/2502.10857/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 12 of its 26 references that are in the map.
- First posted on arXiv 15 Feb 2025.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)
- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 12 of 12)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs](https://mlsanity.com/paper/2307.16789/) (2023)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [The Rise and Potential of Large Language Model Based Agents: A Survey](https://mlsanity.com/paper/2309.07864/) (2023)
- [MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models](https://mlsanity.com/paper/2309.12284/) (2023)
- [Decomposed Prompting: A Modular Approach for Solving Complex Tasks](https://mlsanity.com/paper/2210.02406/) (2022)
- [Cognitive Architectures for Language Agents](https://mlsanity.com/paper/2309.02427/) (2023)
- [Magicoder: Empowering Code Generation with OSS-Instruct](https://mlsanity.com/paper/2312.02120/) (2023)
- [Unleashing the Emergent Cognitive Synergy in Large Language Models: A Task-Solving Agent through Multi-Persona Self-Collaboration](https://mlsanity.com/paper/2307.05300/) (2023)
- [ChipNeMo: Domain-Adapted LLMs for Chip Design](https://mlsanity.com/paper/2311.00176/) (2023)
- [ChatLLM Network: More brains, More intelligence](https://mlsanity.com/paper/2304.12998/) (2023)

## Built on by (most cited first, 12 of 12)

- [AnalogCoder-Pro: Unifying Analog Circuit Generation and Optimization via Multi-modal LLMs](https://mlsanity.com/paper/2508.02518/) (2025)
- [ORFS-agent: Tool-Using Agents for Chip Design Optimization](https://mlsanity.com/paper/2506.08332/) (2025)
- [BILLY: Steering Large Language Models via Merging Persona Vectors for Creative Generation](https://mlsanity.com/paper/2510.10157/) (2025)
- [Bridging the Last Mile of Circuit Design: PostEDA-Bench, a Hierarchical Benchmark for PPA Convergence and DRC Fixing](https://mlsanity.com/paper/2605.06936/) (2026)
- [MHRC-Bench: A Multilingual Hardware Repository-Level Code Completion benchmark](https://mlsanity.com/paper/2601.03708/) (2026)
- [RefEvo: Agentic Design with Co-Evolutionary Verification for Agile Reference Model Generation](https://mlsanity.com/paper/2604.24218/) (2026)
- [Foundation-Model-Based Agents in Industrial Automation: Purposes, Capabilities, and Open Challenges](https://mlsanity.com/paper/2605.02592/) (2026)
- [Agentic Electronic Design Automation: A Handoff Perspective](https://mlsanity.com/paper/2606.19795/) (2026)
- [AgenticECO: An Agentic Framework for ECO on 3D Integrated Circuits](https://mlsanity.com/paper/2608.03738/) (2026)
- [LLMs in Digital EDA: A perspective on shifting roles from Generation to Orchestration](https://mlsanity.com/paper/2608.27184/) (2026)
- [AstroVLM: Expert Multi-agent Collaborative Reasoning for Astronomical Imaging Quality Diagnosis](https://mlsanity.com/paper/2604.16024/) (2026)
- [Can AI Agents Really Complete RTL-to-GDS? Lessons from Benchmarking Tool-Interactive EDA Workflows](https://mlsanity.com/paper/2607.17528/) (2026)

## Abstract (arXiv)

Recently, with the development of tool-calling capabilities in large language models (LLMs), these models have demonstrated significant potential for automating electronic design automation (EDA) flows by interacting with EDA tool APIs via EDA scripts. However, considering the limited understanding of EDA tools, LLMs face challenges in practical scenarios where diverse interfaces of EDA tools exist across different platforms. Additionally, EDA flow automation often involves intricate, long-chain tool-calling processes, increasing the likelihood of errors in intermediate steps. Any errors will lead to the instability and failure of EDA flow automation. To address these challenges, we introduce EDAid, a multi-agent collaboration system where multiple agents harboring divergent thoughts converge towards a common goal, ensuring reliable and successful EDA flow automation. Specifically, each agent is controlled by ChipLlama models, which are expert LLMs fine-tuned for EDA flow automation. Our experiments demonstrate the state-of-the-art (SOTA) performance of our ChipLlama models and validate the effectiveness of our EDAid in the automation of complex EDA flows, showcasing superior performance compared to single-agent systems.