{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T09:02:36Z","timestamp":1783069356225,"version":"3.54.6"},"reference-count":49,"publisher":"Association for Computing Machinery (ACM)","issue":"2","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["92373207"],"award-info":[{"award-number":["92373207"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Des. Autom. Electron. Syst."],"published-print":{"date-parts":[[2026,3,31]]},"abstract":"<jats:p>Processors serve as the cornerstone of modern computing systems. Although processor design encompasses multiple VLSI levels, the architectural design plays a critical role in determining performance, power consumption, and area efficiency. To address the growing pressure to shorten chip time-to-market, there is an increasing demand for rapid iteration methods in processor architecture development. To achieve efficient and effortless architecture design optimization, we develop ChatArch, a knowledge-driven graph-of-thought multi-LLM-agent framework for processor architecture optimization. Based on processor architecture expertise, we decompose the processor architecture design space and construct an LLM agent graph-of-thought framework to characterize and iteratively optimize these subspaces. Also, by systematically consolidating domain-specific knowledge and empirical design principles validated by experts, we establish a comprehensive RISC-V processor design knowledge repository. Moreover, a knowledge-driven multi-agent framework is developed to enable efficient microarchitecture optimization. Finally, the optimized microarchitecture modules aggregate to form system-level designs. This methodology achieves automated iterative optimization of microarchitectures targeting PPA objectives while generating corresponding behavioral models. The experiments demonstrate that our method effectively designs behavioral processor models, with LLM-generated architectures achieving a validation success rate of over 97.39%, surpassing the performance of other LLMs, including GPT-4o. ChatArch consistently meets requirements, delivering up to 9.97% times better PPA and 32\u201368x efficiency gains compared with traditional black-box optimization methods.<\/jats:p>","DOI":"10.1145\/3774888","type":"journal-article","created":{"date-parts":[[2025,11,13]],"date-time":"2025-11-13T11:30:17Z","timestamp":1763033417000},"page":"1-26","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["ChatArch: A Knowledge-driven Graph-of-thought LLM Framework for Processor Architecture Optimization"],"prefix":"10.1145","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-9726-104X","authenticated-orcid":false,"given":"Zheng","family":"Wu","sequence":"first","affiliation":[{"name":"Fudan University","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-7660-587X","authenticated-orcid":false,"given":"Zhuochu","family":"Yang","sequence":"additional","affiliation":[{"name":"Fudan University","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-7328-957X","authenticated-orcid":false,"given":"Zhuoyuan","family":"Yang","sequence":"additional","affiliation":[{"name":"Fudan University","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-5372-3525","authenticated-orcid":false,"given":"Zihao","family":"Chen","sequence":"additional","affiliation":[{"name":"Fudan University","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3944-7531","authenticated-orcid":false,"given":"Li","family":"Shang","sequence":"additional","affiliation":[{"name":"Computer Science, Fudan University","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2164-8175","authenticated-orcid":false,"given":"Fan","family":"Yang","sequence":"additional","affiliation":[{"name":"Fudan University","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,12,17]]},"reference":[{"key":"e_1_3_2_2_2","article-title":"Gpt-4 technical report","author":"Achiam Josh","year":"2023","unstructured":"Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et\u00a0al. 2023. Gpt-4 technical report. arXiv preprint arXiv:2303.08774 (2023).","journal-title":"arXiv preprint arXiv:2303.08774"},{"key":"e_1_3_2_3_2","article-title":"Language models as agents","author":"Andreas Jacob","year":"2022","unstructured":"Jacob Andreas. 2022. Language models as agents. arXiv preprint arXiv:2212.01779 (2022).","journal-title":"arXiv preprint arXiv:2212.01779"},{"key":"e_1_3_2_4_2","volume-title":"Microprocessor Architecture: From Simple Pipelines to Chip Multiprocessors","author":"Baer Jean-Loup","year":"2010","unstructured":"Jean-Loup Baer. 2010. Microprocessor Architecture: From Simple Pipelines to Chip Multiprocessors. Cambridge University Press."},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD51958.2021.9643455"},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i1.27750"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29720"},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1145\/2024716.2024718"},{"key":"e_1_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/MLCAD58807.2023.10299874"},{"key":"e_1_3_2_10_2","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown Tom","year":"2020","unstructured":"Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D. Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, et\u00a0al. 2020. Language models are few-shot learners. Advances in Neural Information Processing Systems 33 (2020), 1877\u20131901.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/2063384.2063454"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1145\/2629677"},{"key":"e_1_3_2_13_2","article-title":"HEBO: Pushing the limits of sample-efficient hyperparameter optimisation","author":"Cowen-Rivers Alexander","year":"2022","unstructured":"Alexander Cowen-Rivers, Wenlong Lyu, Rasul Tutunov, Zhi Wang, Antoine Grosnit, Ryan-Rhys Griffiths, Alexandre Maravel, Jianye Hao, Jun Wang, Jan Peters, and Haitham Bou Ammar. 2022. HEBO: Pushing the limits of sample-efficient hyperparameter optimisation. Journal of Artificial Intelligence Research 74 (2022), 1269\u20131349.","journal-title":"Journal of Artificial Intelligence Research"},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1145\/1534909.1534910"},{"key":"e_1_3_2_15_2","doi-asserted-by":"crossref","unstructured":"Ggaliwango Marvin Nakayiza Hellen Daudi Jjingo and Joyce Nakatumba-Nabende. 2023. Prompt engineering in large language models. 387\u2013402.","DOI":"10.1007\/978-981-99-7962-2_30"},{"key":"e_1_3_2_16_2","article-title":"CPU Models in gem5","author":"Community gem5","year":"2025","unstructured":"gem5 Community. 2025. CPU Models in gem5. Online. Retrieved from https:\/\/www.gem5.org\/documentation\/general_docs\/cpu_models\/. Accessed: 2025-03-09.","journal-title":"Online"},{"key":"e_1_3_2_17_2","article-title":"MinorCPU in gem5","author":"Community gem5","year":"2025","unstructured":"gem5 Community. 2025. MinorCPU in gem5. Online. Retrieved from https:\/\/www.gem5.org\/documentation\/general_docs\/cpu_models\/minor_cpu. Accessed: 2025-03-09.","journal-title":"Online"},{"key":"e_1_3_2_18_2","article-title":"O3CPU in gem5","author":"Community gem5","year":"2025","unstructured":"gem5 Community. 2025. O3CPU in gem5. Online. Retrieved from https:\/\/www.gem5.org\/documentation\/general_docs\/cpu_models\/O3CPU. Accessed: 2025-03-09.","journal-title":"Online"},{"key":"e_1_3_2_19_2","article-title":"ChatGLM: A family of large language models from GLM-130B to GLM-4 all tools","author":"GLM Team","year":"2024","unstructured":"Team GLM, Aohan Zeng, Bin Xu, Bowen Wang, Chenhui Zhang, Da Yin, Diego Rojas, Guanyu Feng, Hanlin Zhao, Hanyu Lai, et\u00a0al. 2024. ChatGLM: A family of large language models from GLM-130B to GLM-4 all tools. arXiv preprint arXiv:2406.12793 (2024).","journal-title":"arXiv preprint arXiv:2406.12793"},{"key":"e_1_3_2_20_2","volume-title":"Computer Architecture: A Quantitative Approach","author":"Hennessy John L.","year":"2011","unstructured":"John L. Hennessy and David A. Patterson. 2011. Computer Architecture: A Quantitative Approach. Elsevier."},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-25566-3_40"},{"key":"e_1_3_2_22_2","article-title":"Leveraging passage retrieval with generative models for open domain question answering","author":"Izacard Gautier","year":"2020","unstructured":"Gautier Izacard and Edouard Grave. 2020. Leveraging passage retrieval with generative models for open domain question answering. arXiv preprint arXiv:2007.01282 (2020).","journal-title":"arXiv preprint arXiv:2007.01282"},{"key":"e_1_3_2_23_2","volume-title":"5th JILP Workshop on Computer Architecture Competitions (JWAC-5): Championship Branch Prediction (CBP-5)","author":"Jim\u00e9nez Daniel A.","year":"2016","unstructured":"Daniel A. Jim\u00e9nez. 2016. Multiperspective perceptron predictor. In 5th JILP Workshop on Computer Architecture Competitions (JWAC-5): Championship Branch Prediction (CBP-5)."},{"key":"e_1_3_2_24_2","article-title":"Dense passage retrieval for open-domain question answering","author":"Karpukhin Vladimir","year":"2020","unstructured":"Vladimir Karpukhin, Barlas O\u011fuz, Sewon Min, Patrick Lewis, Ledell Wu, Sergey Edunov, Danqi Chen, and Wen-tau Yih. 2020. Dense passage retrieval for open-domain question answering. arXiv preprint arXiv:2004.04906 (2020).","journal-title":"arXiv preprint arXiv:2004.04906"},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/40.755465"},{"key":"e_1_3_2_26_2","first-page":"9459","article-title":"Retrieval-augmented generation for knowledge-intensive nlp tasks","volume":"33","author":"Lewis Patrick","year":"2020","unstructured":"Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich K\u00fcttler, Mike Lewis, Wen-tau Yih, Tim Rockt\u00e4schel, et\u00a0al. 2020. Retrieval-augmented generation for knowledge-intensive nlp tasks. Advances in Neural Information Processing Systems 33 (2020), 9459\u20139474.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1145\/1669112.1669172"},{"key":"e_1_3_2_28_2","article-title":"LayoutCopilot: An LLM-powered multi-agent collaborative framework for interactive analog layout design","author":"Liu Bingyang","year":"2025","unstructured":"Bingyang Liu, Haoyi Zhang, Xiaohan Gao, Zichen Kong, Xiyuan Tang, Yibo Lin, Runsheng Wang, and Ru Huang. 2025. LayoutCopilot: An LLM-powered multi-agent collaborative framework for interactive analog layout design. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems (2025).","journal-title":"IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems"},{"key":"e_1_3_2_29_2","volume-title":"Bayesian Approach to Global Optimization: Theory and Applications","author":"Mockus Jonas","year":"2012","unstructured":"Jonas Mockus. 2012. Bayesian Approach to Global Optimization: Theory and Applications. Vol. 37. Springer Science & Business Media."},{"key":"e_1_3_2_30_2","unstructured":"OpenAI. 2023. GPT-4 Technical Report. https:\/\/arxiv.org\/abs\/2303.08774"},{"key":"e_1_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1145\/3586183.3606763"},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1561\/1500000019"},{"key":"e_1_3_2_33_2","article-title":"A systematic survey of prompt engineering in large language models: Techniques and applications","author":"Sahoo Pranab","year":"2024","unstructured":"Pranab Sahoo, Ayush Kumar Singh, Sriparna Saha, Vinija Jain, Samrat Mondal, and Aman Chadha. 2024. A systematic survey of prompt engineering in large language models: Techniques and applications. arXiv preprint arXiv:2402.07927 (2024).","journal-title":"arXiv preprint arXiv:2402.07927"},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2008.2005605"},{"key":"e_1_3_2_35_2","first-page":"1","article-title":"A 256 kbits l-tage branch predictor","volume":"9","author":"Seznec Andr\u00e9","year":"2007","unstructured":"Andr\u00e9 Seznec. 2007. A 256 kbits l-tage branch predictor. Journal of Instruction-Level Parallelism (JILP) Special Issue: The Second Championship Branch Prediction Competition (CBP-2) 9 (2007), 1\u20136.","journal-title":"Journal of Instruction-Level Parallelism (JILP) Special Issue: The Second Championship Branch Prediction Competition (CBP-2)"},{"key":"e_1_3_2_36_2","first-page":"1919","volume-title":"International Conference on Machine Learning","author":"Shah Amar","year":"2016","unstructured":"Amar Shah and Zoubin Ghahramani. 2016. Pareto frontier learning with expensive correlated objectives. In International Conference on Machine Learning. PMLR, 1919\u20131927."},{"key":"e_1_3_2_37_2","volume-title":"Modern Processor Design: Fundamentals of Superscalar Processors","author":"Shen John Paul","year":"2013","unstructured":"John Paul Shen and Mikko H. Lipasti. 2013. Modern Processor Design: Fundamentals of Superscalar Processors. Waveland Press."},{"key":"e_1_3_2_38_2","unstructured":"GitHub Username Takeya. Year of Last Update or Access. gem5 to McPAT Pipeline. Retrieved from https:\/\/github.com\/TAKAKEYA\/gem5tomcpat"},{"key":"e_1_3_2_39_2","doi-asserted-by":"publisher","unstructured":"Mingxin Tang Wei Chen Lizhou Wu Libo Huang and Kun Zeng. 2025. ChatDSE: A zero-shot microarchitecture design space explorer powered by GPT4. 0. ACM Trans. Des. Autom. Electron. Syst. 30 4 Article 62 (July 2025) 24 pages. DOI:10.1145\/3735640","DOI":"10.1145\/3735640"},{"key":"e_1_3_2_40_2","article-title":"Llama: Open and efficient foundation language models","author":"Touvron Hugo","year":"2023","unstructured":"Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timoth\u00e9e Lacroix, Baptiste Rozi\u00e8re, Naman Goyal, Eric Hambro, Faisal Azhar, et\u00a0al. 2023. Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023).","journal-title":"arXiv preprint arXiv:2302.13971"},{"key":"e_1_3_2_41_2","first-page":"5998","article-title":"Attention is all you need","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, and et al.2017. Attention is all you need. Advances in Neural Information Processing Systems (2017), 5998\u20136008.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_42_2","article-title":"Attention is all you need","volume":"30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in Neural Information Processing Systems 30 (2017).","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1145\/3649329.3658493"},{"key":"e_1_3_2_44_2","first-page":"24824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume":"35","author":"Wei Jason","year":"2022","unstructured":"Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, Quoc V. Le, Denny Zhou, et\u00a0al. 2022. Chain-of-thought prompting elicits reasoning in large language models. Advances in Neural Information Processing Systems 35 (2022), 24824\u201324837.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_45_2","article-title":"Prior-boosted GRL: Microarchitecture design space exploration via graph representation learning","author":"Wu Zheng","year":"2024","unstructured":"Zheng Wu, Jinyi Shen, Xiaoling Yi, Li Shang, Fan Yang, and Xuan Zeng. 2024. Prior-boosted GRL: Microarchitecture design space exploration via graph representation learning. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems (2024).","journal-title":"IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems"},{"key":"e_1_3_2_46_2","unstructured":"Shunyu Yao Dian Yu Jeffrey Zhao Izhak Shafran Tom Griffiths Yuan Cao and Karthik Narasimhan. 2024. Tree of thoughts: Deliberate problem solving with large language models. Advances in Neural Information Processing Systems 36 (2023) 11809\u201311822."},{"key":"e_1_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1109\/DAC56929.2023.10247687"},{"key":"e_1_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD57390.2023.10323961"},{"key":"e_1_3_2_49_2","doi-asserted-by":"crossref","unstructured":"X. Zhao T. Gao Z. Wu et\u00a0al. 2025. APPLE-DSE: Asynchronous parallel pareto set learning for microarchitecture design space exploration. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems 44 7 (2025) 2765\u20132778.","DOI":"10.1109\/TCAD.2024.3522880"},{"key":"e_1_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2024.3443006"}],"container-title":["ACM Transactions on Design Automation of Electronic Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3774888","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T13:27:48Z","timestamp":1770384468000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3774888"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,17]]},"references-count":49,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,3,31]]}},"alternative-id":["10.1145\/3774888"],"URL":"https:\/\/doi.org\/10.1145\/3774888","relation":{},"ISSN":["1084-4309","1557-7309"],"issn-type":[{"value":"1084-4309","type":"print"},{"value":"1557-7309","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,17]]},"assertion":[{"value":"2025-06-06","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-10-20","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-12-17","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}