{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T02:27:29Z","timestamp":1773800849114,"version":"3.50.1"},"reference-count":0,"publisher":"Association for the Advancement of Artificial Intelligence (AAAI)","issue":"2","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["AAAI"],"abstract":"<jats:p>In this paper, we propose AMS-IO-Agent, a domain-specialized LLM-based agent for structure-aware input\/output (I\/O) subsystem generation in analog and mixed-signal (AMS) integrated circuits (ICs). \nThe central contribution of this work is a framework that connects natural language design intent with industrial-level AMS IC design deliverables.\nAMS-IO-Agent integrates two key capabilities: \n(1) a structured domain knowledge base that captures reusable constraints and design conventions; \n(2) design intent structuring, which converts ambiguous user intent into verifiable logic steps using JSON and Python as intermediate formats.\nWe further introduce AMS-IO-Bench, a benchmark for wirebond-packaged AMS I\/O ring automation. \nOn this benchmark, AMS-IO-Agent achieves over 70% DRC+LVS pass rate and reduces design turnaround time from hours to minutes, outperforming the baseline LLM. \nFurthermore, an agent-generated I\/O ring was fabricated and validated in a 28 nm CMOS tape-out, demonstrating the practical effectiveness of the approach in real AMS IC design flows.\nTo our knowledge, this is the first reported human-agent collaborative AMS IC design in which an LLM-based agent completes a nontrivial subtask with outputs directly used in silicon.<\/jats:p>","DOI":"10.1609\/aaai.v40i2.37134","type":"journal-article","created":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T22:49:55Z","timestamp":1773787795000},"page":"1579-1586","source":"Crossref","is-referenced-by-count":0,"title":["AMS-IO-Bench and AMS-IO-Agent: Benchmarking and Structured Reasoning for Analog and Mixed-Signal Integrated Circuit Input\/Output Design"],"prefix":"10.1609","volume":"40","author":[{"given":"Zhishuai","family":"Zhang","sequence":"first","affiliation":[]},{"given":"Xintian","family":"Li","sequence":"additional","affiliation":[]},{"given":"Shilong","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Aodong","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Lu","family":"Jie","sequence":"additional","affiliation":[]},{"given":"Nan","family":"Sun","sequence":"additional","affiliation":[]}],"member":"9382","published-online":{"date-parts":[[2026,3,14]]},"container-title":["Proceedings of the AAAI Conference on Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/37134\/41096","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/37134\/41096","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T22:49:56Z","timestamp":1773787796000},"score":1,"resource":{"primary":{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/37134"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,14]]},"references-count":0,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2026,3,17]]}},"URL":"https:\/\/doi.org\/10.1609\/aaai.v40i2.37134","relation":{},"ISSN":["2374-3468","2159-5399"],"issn-type":[{"value":"2374-3468","type":"electronic"},{"value":"2159-5399","type":"print"}],"subject":[],"published":{"date-parts":[[2026,3,14]]}}}