{"ID":2883125,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.08709","arxiv_id":"2508.08709","title":"CRADLE: Conversational RTL Design Space Exploration with LLM-based Multi-Agent Systems","abstract":"This paper presents CRADLE, a conversational framework for design space exploration of RTL designs using LLM-based multi-agent systems. Unlike existing rigid approaches, CRADLE enables user-guided flows with internal self-verification, correction, and optimization. We demonstrate the framework with a generator-critic agent system targeting FPGA resource minimization using state-of-the-art LLMs. Experimental results on the RTLLM benchmark show that CRADLE achieves significant reductions in resource usage with averages of 48% and 40% in LUTs and FFs across all benchmark designs.","short_abstract":"This paper presents CRADLE, a conversational framework for design space exploration of RTL designs using LLM-based multi-agent systems. Unlike existing rigid approaches, CRADLE enables user-guided flows with internal self-verification, correction, and optimization. We demonstrate the framework with a generator-critic a...","url_abs":"https://arxiv.org/abs/2508.08709","url_pdf":"https://arxiv.org/pdf/2508.08709v1","authors":"[\"Lukas Krupp\",\"Maximilian Schöffel\",\"Elias Biehl\",\"Norbert Wehn\"]","published":"2025-08-12T07:54:39Z","proceeding":"cs.RO","tasks":"[\"cs.RO\",\"cs.AR\",\"cs.LG\",\"cs.MA\"]","methods":"[\"Large Language Model\",\"LoRA\"]","has_code":false}