Can AI Agents Really Complete RTL-to-GDS? Lessons from Benchmarking Tool-Interactive EDA Workflows

• URL: http://arxiv.org/abs/2607.17528v3
• Date: Thu, 23 Jul 2026 03:04:35 GMT
• Title: Can AI Agents Really Complete RTL-to-GDS? Lessons from Benchmarking Tool-Interactive EDA Workflows
• Abstract summary: Large language model (LLM) agents are extending electronic design automation (EDA) beyond static RTL generation toward long-horizon, tool-interactive.<n>Yet it remains unclear whether general-purpose coding agents, even with domain-specific EDA skills, can reliably execute an end-to-end RTL-to-GDS flow.<n>We evaluate AI agents on a PicoRV32 RTL-to-GDS flow using commercial EDA tools under two timing targets.<n>Their performance is assessed using end-to-end design score, stage completion, and Token ROI, a cost-efficiency metric relating design quality to runtime and
• Score: 8.003851287933244
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Large language model (LLM) agents are extending electronic design automation (EDA) beyond static RTL generation toward long-horizon, tool-interactive workflows. Yet it remains unclear whether general-purpose coding agents, even with domain-specific EDA skills, can reliably execute an end-to-end RTL-to-GDS flow encompassing synthesis, physical implementation, and engineering change order (ECO) optimization. We evaluate AI agents on a PicoRV32 RTL-to-GDS flow using commercial EDA tools under two timing targets. Their performance is assessed using end-to-end design score, stage completion, and Token ROI, a cost-efficiency metric relating design quality to runtime and cost. Comparing three agent architectures and four foundation models, we derive three practical lessons. First, domain-specific skills improve agents' understanding of individual subtasks but do not ensure reliable completion of a long-horizon EDA flow. Second, agents that achieve similar design progress can still differ by up to 141 times in Token ROI, revealing substantial differences in runtime and cost efficiency. Third, low-level tool-interface mismatches are a major source of physical design failures, particularly when Tcl commands depend on the tool version or execution mode. These results suggest that robust Agentic EDA requires not only stronger models but also structured tool interfaces, persistent design context, controlled execution, and process-level evaluation.

Related papers

• Beyond Generalist LLMs: Specialist Agentic Systems for Structured Code Workflow Execution [0.40631409309544836]
  Large Language Models (LLMs) have accelerated the adoption of software development agents, now widely available as Integrated Development Environment (IDE) extensions and standalone applications.<n>While these agents are typically general-purpose, it remains unclear whether specialist agents justify their additional development effort.<n>We investigate this question in the context of business process automation, focusing on the transformation of Business Process Model and Notation (BPMN) diagrams into executable agentic.
  arXiv  Detail & Related papers  (2026-07-16T01:06:38Z)
• From Atomic Actions to Standard Operating Procedures: Iterative Tool Optimization for Self-Evolving LLM Agents [90.3279207163486]
  EvoSOP is a framework that empowers agents to extract SOPs from execution trajectories and iteratively optimize the toolset.<n>We show that EvoSOP significantly boosts task success rates while substantially reducing the number of interaction rounds.
  arXiv  Detail & Related papers  (2026-07-08T12:09:49Z)
• GTA-2: Benchmarking General Tool Agents from Atomic Tool-Use to Open-Ended Workflows [90.35728421223673]
  GTA-2 is a hierarchical benchmark for General Tool Agents (GTA)<n>Built on real-world authenticity, it leverages real user queries, deployed tools, and multimodal contexts.<n>Experiments reveal a pronounced capability cliff: while frontier models already struggle on atomic tasks, top models achieving only 14.39% success.
  arXiv  Detail & Related papers  (2026-04-17T05:36:00Z)
• AVDA: Autonomous Vibe Detection Authoring for Cybersecurity [0.1633272850273525]
  We introduce AVDA, a framework that leverages the Model Context Protocol (MCP) to automate detection by integrating organizational context into AI-assisted code generation.<n>We evaluate three authoring strategies - Baseline, Sequential, and Agentic - across a diverse corpus of production detections and state-of-the-art LLMs.<n>Our results show that Agentic attains 87% of Agentic quality at 40x lower token cost.
  arXiv  Detail & Related papers  (2026-03-26T21:52:33Z)
• FluxEDA: A Unified Execution Infrastructure for Stateful Agentic EDA [13.976446231636166]
  We present FluxEDA, a unified and stateful infrastructure substrate for agentic EDA.<n>F FluxEDA introduces a managed gateway-based execution interface with structured request and response handling.<n>It also maintains persistent backend instances.
  arXiv  Detail & Related papers  (2026-03-26T09:49:19Z)
• ToolSelf: Unifying Task Execution and Self-Reconfiguration via Tool-Driven Intrinsic Adaptation [60.25542764389203]
  Agentic systems powered by Large Language Models (LLMs) have demonstrated remarkable potential in tackling complex, long-horizon tasks.<n>Existing approaches, relying on manual orchestration or runtime-based patches, often struggle with poor generalization and fragmented optimization.<n>We propose ToolSelf, a novel paradigm enabling tool-driven self-readjustment.
  arXiv  Detail & Related papers  (2026-02-08T09:27:18Z)
• PerfGuard: A Performance-Aware Agent for Visual Content Generation [53.591105729011595]
  PerfGuard is a performance-aware agent framework for visual content generation.<n>It integrates tool performance boundaries into task planning and scheduling.<n>It has advantages in tool selection accuracy, execution reliability, and alignment with user intent.
  arXiv  Detail & Related papers  (2026-01-30T05:12:19Z)
• Let It Flow: Agentic Crafting on Rock and Roll, Building the ROME Model within an Open Agentic Learning Ecosystem [90.17610617854247]
  We introduce the Agentic Learning Ecosystem (ALE), a foundational infrastructure that optimize the production pipeline for agentic model.<n>ALE consists of three components: ROLL, a post-training framework for weight optimization; ROCK, a sandbox environment manager for trajectory generation; and iFlow CLI, an agent framework for efficient context engineering.<n>We release ROME, an open-source agent grounded by ALE and trained on over one million trajectories.
  arXiv  Detail & Related papers  (2025-12-31T14:03:39Z)
• AgentMath: Empowering Mathematical Reasoning for Large Language Models via Tool-Augmented Agent [80.83250816918861]
  Large Reasoning Models (LRMs) like o3 and DeepSeek-R1 have achieved remarkable progress in natural language reasoning with long chain-of-thought.<n>However, they remain computationally inefficient and struggle with accuracy when solving problems requiring complex mathematical operations.<n>We present AgentMath, an agent framework that seamlessly integrates language models' reasoning capabilities with code interpreters' computational precision.
  arXiv  Detail & Related papers  (2025-12-23T19:57:49Z)
• LoCoBench-Agent: An Interactive Benchmark for LLM Agents in Long-Context Software Engineering [90.84806758077536]
  We introduce textbfLoCoBench-Agent, a comprehensive evaluation framework specifically designed to assess large language models (LLMs) agents in realistic, long-context software engineering.<n>Our framework extends LoCoBench's 8,000 scenarios into interactive agent environments, enabling systematic evaluation of multi-turn conversations.<n>Our framework provides agents with 8 specialized tools (file operations, search, code analysis) and evaluates them across context lengths ranging from 10K to 1M tokens.
  arXiv  Detail & Related papers  (2025-11-17T23:57:24Z)
• AgentEvolver: Towards Efficient Self-Evolving Agent System [51.54882384204726]
  We present AgentEvolver, a self-evolving agent system that drives autonomous agent learning.<n>AgentEvolver introduces three synergistic mechanisms: self-questioning, self-navigating, and self-attributing.<n>Preliminary experiments indicate that AgentEvolver achieves more efficient exploration, better sample utilization, and faster adaptation compared to traditional RL-based baselines.
  arXiv  Detail & Related papers  (2025-11-13T15:14:47Z)
• Agentic AI Sustainability Assessment for Supply Chain Document Insights [0.0]
  This paper presents a comprehensive sustainability assessment framework for document intelligence within supply chain operations centered on agentic artificial intelligence (AI)<n>We address the dual objective of improving automation efficiency while providing measurable environmental performance in document-intensive paper extraction.<n>We show that AI-assisted HITL and agentic AI scenarios achieve reductions of up to 7 in energy consumption, 90-97% in carbon dioxide emissions, and 89-98% in water usage compared to manual processes.
  arXiv  Detail & Related papers  (2025-11-10T13:38:08Z)
• AutoEDA: Enabling EDA Flow Automation through Microservice-Based LLM Agents [15.41283323575065]
  AutoEDA is a framework for EDA automation that leverages paralleled learning through the Model Context Protocol (MCP) specific for standardized and scalable natural language experience.<n>Results from experiments show improvements in automation accuracy and efficiency, as well as script quality when compared to existing methods.
  arXiv  Detail & Related papers  (2025-08-01T18:23:57Z)
• Divergent Thoughts toward One Goal: LLM-based Multi-Agent Collaboration System for Electronic Design Automation [5.536630285985836]
  We introduce EDAid, a multi-agent collaboration system where multiple agents harboring divergent thoughts converge towards a common goal.<n>Specifically, each agent is controlled by ChipLlama models, which are expert LLMs fine-tuned for EDA flow automation.<n>Our experiments demonstrate the state-of-the-art (SOTA) performance of our ChipLlama models and validate the effectiveness of our EDAid.
  arXiv  Detail & Related papers  (2025-02-15T16:59:29Z)
• Flow: Modularized Agentic Workflow Automation [53.073598156915615]
  Multi-agent frameworks powered by large language models (LLMs) have demonstrated great success in automated planning and task execution.<n>However, the effective adjustment of agentic during execution has not been well studied.<n>In this paper, we define an activity-on-vertex (AOV) graph, which allows continuous workflow refinement by agents.<n>Our proposed multi-agent framework achieves efficient concurrent execution of subtasks, effective goal achievement, and enhanced error tolerance.
  arXiv  Detail & Related papers  (2025-01-14T04:35:37Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.