mlsanityData to 14 Oct 2026

A3D: Agentic AI flow for autonomous Accelerator Design

arXiv 2605.15237 ↗First posted 14 May 2026cs.AR cs.AIcited by 0

On the map: LLM agents and tool use → Software engineering coding agents

Abstract (arXiv)

Accelerating applications through the design of hardware accelerators can significantly enhance system performance and energy efficiency. Despite advances, such as high-level synthesis (HLS), designing accelerators for complex applications still remains highly labor-intensive, demanding considerable expertise in understanding workloads to be accelerated, hardware design, micro-architecture, and EDA tool usage, posing challenges for application domain experts. Therefore, most accelerator solutions are limited to applications with a regular predictable dataflow. Advances in AI have enabled agents that perform autonomous planning, reasoning, execution and reflection, leading to unprecedented potential for automation through agentic AI. We present A3D, an Agentic AI flow for end-to-end Automation of hardware Accelerator Design. A3D automates workload analysis, performance bottleneck identification, code refactoring for HLS compatibility and micro-architecture generation. A3D also generates diverse accelerator designs by automatically exploring the speed-area tradeoff space. Recent efforts have explored the use of AI for specific tasks such as design space exploration in HLS, leaving several tasks to still be performed manually. A3D addresses the challenges in applying modern LLMs to accelerator design by judiciously partitioning tasks among specialist agents, orchestrating process loops with specialist and verifier agents, utilizing pre-existing and custom tools, and employing agentic RAG for codebase and proprietary EDA tool documentation exploration. Our implementation of A3D, using commercial components like Claude Sonnet 4.5 and the Catapult HLS tool, demonstrates its effectiveness by generating accelerator designs with no human intervention from complex scientific applications like LAMMPS (molecular dynamics simulation) and QMCPACK (quantum chemistry).

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use. Builds on 14 of its 34 references that are in the map. First posted on arXiv 14 May 2026.

Builds on

14 of 34 references.

Closest ancestors · 2

Same direction, newest first

  1. 2025LLM-DSE: Searching Accelerator Parameters with LLM Agents18 May
  2. 2024Agentic-HLS: An agentic reasoning based high-level synthesis system using large language models (AI for EDA workshop 2024)2 Dec

Other references · 12

  1. 2023SWE-bench: Can Language Models Resolve Real-World GitHub Issues?cited by 3,373
  2. 2023LongBench: A Bilingual, Multitask Benchmark for Long Context Understandingcited by 1,417
  3. 2024A Survey on Large Language Models for Code Generationcited by 658
  4. 2017In-Datacenter Performance Analysis of a Tensor Processing Unitcited by 618
  5. 2025Seedance 1.0: Exploring the Boundaries of Video Generation Modelscited by 259
  6. 2023RenAIssance: A Survey into AI Text-to-Image Generation in the Era of Large Modelcited by 47
  7. 2020AutoDSE: Enabling Software Programmers to Design Efficient FPGA Acceleratorscited by 25
  8. 2021F1: A Fast and Programmable Accelerator for Fully Homomorphic Encryption (Extended Version)cited by 23
  9. 2024Automated C/C++ Program Repair for High-Level Synthesis via Large Language Modelscited by 18
  10. 2024C2HLSC: Leveraging Large Language Models to Bridge the Software-to-Hardware Design Gapcited by 16
  11. 2025SAGE-HLS: Syntax-Aware AST-Guided LLM for High-Level Synthesis Code Generationcited by 9
  12. 2025LIFT: LLM-Based Pragma Insertion for HLS via GNN Supervised Fine-Tuningcited by 8

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Agentic Artificial Intelligence for Multistage Physics Experiments at a Large-Scale User Facility Particle Accelerator
  2. 2026Is Agentic AI Ready for Real-World Hardware Engineering? A Deep Dive with Phoenix-bench
  3. 2026ArchAgent: Agentic AI-driven Computer Architecture Discovery
  4. 2026Benchmarking AI Agents for Hardware Design Automation via MCP Tool Calling
  5. 2025ASIC-Agent: An Autonomous Multi-Agent System for ASIC Design with Benchmark Evaluation
  6. 2026Can Agents Design Better Chips with a Higher Level Abstraction?
  7. 2026Agentic Hardware Design as Repository-Level Code Evolution
  8. 2026Toward a Fully Autonomous, AI-Native Particle Accelerator