mlsanityData to 14 Oct 2026

PEFA-AI: Advancing Open-source LLMs for RTL generation using Progressive Error Feedback Agentic-AI

arXiv 2511.03934 ↗First posted 6 Nov 2025cs.SE cs.AIcited by 0

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

Abstract (arXiv)

We present an agentic flow consisting of multiple agents that combine specialized LLMs and hardware simulation tools to collaboratively complete the complex task of Register Transfer Level (RTL) generation without human intervention. A key feature of the proposed flow is the progressive error feedback system of agents (PEFA), a self-correcting mechanism that leverages iterative error feedback to progressively increase the complexity of the approach. The generated RTL includes checks for compilation, functional correctness, and synthesizable constructs. To validate this adaptive approach to code generation, benchmarking is performed using two opensource natural language-to-RTL datasets. We demonstrate the benefits of the proposed approach implemented on an open source agentic framework, using both open- and closed-source LLMs, effectively bridging the performance gap between them. Compared to previously published methods, our approach sets a new benchmark, providing state-of-the-art pass rates while being efficient in token counts.

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 29 of its 42 references that are in the map. First posted on arXiv 6 Nov 2025.

Builds on

29 of 42 references.

Closest ancestors · 3

Same direction, newest first

  1. 2024VerilogCoder: Autonomous Verilog Coding Agents with Graph-based Planning and Abstract Syntax Tree (AST)-based Waveform Tracing Tool15 Aug
  2. 2024Self-Organized Agents: A LLM Multi-Agent Framework toward Ultra Large-Scale Code Generation and Optimization2 Apr
  3. 2023Self-collaboration Code Generation via ChatGPT15 Apr

Other references · 26

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2024The Llama 3 Herd of Modelscited by 14,715
  3. 2022Competition-Level Code Generation with AlphaCodecited by 1,462
  4. 2024DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligencecited by 1,181
  5. 2022CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesiscited by 885
  6. 2024A Survey on Large Language Models for Code Generationcited by 658
  7. 2023AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviorscited by 598
  8. 2023A Survey on Large Language Model (LLM) Security and Privacy: The Good, the Bad, and the Uglycited by 387
  9. 2023CodeT5+: Open Code Large Language Models for Code Understanding and Generationcited by 333
  10. 2023VerilogEval: Evaluating Large Language Models for Verilog Code Generationcited by 252
  11. 2024AI Agents That Mattercited by 219
  12. 2023VeriGen: A Large Language Model for Verilog Code Generationcited by 200
14 more
  1. 2023Planning with Large Language Models for Code Generationcited by 182
  2. 2023RTLLM: An Open-Source Benchmark for Design RTL Generation with Large Language Modelcited by 148
  3. 2022Large Language Models are Few-shot Testers: Exploring LLM-based General Bug Reproductioncited by 111
  4. 2024The Dawn After the Dark: An Empirical Study on Factuality Hallucination in Large Language Modelscited by 88
  5. 2020Chip Placement with Deep Reinforcement Learningcited by 83
  6. 2023AutoChip: Automating HDL Generation Using LLM Feedbackcited by 83
  7. 2024OriGen:Enhancing RTL Code Generation with Code-to-Code Augmentation and Self-Reflectioncited by 56
  8. 2024Make Every Move Count: LLM-based High-Quality RTL Code Generation Using MCTScited by 43
  9. 2024CreativEval: Evaluating Creativity of LLM-Based Hardware Code Generationcited by 19
  10. 2024AIvril: AI-Driven RTL Generation With Verification In-The-Loopcited by 15
  11. 2023Advanced Large Language Model (LLM)-Driven Verilog Development: Enhancing Power, Performance, and Area Optimization in Code Synthesiscited by 14
  12. 2024Zero-Shot RTL Code Generation with Attention Sink Augmented Large Language Modelscited by 5
  13. 2025DOSA: Differentiable Model-Based One-Loop Search for DNN Acceleratorscited by 4
  14. 2019Yosys+nextpnr: an Open Source Framework from Verilog to Bitstream for Commercial FPGAscited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024EDA-Aware RTL Generation with Large Language Models
  2. 2026VeriAgent: A Tool-Integrated Multi-Agent System with Evolving Memory for PPA-Aware RTL Code Generation
  3. 2026ChipCraftBrain: Validation-First RTL Generation via Multi-Agent Orchestration
  4. 2024MAGE: A Multi-Agent Engine for Automated RTL Code Generation
  5. 2026ACE-RTL: When Agentic Context Evolution Meets RTL-Specialized LLMs
  6. 2025RTLSquad: Multi-Agent Based Interpretable RTL Design
  7. 2025TuRTLe: A Unified Evaluation of LLMs for RTL Generation
  8. 2026CODMAS: A Dialectic Multi-Agent Collaborative Framework for Structured RTL Optimization