mlsanityData to 7 Oct 2026

CoopetitiveV: Leveraging LLM-powered Coopetitive Multi-Agent Prompting for High-quality Verilog Generation

arXiv 2412.11014 ↗First posted 15 Dec 2024cs.LG cs.AI cs.ARcited by 9

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

Abstract (arXiv)

Recent advances in agentic LLMs have demonstrated great capabilities in Verilog code generation. However, existing approaches either use LLM-assisted single-agent prompting or cooperation-only multi-agent learning, which will lead to: (i) Degeneration issue for single-agent learning: characterized by diminished error detection and correction capabilities; (ii) Error propagation in cooperation-only multi-agent learning: erroneous information from the former agent will be propagated to the latter through prompts, which can make the latter agents generate buggy code. In this paper, we propose an LLM-based coopetitive multi-agent prompting framework, in which the agents cannot collaborate with each other to form the generation pipeline, but also create a healthy competitive mechanism to improve the generating quality. Our experimental results show that the coopetitive multi-agent framework can effectively mitigate the degeneration risk and reduce the error propagation while improving code error correction capabilities, resulting in higher quality Verilog code generation. The effectiveness of our approach is validated through extensive experiments. On VerilogEval Machine and Human dataset, CoopetitiveV+GPT-4 achieves 99.2% and 99.1% pass@10 scores, respectively. While on RTLLM, CoopetitiveV+GPT-4 obtains 100% syntax and 99.9% functionality pass@5 scores.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use. Builds on 20 of its 29 references that are in the map. First posted on arXiv 15 Dec 2024.

Builds on

20 of 29 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024VerilogCoder: Autonomous Verilog Coding Agents with Graph-based Planning and Abstract Syntax Tree (AST)-based Waveform Tracing Tool15 Aug

Other references · 19

  1. 2024The Llama 3 Herd of Modelscited by 14,192
  2. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  3. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  4. 2022Self-Instruct: Aligning Language Models with Self-Generated Instructionscited by 2,674
  5. 2023A Survey on Large Language Model based Autonomous Agentscited by 2,203
  6. 2023Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debatecited by 995
  7. 2023VerilogEval: Evaluating Large Language Models for Verilog Code Generationcited by 246
  8. 2023Is Self-Repair a Silver Bullet for Code Generation?cited by 191
  9. 2022Large Language Models Meet NL2Code: A Surveycited by 135
  10. 2023Self-Edit: Fault-Aware Code Editor for Code Generationcited by 110
  11. 2022Repository-Level Prompt Generation for Large Language Models of Codecited by 106
  12. 2024BetterV: Controlled Verilog Generation with Discriminative Guidancecited by 99
7 more
  1. 2022Coder Reviewer Reranking for Code Generationcited by 83
  2. 2023RTLCoder: Outperforming GPT-3.5 in Design RTL Generation with Our Open-Source Dataset and Lightweight Solutioncited by 69
  3. 2020DAVE: Deriving Automatically Verilog from Englishcited by 46
  4. 2024Towards LLM-Powered Verilog RTL Assistant: Self-Verification and Self-Correctioncited by 39
  5. 2024AutoBench: Automatic Testbench Generation and Evaluation Using LLMs for HDL Designcited by 38
  6. 2024Search-Based LLMs for Code Optimizationcited by 27
  7. 2024LASSI: An LLM-based Automated Self-Correcting Pipeline for Translating Parallel Scientific Codescited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 6; 2026: 3.

9 papers.

  1. 2025VeriMoA: A Mixture-of-Agents Framework for Spec-to-HDL Generationcited by 15
  2. 2025VerilogDB: The Largest, Highest-Quality Dataset with a Preprocessing Framework for LLM-based RTL Generationcited by 8
  3. 2025Understanding and Mitigating Errors of LLM-Generated RTL Codecited by 8
  4. 2025Large Language Model for Verilog Code Generation: Literature Review and the Road Aheadcited by 7
  5. 2025Towards Optimal Circuit Generation: Multi-Agent Collaboration Meets Collective Intelligencecited by 1
  6. 2025DeepV: A Model-Agnostic Retrieval-Augmented Framework for Verilog Code Generation with a High-Quality Knowledge Basecited by 1
  7. 2026ChipMATE: Multi-Agent Training via Reinforcement Learning for Enhanced RTL Generationcited by 1
  8. 2026Agentic Electronic Design Automation: A Handoff Perspectivecited by 0
  9. 2026VeriPilot: An LLM-Powered Verilog Debugging Frameworkcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026LLM-Based Multi-Agent Systems for Code Generation: A Multi-Vocal Literature Review
  2. 2025Lessons Learned: A Multi-Agent Framework for Code LLMs to Learn and Improve
  3. 2025CodeAgents: A Token-Efficient Framework for Codified Multi-Agent Reasoning in LLMs
  4. 2026SiliconMind-V1: Multi-Agent Distillation and Debug-Reasoning Workflows for Verilog Code Generation
  5. 2024A Survey on LLM-based Multi-Agent System: Recent Advances and New Frontiers in Application
  6. 2025Adaptive Coopetition: Leveraging Coarse Verifier Signals for Resilient Multi-Agent LLM Reasoning
  7. 2024MapCoder: Multi-Agent Code Generation for Competitive Problem Solving
  8. 2023AgentTuning: Enabling Generalized Agent Abilities for LLMs