CoopetitiveV: Leveraging LLM-powered Coopetitive Multi-Agent Prompting for High-quality Verilog Generation Article Swipe
Zhendong Mi
,
Run Zheng
,
Zhong Hai-ming
,
Yu-E Sun
,
Shaoyi Huang
·
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2412.11014
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2412.11014
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.
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2412.11014
- https://arxiv.org/pdf/2412.11014
- OA Status
- green
- Cited By
- 3
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4405469574
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4405469574Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2412.11014Digital Object Identifier
- Title
-
CoopetitiveV: Leveraging LLM-powered Coopetitive Multi-Agent Prompting for High-quality Verilog GenerationWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2024Year of publication
- Publication date
-
2024-12-15Full publication date if available
- Authors
-
Zhendong Mi, Run Zheng, Zhong Hai-ming, Yu-E Sun, Shaoyi HuangList of authors in order
- Landing page
-
https://arxiv.org/abs/2412.11014Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2412.11014Direct link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
greenOpen access status per OpenAlex
- OA URL
-
https://arxiv.org/pdf/2412.11014Direct OA link when available
- Concepts
-
Verilog, Computer science, Quality (philosophy), Computer architecture, Embedded system, Field-programmable gate array, Physics, Quantum mechanicsTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
3Total citation count in OpenAlex
- Citations by year (recent)
-
2025: 3Per-year citation counts (last 5 years)
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4405469574 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2412.11014 |
| ids.doi | https://doi.org/10.48550/arxiv.2412.11014 |
| ids.openalex | https://openalex.org/W4405469574 |
| fwci | |
| type | preprint |
| title | CoopetitiveV: Leveraging LLM-powered Coopetitive Multi-Agent Prompting for High-quality Verilog Generation |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T10181 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.9714999794960022 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/1702 |
| topics[0].subfield.display_name | Artificial Intelligence |
| topics[0].display_name | Natural Language Processing Techniques |
| topics[1].id | https://openalex.org/T10201 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9402999877929688 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/1702 |
| topics[1].subfield.display_name | Artificial Intelligence |
| topics[1].display_name | Speech Recognition and Synthesis |
| topics[2].id | https://openalex.org/T10028 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.914900004863739 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/1702 |
| topics[2].subfield.display_name | Artificial Intelligence |
| topics[2].display_name | Topic Modeling |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C2779030575 |
| concepts[0].level | 3 |
| concepts[0].score | 0.6802539229393005 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q827773 |
| concepts[0].display_name | Verilog |
| concepts[1].id | https://openalex.org/C41008148 |
| concepts[1].level | 0 |
| concepts[1].score | 0.6248170137405396 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[1].display_name | Computer science |
| concepts[2].id | https://openalex.org/C2779530757 |
| concepts[2].level | 2 |
| concepts[2].score | 0.528727114200592 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q1207505 |
| concepts[2].display_name | Quality (philosophy) |
| concepts[3].id | https://openalex.org/C118524514 |
| concepts[3].level | 1 |
| concepts[3].score | 0.4001389443874359 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q173212 |
| concepts[3].display_name | Computer architecture |
| concepts[4].id | https://openalex.org/C149635348 |
| concepts[4].level | 1 |
| concepts[4].score | 0.27121514081954956 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q193040 |
| concepts[4].display_name | Embedded system |
| concepts[5].id | https://openalex.org/C42935608 |
| concepts[5].level | 2 |
| concepts[5].score | 0.057774752378463745 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q190411 |
| concepts[5].display_name | Field-programmable gate array |
| concepts[6].id | https://openalex.org/C121332964 |
| concepts[6].level | 0 |
| concepts[6].score | 0.04432809352874756 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q413 |
| concepts[6].display_name | Physics |
| concepts[7].id | https://openalex.org/C62520636 |
| concepts[7].level | 1 |
| concepts[7].score | 0.0 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q944 |
| concepts[7].display_name | Quantum mechanics |
| keywords[0].id | https://openalex.org/keywords/verilog |
| keywords[0].score | 0.6802539229393005 |
| keywords[0].display_name | Verilog |
| keywords[1].id | https://openalex.org/keywords/computer-science |
| keywords[1].score | 0.6248170137405396 |
| keywords[1].display_name | Computer science |
| keywords[2].id | https://openalex.org/keywords/quality |
| keywords[2].score | 0.528727114200592 |
| keywords[2].display_name | Quality (philosophy) |
| keywords[3].id | https://openalex.org/keywords/computer-architecture |
| keywords[3].score | 0.4001389443874359 |
| keywords[3].display_name | Computer architecture |
| keywords[4].id | https://openalex.org/keywords/embedded-system |
| keywords[4].score | 0.27121514081954956 |
| keywords[4].display_name | Embedded system |
| keywords[5].id | https://openalex.org/keywords/field-programmable-gate-array |
| keywords[5].score | 0.057774752378463745 |
| keywords[5].display_name | Field-programmable gate array |
| keywords[6].id | https://openalex.org/keywords/physics |
| keywords[6].score | 0.04432809352874756 |
| keywords[6].display_name | Physics |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2412.11014 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S4306400194 |
| locations[0].source.issn | |
| locations[0].source.type | repository |
| locations[0].source.is_oa | True |
| locations[0].source.issn_l | |
| locations[0].source.is_core | False |
| locations[0].source.is_in_doaj | False |
| locations[0].source.display_name | arXiv (Cornell University) |
| locations[0].source.host_organization | https://openalex.org/I205783295 |
| locations[0].source.host_organization_name | Cornell University |
| locations[0].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[0].license | |
| locations[0].pdf_url | https://arxiv.org/pdf/2412.11014 |
| locations[0].version | submittedVersion |
| locations[0].raw_type | text |
| locations[0].license_id | |
| locations[0].is_accepted | False |
| locations[0].is_published | False |
| locations[0].raw_source_name | |
| locations[0].landing_page_url | http://arxiv.org/abs/2412.11014 |
| locations[1].id | doi:10.48550/arxiv.2412.11014 |
| locations[1].is_oa | True |
| locations[1].source.id | https://openalex.org/S4306400194 |
| locations[1].source.issn | |
| locations[1].source.type | repository |
| locations[1].source.is_oa | True |
| locations[1].source.issn_l | |
| locations[1].source.is_core | False |
| locations[1].source.is_in_doaj | False |
| locations[1].source.display_name | arXiv (Cornell University) |
| locations[1].source.host_organization | https://openalex.org/I205783295 |
| locations[1].source.host_organization_name | Cornell University |
| locations[1].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[1].license | cc-by |
| locations[1].pdf_url | |
| locations[1].version | |
| locations[1].raw_type | article |
| locations[1].license_id | https://openalex.org/licenses/cc-by |
| locations[1].is_accepted | False |
| locations[1].is_published | |
| locations[1].raw_source_name | |
| locations[1].landing_page_url | https://doi.org/10.48550/arxiv.2412.11014 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5105697701 |
| authorships[0].author.orcid | |
| authorships[0].author.display_name | Zhendong Mi |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Mi, Zhendong |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5073179011 |
| authorships[1].author.orcid | https://orcid.org/0000-0002-9117-6639 |
| authorships[1].author.display_name | Run Zheng |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Zheng, Renming |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5000040005 |
| authorships[2].author.orcid | |
| authorships[2].author.display_name | Zhong Hai-ming |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Zhong, Haowen |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5053110771 |
| authorships[3].author.orcid | https://orcid.org/0000-0002-0018-4810 |
| authorships[3].author.display_name | Yu-E Sun |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Sun, Yue |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5073345631 |
| authorships[4].author.orcid | https://orcid.org/0000-0001-6093-9798 |
| authorships[4].author.display_name | Shaoyi Huang |
| authorships[4].author_position | last |
| authorships[4].raw_author_name | Huang, Shaoyi |
| authorships[4].is_corresponding | False |
| has_content.pdf | False |
| has_content.grobid_xml | False |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://arxiv.org/pdf/2412.11014 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2024-12-18T00:00:00 |
| display_name | CoopetitiveV: Leveraging LLM-powered Coopetitive Multi-Agent Prompting for High-quality Verilog Generation |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T10181 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.9714999794960022 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/1702 |
| primary_topic.subfield.display_name | Artificial Intelligence |
| primary_topic.display_name | Natural Language Processing Techniques |
| related_works | https://openalex.org/W4391375266, https://openalex.org/W2899084033, https://openalex.org/W2748952813, https://openalex.org/W2390279801, https://openalex.org/W1761969858, https://openalex.org/W2391854357, https://openalex.org/W3114194214, https://openalex.org/W1748531671, https://openalex.org/W4206948312, https://openalex.org/W2132512458 |
| cited_by_count | 3 |
| counts_by_year[0].year | 2025 |
| counts_by_year[0].cited_by_count | 3 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2412.11014 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S4306400194 |
| best_oa_location.source.issn | |
| best_oa_location.source.type | repository |
| best_oa_location.source.is_oa | True |
| best_oa_location.source.issn_l | |
| best_oa_location.source.is_core | False |
| best_oa_location.source.is_in_doaj | False |
| best_oa_location.source.display_name | arXiv (Cornell University) |
| best_oa_location.source.host_organization | https://openalex.org/I205783295 |
| best_oa_location.source.host_organization_name | Cornell University |
| best_oa_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| best_oa_location.license | |
| best_oa_location.pdf_url | https://arxiv.org/pdf/2412.11014 |
| best_oa_location.version | submittedVersion |
| best_oa_location.raw_type | text |
| best_oa_location.license_id | |
| best_oa_location.is_accepted | False |
| best_oa_location.is_published | False |
| best_oa_location.raw_source_name | |
| best_oa_location.landing_page_url | http://arxiv.org/abs/2412.11014 |
| primary_location.id | pmh:oai:arXiv.org:2412.11014 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S4306400194 |
| primary_location.source.issn | |
| primary_location.source.type | repository |
| primary_location.source.is_oa | True |
| primary_location.source.issn_l | |
| primary_location.source.is_core | False |
| primary_location.source.is_in_doaj | False |
| primary_location.source.display_name | arXiv (Cornell University) |
| primary_location.source.host_organization | https://openalex.org/I205783295 |
| primary_location.source.host_organization_name | Cornell University |
| primary_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| primary_location.license | |
| primary_location.pdf_url | https://arxiv.org/pdf/2412.11014 |
| primary_location.version | submittedVersion |
| primary_location.raw_type | text |
| primary_location.license_id | |
| primary_location.is_accepted | False |
| primary_location.is_published | False |
| primary_location.raw_source_name | |
| primary_location.landing_page_url | http://arxiv.org/abs/2412.11014 |
| publication_date | 2024-12-15 |
| publication_year | 2024 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 101 |
| abstract_inverted_index.In | 73 |
| abstract_inverted_index.On | 153 |
| abstract_inverted_index.an | 78 |
| abstract_inverted_index.be | 57 |
| abstract_inverted_index.by | 36 |
| abstract_inverted_index.in | 2, 9, 46, 84, 137 |
| abstract_inverted_index.is | 148 |
| abstract_inverted_index.of | 145 |
| abstract_inverted_index.on | 168 |
| abstract_inverted_index.or | 21 |
| abstract_inverted_index.to | 59, 93, 105 |
| abstract_inverted_index.we | 76 |
| abstract_inverted_index.(i) | 29 |
| abstract_inverted_index.Our | 110 |
| abstract_inverted_index.The | 143 |
| abstract_inverted_index.and | 40, 125, 156, 162, 174 |
| abstract_inverted_index.but | 98 |
| abstract_inverted_index.can | 65, 119 |
| abstract_inverted_index.for | 32 |
| abstract_inverted_index.our | 146 |
| abstract_inverted_index.the | 53, 60, 67, 86, 95, 107, 115, 122, 127 |
| abstract_inverted_index.to: | 28 |
| abstract_inverted_index.use | 17 |
| abstract_inverted_index.(ii) | 43 |
| abstract_inverted_index.100% | 172 |
| abstract_inverted_index.LLMs | 4 |
| abstract_inverted_index.also | 99 |
| abstract_inverted_index.code | 11, 132, 141 |
| abstract_inverted_index.each | 91 |
| abstract_inverted_index.form | 94 |
| abstract_inverted_index.from | 52 |
| abstract_inverted_index.have | 5 |
| abstract_inverted_index.lead | 27 |
| abstract_inverted_index.make | 66 |
| abstract_inverted_index.risk | 124 |
| abstract_inverted_index.show | 113 |
| abstract_inverted_index.that | 114 |
| abstract_inverted_index.this | 74 |
| abstract_inverted_index.will | 26, 56 |
| abstract_inverted_index.with | 90 |
| abstract_inverted_index.99.1% | 163 |
| abstract_inverted_index.99.2% | 161 |
| abstract_inverted_index.99.9% | 175 |
| abstract_inverted_index.Error | 44 |
| abstract_inverted_index.Human | 157 |
| abstract_inverted_index.While | 167 |
| abstract_inverted_index.agent | 55 |
| abstract_inverted_index.buggy | 71 |
| abstract_inverted_index.code. | 72 |
| abstract_inverted_index.error | 38, 128, 133 |
| abstract_inverted_index.great | 7 |
| abstract_inverted_index.issue | 31 |
| abstract_inverted_index.other | 92 |
| abstract_inverted_index.which | 25, 64, 85 |
| abstract_inverted_index.while | 130 |
| abstract_inverted_index.RTLLM, | 169 |
| abstract_inverted_index.Recent | 0 |
| abstract_inverted_index.agents | 69, 87 |
| abstract_inverted_index.cannot | 88 |
| abstract_inverted_index.create | 100 |
| abstract_inverted_index.either | 16 |
| abstract_inverted_index.former | 54 |
| abstract_inverted_index.higher | 138 |
| abstract_inverted_index.latter | 61, 68 |
| abstract_inverted_index.paper, | 75 |
| abstract_inverted_index.pass@5 | 177 |
| abstract_inverted_index.reduce | 126 |
| abstract_inverted_index.syntax | 173 |
| abstract_inverted_index.Machine | 155 |
| abstract_inverted_index.Verilog | 10, 140 |
| abstract_inverted_index.agentic | 3 |
| abstract_inverted_index.healthy | 102 |
| abstract_inverted_index.improve | 106 |
| abstract_inverted_index.obtains | 171 |
| abstract_inverted_index.pass@10 | 164 |
| abstract_inverted_index.propose | 77 |
| abstract_inverted_index.quality | 139 |
| abstract_inverted_index.results | 112 |
| abstract_inverted_index.scores, | 165 |
| abstract_inverted_index.scores. | 178 |
| abstract_inverted_index.through | 62, 150 |
| abstract_inverted_index.However, | 13 |
| abstract_inverted_index.achieves | 160 |
| abstract_inverted_index.advances | 1 |
| abstract_inverted_index.approach | 147 |
| abstract_inverted_index.dataset, | 158 |
| abstract_inverted_index.existing | 14 |
| abstract_inverted_index.generate | 70 |
| abstract_inverted_index.mitigate | 121 |
| abstract_inverted_index.prompts, | 63 |
| abstract_inverted_index.quality. | 109 |
| abstract_inverted_index.LLM-based | 79 |
| abstract_inverted_index.detection | 39 |
| abstract_inverted_index.erroneous | 50 |
| abstract_inverted_index.extensive | 151 |
| abstract_inverted_index.framework | 118 |
| abstract_inverted_index.improving | 131 |
| abstract_inverted_index.learning, | 24 |
| abstract_inverted_index.learning: | 34, 49 |
| abstract_inverted_index.mechanism | 104 |
| abstract_inverted_index.pipeline, | 97 |
| abstract_inverted_index.prompting | 20, 82 |
| abstract_inverted_index.resulting | 136 |
| abstract_inverted_index.validated | 149 |
| abstract_inverted_index.approaches | 15 |
| abstract_inverted_index.correction | 41, 134 |
| abstract_inverted_index.diminished | 37 |
| abstract_inverted_index.framework, | 83 |
| abstract_inverted_index.generating | 108 |
| abstract_inverted_index.generation | 96 |
| abstract_inverted_index.propagated | 58 |
| abstract_inverted_index.VerilogEval | 154 |
| abstract_inverted_index.collaborate | 89 |
| abstract_inverted_index.competitive | 103 |
| abstract_inverted_index.coopetitive | 80, 116 |
| abstract_inverted_index.effectively | 120 |
| abstract_inverted_index.generation. | 12, 142 |
| abstract_inverted_index.information | 51 |
| abstract_inverted_index.multi-agent | 23, 48, 81, 117 |
| abstract_inverted_index.propagation | 45, 129 |
| abstract_inverted_index.Degeneration | 30 |
| abstract_inverted_index.LLM-assisted | 18 |
| abstract_inverted_index.capabilities | 8 |
| abstract_inverted_index.degeneration | 123 |
| abstract_inverted_index.demonstrated | 6 |
| abstract_inverted_index.experimental | 111 |
| abstract_inverted_index.experiments. | 152 |
| abstract_inverted_index.single-agent | 19, 33 |
| abstract_inverted_index.capabilities, | 135 |
| abstract_inverted_index.capabilities; | 42 |
| abstract_inverted_index.characterized | 35 |
| abstract_inverted_index.effectiveness | 144 |
| abstract_inverted_index.functionality | 176 |
| abstract_inverted_index.respectively. | 166 |
| abstract_inverted_index.cooperation-only | 22, 47 |
| abstract_inverted_index.CoopetitiveV+GPT-4 | 159, 170 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 5 |
| citation_normalized_percentile |