Rango: Adaptive Retrieval-Augmented Proving for Automated Software Verification
-д хадгалсан:
| -д хэвлэсэн: | The Institute of Electrical and Electronics Engineers, Inc. (IEEE) Conference Proceedings (2025), p. 347-359 |
|---|---|
| Үндсэн зохиолч: | |
| Бусад зохиолчид: | , , , , , , , |
| Хэвлэсэн: |
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
|
| Нөхцлүүд: | |
| Онлайн хандалт: | Citation/Abstract |
| Шошгууд: |
Шошго байхгүй, Энэхүү баримтыг шошголох эхний хүн болох!
|
MARC
| LEADER | 00000nab a2200000uu 4500 | ||
|---|---|---|---|
| 001 | 3223972140 | ||
| 003 | UK-CbPIL | ||
| 024 | 7 | |a 10.1109/ICSE55347.2025.00161 |2 doi | |
| 035 | |a 3223972140 | ||
| 045 | 2 | |b d20250101 |b d20251231 | |
| 084 | |a 228229 |2 nlm | ||
| 100 | 1 | |a Thompson, Kyle |u University of California,San Diego,CA,USA | |
| 245 | 1 | |a Rango: Adaptive Retrieval-Augmented Proving for Automated Software Verification | |
| 260 | |b The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |c 2025 | ||
| 513 | |a Conference Proceedings | ||
| 520 | 3 | |a Conference Title: 2025 IEEE/ACM 47th International Conference on Software Engineering (ICSE)Conference Start Date: 2025 April 26Conference End Date: 2025 May 6Conference Location: Ottawa, ON, CanadaFormal verification using proof assistants, such as Coq, enables the creation of high-quality software. However, the verification process requires significant expertise and manual effort to write proofs. Recent work has explored automating proof synthesis using machine learning and large language models (LLMs). This work has shown that identifying relevant premises, such as lemmas and definitions, can aid synthesis. We present Rango, a fully automated proof synthesis tool for Coq that automatically identifies relevant premises and also similar proofs from the current project and uses them during synthesis. Rango uses retrieval augmentation at every step of the proof to automatically determine which proofs and premises to include in the context of its fine-tuned LLM. In this way, Rango adapts to the project and to the evolving state of the proof. We create a new dataset, CoqStoq, of 2,226 open-source Coq projects and 196,929 theorems from GitHub, which includes both training data and a curated evaluation benchmark of well-maintained projects. On this benchmark, Rango synthesizes proofs for 32.0% of the theorems, which is 29% more theorems than the prior state-of-the-art tool Tactician. Our evaluation also shows that Rango adding relevant proofs to its context leads to a 47% increase in the number of theorems proven. | |
| 653 | |a Program verification (computers) | ||
| 653 | |a Theorems | ||
| 653 | |a Large language models | ||
| 653 | |a Automation | ||
| 653 | |a Machine learning | ||
| 653 | |a Synthesis | ||
| 653 | |a Context | ||
| 653 | |a Benchmarks | ||
| 653 | |a Retrieval | ||
| 653 | |a Economic | ||
| 700 | 1 | |a Saavedra, Nuno |u INESC-ID & IST, University of Lisbon,Lisbon,Portugal | |
| 700 | 1 | |a Carrott, Pedro |u Imperial College London,London,UK | |
| 700 | 1 | |a Fisher, Kevin |u University of California,San Diego,CA,USA | |
| 700 | 1 | |a Sanchez-Stern, Alex |u University of Massachusetts,Amherst,MA,USA | |
| 700 | 1 | |a Brun, Yuriy |u University of Massachusetts,Amherst,MA,USA | |
| 700 | 1 | |a Ferreira, Joao F |u INESC-ID & IST, University of Lisbon,Lisbon,Portugal | |
| 700 | 1 | |a Lerner, Sorin |u University of California,San Diego,CA,USA | |
| 700 | 1 | |a First, Emily |u University of California,San Diego,CA,USA | |
| 773 | 0 | |t The Institute of Electrical and Electronics Engineers, Inc. (IEEE) Conference Proceedings |g (2025), p. 347-359 | |
| 786 | 0 | |d ProQuest |t Science Database | |
| 856 | 4 | 1 | |3 Citation/Abstract |u https://www.proquest.com/docview/3223972140/abstract/embedded/7BTGNMKEMPT1V9Z2?source=fedsrch |