arXiv Machine Learning June 24, 2026 By Ido Pinto, Yizhak Yisrael Elboher, Haoze Wu, Nina Narodytska, Guy Katz

Not All Invariants Are Equal: Curating Training Data to Accelerate Program Verification with SLMs

Read the original on arXiv Machine Learning →

arXiv:2603. 15510v2 Announce Type: replace Abstract: The synthesis of inductive loop invariants remains a critical bottleneck in automated program verification.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv AI

Aug 11

Quokka: Accelerating Program Verification with LLMs via Invariant Synthesis

arXiv:2509. 21629v4 Announce Type: replace-cross Abstract: Program verification relies on loop invariants, yet automatically discovering strong invariants remains a long-standing challenge.

By Anjiang Wei, Tianran Sun, Tarun Suresh, Haoze Wu, Ke Wang, Alex Aiken

llms fine-tuning benchmarks

arXiv AI

Jun 15

HierSVA: A Data Synthesis Pipeline, Dataset, and Benchmark for LLM-Driven Hierarchical Hardware Formal Verification

arXiv:2606. 13706v1 Announce Type: cross Abstract: We present HierSVA, an integrated suite that combines a pipeline, dataset, and benchmark for LLM-driven hierarchical hardware formal verification.

By Maohua Nie, Jiang Zhu, Jingqun Zhang, Zhichen Zeng, Jiayi Wang, Sibo Zhang, Jialin Wang, C. -J. Richard Shi

llms agents benchmarks

arXiv AI

Jun 4

AlgoVeri: An Aligned Benchmark for Verified Code Generation on Classical Algorithms

arXiv:2602. 09464v2 Announce Type: replace-cross Abstract: Vericoding refers to the generation of formally verified code from rigorous specifications.

By Haoyu Zhao, Ziran Yang, Jiawei Li, Deyuan He, Zenan Li, Chi Jin, Venugopal V. Veeravalli, Aarti Gupta, Sanjeev Arora

llms benchmarks

arXiv Machine Learning

Jul 10

Selective Left-Shift: Turning Test-Time Compute and Difficulty-based Curation into Training Data for Low-Resource Code Generation

arXiv:2607. 07748v1 Announce Type: new Abstract: Large Language Models achieve strong code generation for high resource languages like Python and Java but suffer sharp performance drops on Low-Resource Programming Languages~(LRPLs) such as Julia.

By Didula Samaraweera, Anjana Supun, Srinath Perera

llms reinforcement-learning fine-tuning benchmarks

arXiv AI

Jun 2

T1: Tool-integrated Verification for Test-time Compute Scaling in Small Language Models

arXiv:2504. 04718v2 Announce Type: replace-cross Abstract: Recent studies have demonstrated that test-time compute scaling effectively improves the performance of small language models (sLMs).

By Minki Kang, Jongwon Jeong, Jaewoong Cho

llms efficiency benchmarks

arXiv AI

Jun 16

LLM4RTL: Tool-Assisted LLM for RTL Generation

arXiv:2606. 15500v1 Announce Type: cross Abstract: Large language models (LLMs) have facilitated impressive progress in software engineering, code generation, tooling, and systems.

By Jing Jin, Robert Chu, Ning Yan, Masood S. Mortazavi

llms fine-tuning benchmarks

Related stories

Quokka: Accelerating Program Verification with LLMs via Invariant Synthesis

HierSVA: A Data Synthesis Pipeline, Dataset, and Benchmark for LLM-Driven Hierarchical Hardware Formal Verification

AlgoVeri: An Aligned Benchmark for Verified Code Generation on Classical Algorithms

Selective Left-Shift: Turning Test-Time Compute and Difficulty-based Curation into Training Data for Low-Resource Code Generation

T1: Tool-integrated Verification for Test-time Compute Scaling in Small Language Models

LLM4RTL: Tool-Assisted LLM for RTL Generation