5 papers
Beyond Accuracy: Diagnosing Algebraic Reasoning Failures in LLMs Across Nine Complexity Dimensions
Parth Patil, Dhruv Kumar, Yash Sinha +1
Algebraic reasoning remains one of the most informative stress tests for large language models, yet current benchmarks provide no mechanism for attributing failure to a specific ca…
Beyond Local Code Optimization: Multi-Agent Reasoning for Software System Optimization
Huiyun Peng, Parth Vinod Patil, Antonio Zhong Qiu +2
Large language models and AI agents have recently shown promise in automating software performance optimization, but existing approaches predominantly rely on local, syntax-driven…
Do Unit Proofs Work? An Empirical Study of Compositional Bounded Model Checking for Memory Safety Verification
Paschal C. Amusuo, Owen Cochell, Taylor Le Lievre +3
Memory safety defects pose a major threat to software reliability, enabling cyberattacks, outages, and crashes. To mitigate these risks, organizations adopt Compositional Bounded M…
Recommending Pre-Trained Models for IoT Devices
Parth V. Patil, Wenxin Jiang, Huiyun Peng +7
The availability of pre-trained models (PTMs) has enabled faster deployment of machine learning across applications by reducing the need for extensive training. Techniques like qua…
A Unit Proofing Framework for Code-level Verification: A Research Agenda
Paschal C. Amusuo, Parth V. Patil, Owen Cochell +2
Formal verification provides mathematical guarantees that a software is correct. Design-level verification tools ensure software specifications are correct, but they do not expose…