2 papers
cs.SE2026
From Empirical Evaluation to Context-Aware Enhancement: Repairing Regression Errors with LLMs
Anh Ho, Thanh Le-Cong, Bach Le +1
[...] Since then, various APR approaches, especially those leveraging the power of large language models (LLMs), have been rapidly developed to fix general software bugs. Unfortuna…
cs.PL2026
Uniqueness is Separation
Liam O'Connor, Pilar Selene Linares Arevalo, Christine Rizkallah
Value independence is enormously beneficial for reasoning about software systems at scale. These benefits carry over into the world of formal verification. Reasoning about programs…