AgenticSZZ reframes bug-inducing commit identification as temporal knowledge graph search navigated by an LLM agent, reporting F1 scores of 0.47-0.79 and up to 34% improvement over prior SZZ methods on three datasets.
Search-based software engineering: Trends, techniques and applications.ACM Computing Surveys (CSUR), 45(1):1–61
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
AdaTrans uses strategy-driven RAG, error-stratified transformation, and multi-stage validation to reach 95.51% mean compilation pass rate and 81.09% solve rate on 104 algorithmic problems with only 1.19% unsafe files.
Constructs infinite 3⁺-parameterized-square-free ternary words and 3⁺-order-preserving-square-free binary words via morphic substitutions, plus reports longest finite ℓ⁺-square-free words under several equivalences.
A hybrid framework uses adaptive bin partitioning, CVAE, multistage oversampling, LDWL loss, and gated fusion to improve performance on imbalanced regression benchmarks.
Proposes autopoietic architectures for self-constructing software as a fundamental shift in the SDLC, leveraging foundation models for autonomous evolution and maintenance.
A research roadmap analyzing the current state of search-based software engineering with foundation models, outlining challenges and directions across three integration aspects.
citing papers explorer
-
AdaTrans: Automated C to Rust Transformation via Error-Adaptive Repair
AdaTrans uses strategy-driven RAG, error-stratified transformation, and multi-stage validation to reach 95.51% mean compilation pass rate and 81.09% solve rate on 104 algorithmic problems with only 1.19% unsafe files.
-
Relaxation of Square-Freeness
Constructs infinite 3⁺-parameterized-square-free ternary words and 3⁺-order-preserving-square-free binary words via morphic substitutions, plus reports longest finite ℓ⁺-square-free words under several equivalences.
-
Hybrid Imbalanced Regression Through Unified Data-Level and Algorithm-Level Balancing
A hybrid framework uses adaptive bin partitioning, CVAE, multistage oversampling, LDWL loss, and gated fusion to improve performance on imbalanced regression benchmarks.
-
Towards Enabling An Artificial Self-Construction Software Life-cycle via Autopoietic Architectures
Proposes autopoietic architectures for self-constructing software as a fundamental shift in the SDLC, leveraging foundation models for autonomous evolution and maintenance.
-
Search-Based Software Engineering and AI Foundation Models: Current Landscape and Future Roadmap
A research roadmap analyzing the current state of search-based software engineering with foundation models, outlining challenges and directions across three integration aspects.