6 papers
Escaping the Self-Repair Trap: Improving Test Oracle Generation via Dual-Context Awareness
Kefan Li, Hongyue Yu, Yuan Yuan
Large Language Models (LLMs) have shown strong potential for regression-oracle completion, where a test prefix is given and the current program version is treated as expected behav…
Efficient Test-Time Scaling via Temporal Reasoning Aggregation
Jiakun Li, Xingwei He, Kefan Li +3
Test-time scaling improves the reasoning performance of large language models but often results in token-inefficient overthinking, where models continue reasoning beyond what is ne…
IceCache: Memory-efficient KV-cache Management for Long-Sequence LLMs
Yuzhen Mao, Qitong Wang, Martin Ester +1
Key-Value (KV) cache plays a crucial role in accelerating inference in large language models (LLMs) by storing intermediate attention states and avoiding redundant computation duri…
Beyond Fixed Tests: Repository-Level Issue Resolution as Coevolution of Code and Behavioral Constraints
Kefan Li, Yuan Yuan, Mengfei Wang +5
Software engineers resolving repository-level issues do not treat existing tests as immutable correctness oracles. Instead, they iteratively refine both code and the tests used to…
InfCode: Adversarial Iterative Refinement of Tests and Patches for Reliable Software Issue Resolution
KeFan Li, Mengfei Wang, Hengzhi Zhang +7
Large language models have advanced software engineering automation, yet resolving real-world software issues remains difficult because it requires repository-level reasoning, accu…
CoCoEvo: Co-Evolution of Programs and Test Cases to Enhance Code Generation
Kefan Li, Yuan Yuan, Hongyue Yu +2
Large Language Models (LLMs) have shown remarkable performance in automated code generation. However, existing approaches often rely heavily on pre-defined test cases, which become…