benchmark 1benchmark evaluation 1code language models 1group relative policy optimization 1guide generation 1language models 1learning rate effects 1model scaling 1multimodal learning 1prompt engineering 1representation analysis 1screenshot grounding 1
From the 3 of 7 linked papers with an AI index.
Showing cs.SEShow all
3 papers · 1 filter
cs.SE2026
Auditing and Decomposing Feedback-Driven Evolution in LLM Test Generation under the Oracle Problem
Yunhao Liang, Chengguang Gan, Ruixuan Ying +3
Execution feedback is often treated as a self-verifying signal for improving LLM-generated tests. However, when generated inputs are executed on a single accepted program and its o…
cs.SE2026
Security Tests as Executable Specifications for LLM Code Generation: Benefits, Trade-offs, and Coverage Limits
Yunhao Liang, Chengguang Gan, Ruixuan Ying +3
Large language models (LLMs) can generate functionally useful code that remains vulnerable, while security-focused interventions may break intended behavior. We investigate securit…
cs.SE2026
Do Code Language Models Use Tests? A Behavioral and Representational Study of Test-Driven Code Generation
Yunhao Liang, Chengguang Gan, Ruixuan Ying +3
The paper investigates how code language models respond to test cases in prompts, analyzing whether tests act as executable specifications or merely extra context, and finds that t…