4 papers
Diagnose Before You Compress: Prediction-Independent Bottleneck Witness Refinement for LLM Serving Traces
Liming Liu, Chao Hu, Mingfei Lu +7
Production LLM serving generates millions of diverse requests, making full-trace replay across serving configurations increasingly expensive. Existing trace reduction methods mainl…
Evaluating Privilege Usage of Agents with Real-World Tools
Quan Zhang, Lianhang Fu, Lvsi Lian +5
Equipping LLM agents with real-world tools can substantially improve productivity. However, granting agents autonomy over tool use also transfers the associated privileges to both…
LSPRAG: LSP-Guided RAG for Language-Agnostic Real-Time Unit Test Generation
Gwihwan Go, Quan Zhang, Chijin Zhou +2
Automated unit test generation is essential for robust software development, yet existing approaches struggle to generalize across multiple programming languages and operate within…
Inducing Vulnerable Code Generation in LLM Coding Assistants
Binqi Zeng, Quan Zhang, Chijin Zhou +3
Due to insufficient domain knowledge, LLM coding assistants often reference related solutions from the Internet to address programming problems. However, incorporating external inf…