7 papers
Rethinking Code Performance Benchmarks for LLMs
Nhat Minh Le, Yisen Xu, Zhijie Wang +2
Many function-level performance benchmarks have been proposed to evaluate whether large language models (LLMs) can generate efficient programs. However, results on these benchmarks…
LogSemFuse: Semantic Evidence Fusion for Explainable Log Anomaly Detection
Hassan Jabri, Zeyang Ma, Zhijie Wang +1
Log anomaly detection is critical for reliability monitoring and failure diagnosis in modern software systems. Existing model-based detectors provide useful anomaly signals, but th…
OpenRath: Session-Centered Runtime State for Agent Systems
Fukang Wen, Zhijie Wang, Ruilin Xu
Modern agent systems often suffer from fragmented runtime state: transcripts, tool effects, memory events, workspace placement, branch provenance, and replay evidence are recorded…
vLLM Semantic Router: Signal Driven Decision Routing for Mixture-of-Modality Models
Xunzhuo Liu, Huamin Chen, Samzong Lu +30
As large language models (LLMs) diversify across modalities, capabilities, and cost profiles, the problem of intelligent request routing: selecting the right model for each query a…
FALAT: Tracing Failures in LLM Agent Trajectories via Dependency-Guided Search
Md Nakhla Rafi, Md Ahasanuzzaman, Dong Jae Kim +2
LLM-based agents increasingly solve complex tasks through long trajectories involving reasoning steps, tool calls, and inter-agent communication. However, when these agents fail, i…
RaSA: Rank-Sharing Low-Rank Adaptation
Zhiwei He, Zhaopeng Tu, Xing Wang +7
Low-rank adaptation (LoRA) has been prominently employed for parameter-efficient fine-tuning of large language models (LLMs). However, the limited expressive capacity of LoRA, stem…