8 citations · 8 across the 4 of their papers we have counts for
7 papers
Token-Budgeted Escalation for Financial Document QA: Cost Is Predictable, Benefit Is the Bottleneck
Junru Zhu, Yixin Yang, Xiaoqing Ding +1
Retrieval-augmented generation systems can route difficult queries to deeper context, but batch deployments must allocate a shared token budget across calls whose costs vary by que…
Failure-Transparent Agents: Benchmarking Post-Failure Reporting in Tool-Using Language Models
Junru Zhu, Shiming Xie, Aime Lu Fan Chen +4
Tool-using agents can fail twice: a required tool can fail, and the agent can then report success without the evidence needed to justify it. Existing benchmarks often entangle this…
Stress-Testing Structure-Aware Calibration of Malware Graph Neural Networks under Type Shift
Junru Zhu, Yixin Yang, Xiaoqing Ding +1
Post-hoc malware calibrators can condition confidence on graph structure, but their structural inputs may leave the support represented by validation data under malware-type shift.…
Partition-Matched Evaluation of Community Features under Distribution Shift in Android Malware Function-Call Graphs
Junru Zhu, Yixin Yang, Xiaoqing Ding +1
Graph-based Android malware classifiers can lose accuracy under malware-type or family shifts. We test whether mesoscopic organization in function-call graphs provides shift-stable…
Residual Community Prototypes Under-Reject Held-Out Malware Families in FCG-MFD
Junru Zhu, Yixin Yang, Xiaoqing Ding +1
Open-set malware-family recognition must classify known families while rejecting families absent from training. We test whether Louvain-community summaries add rejection informatio…
LeaseGuard: Incumbent-Preserving Admission Control for Privileged LLM Agents
Junru Zhu, Yixin Yang, Xiaoqing Ding +1
Privileged language-model agents can satisfy a new system task by displacing a healthy incumbent that depends on the same file, process, socket, lock, or capacity allocation. This…