10 papers
Auditing Escalation Reliability in Healthcare LLM Agents: A Perturbation-Controlled Benchmark of Workflow-State Failures
Zihao Zheng, Junyi Yao, Baichuan Li +1
Trustworthy biomedical AI requires reliable action selection when evidence is missing, stale, conflicting, or late, not only accurate answers on static inputs. We instantiate an ep…
Engineering Reliable Commit Gates for Agentic AI: Cost-Aware Verification Portfolios under Common-Mode Data Failures
Zihao Zheng, Baichuan Li, Junyi Yao +1
Agentic systems commit state-changing actions, but additional verifiers can inherit the same upstream fault. We present VP-CONTROL, a runtime-assurance design and deterministic ben…
Toward Workflow-Aware Benchmarking for Healthcare NLP Agents
Junyi Yao, Baichuan Li, Zihao Zheng +1
Large language model (LLM) agents are increasingly proposed for healthcare tasks such as clinical documentation, evidence retrieval, patient messaging, and care coordination. Yet m…
Reliable Financial Named Entity Recognition Under Domain Shift: Confidence Estimation and Selective Prediction
Zihao Zheng, Baichuan Li, Junyi Yao +1
Financial AI systems often train information extractors on one textual register and deploy them across filings, news, and user-generated content, and standard F1 scores do not indi…
Stale Does Not Mean Unsafe: Guard Precision for Tool-Using LLM Agents under Infrastructure State Races
Zihao Zheng, Jiayu Long, Baichuan Li +1
Tool-using language-model agents increasingly mutate schedulers, data pipelines, object stores, and access-control systems. Between an agent's read and its commit, external state c…
Remember, Verify, or Ask? Evaluating Memory Decisions at Reuse Time
Baichuan Li, Junyi Yao, Zihao Zheng
Persistent memory can personalize an LLM agent, but an incorrect durable update can silently distort future behavior. We study the memory-clarification boundary: whether interactio…
JailMeter: An Evidence-Based Evaluation Framework for Jailbreak Attacks on Large Language Models
Qingjia Huang, Jingyu Zhang, Jianguo Wu +6
The assessment of jailbreak attacks against large language models currently suffers from inconsistent evaluation criteria and methods, leading to unreliable estimates of attack suc…
Execution Realism and Reproducibility in LLM-Based Trading Systems: A Systematic Scoping Review and Evidence Audit
Junyi Yao, Zihao Zheng, Baichuan Li +1
Execution realism remains weakly standardized in research on large-language-model-based trading systems, limiting comparison and reproduction across backtests, simulations, and por…
Beyond Helpfulness: A Teaching-over-Solving Diagnostic for Measuring Educational Impact in LLM Tutors
Junyi Yao, Zihao Zheng, Baichuan Li
Large language models are increasingly proposed as educational tutors, yet stronger task-solving ability does not necessarily imply stronger learning support. Motivated by recent c…
Perturbation Sensitivity of Maximum-Likelihood Pairwise Ranking in Computational Decision Systems
Junyi Yao, Zihao Zheng, Jiayu Long
Maximum-likelihood pairwise ranking is a com- mon computational mechanism for prioritization, reputation estimation, and comparison-driven decision support. Despite its broad use,…