Get started
Author

Pin Qian

Observed name: Qian, Pin
Observed institution: Carnegie Mellon University
OpenAlex ID: A5136194164
When Safe Skills Collide: Measuring Compositional Risk in Agent Skill Ecosystems
2026 · Wang, Su, Qian, Pin, et al. · arXiv (Cornell University) · 21
PDF
Relevant Is Not Warranted: Evidence-Force Calibration for Cited RAG
2026 · Pin Qian, Su Wang, et al. · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · 19
PDF
Does RAG Know When Retrieval Is Wrong? Diagnosing Context Compliance under Knowledge Conflict
2026 · Yihang Chen, Pin Qian, et al. · 12
PDF
Phantom Guardrails: When Self-Improving Agent Harnesses Fix Failures That Never Happened
2026 · Wang, Su, Qian, Pin, et al. · arXiv (Cornell University) · 7
PDF
Operational Reframing and Approval-Framed Delegation in Multi-Agent LLM Safety
2026 · Liu, Lifei, Yu, Haoran, et al. · arXiv (Cornell University) · 7
PDF
When Should Active RAG Retrieve? A Budget-Aware Evaluation of Utility, Calibration, and Cost
2026 · Qian, Pin, Wang, Su, et al. · arXiv (Cornell University) · 6
PDF
Toward User-Conditioned Evaluation of Personal LLM Agents under Temporal Interventions
2026 · Qian, Pin, Wang, Su, et al. · arXiv (Cornell University) · 5
PDF
Habituation at the Gate: Rising Approval and Declining Scrutiny in Human Review of AI Agent Code
2026 · Yu, Haoran, Liu, Lifei, et al. · arXiv (Cornell University) · 4
PDF
Beyond Simpson's Paradox: A Cascade of Confounders in AI Agent Pull-Request Co-Authorship
2026 · Yu, Haoran, Jiang, Xiaochong, et al. · arXiv (Cornell University) · 3
PDF
BAP-SQL: Budget-Aware Observation Planning for Agentic Text-to-SQL
2026 · Peng, Chong, Qian, Pin, et al. · arXiv (Cornell University) · 2
PDF
Explicit State Elicitation Is Not Enough: A Controlled Audit of Memory-Policy Classification
2026 · Yihang Chen, Pin Qian, et al. · Workshop for Research on Agent Language Models (REALM) · 2
PDF
Noise Floor Audit for Agent Benchmarks
2026 · Chen, Yihang, Qian, Pin, et al. · arXiv (Cornell University) · 1
PDF
CreepScope: Measuring Post-Use Authorization Exposure in Tool-Using Agents
2026 · Yu, Haoran, Liu, Lifei, et al. · arXiv (Cornell University)
PDF
Works count: 13
Citation count: 89
H-index: 6
I10-index: 3
Year
Topic
Type