1 citations · 1 across the 15 of their papers we have counts for
18 papers
Understanding and Mitigating Inference-Time Overreliance Using Agentic Memory
Luoxi Tang, Yuqiao Meng, Nilesh Auradkar +3
Agentic memory allows LLM agents to reuse past experience, yet retrieved memories can also distort inference even when they are benign, correctly stored, and appropriately retrieve…
Polar: LLM-Powered Synthesis of Real-World Cyber Evidence for Prioritization and Mitigation
Luoxi Tang, Yuqiao Meng, Ankita Patra +3
Cyber threat analysis increasingly depends on evidence distributed across vendor advisories, vulnerability databases, and threat intelligence sources. Turning these fragmented obse…
When Correct Memory Goes Wrong: Fuzzing Persistent Memory Use in LLM Agents
Yuqiao Meng, Luoxi Tang, Yingxue Zhang +2
Persistent memory helps LLM agents carry information across long interactions, but correct memory can still be used incorrectly when queries change or memory states evolve. Existin…
The Trap of Trajectory: Towards Understanding and Mitigating Spurious Correlations in Agentic Memory
Luoxi Tang, Rupali Rajendra Vaje, Yuqiao Meng +5
Agentic memory enables LLMs to persist information beyond a single context window and reuse it in later decisions, but it also introduces a new vulnerability: spurious correlations…
EquiMem: Calibrating Shared Memory in Multi-Agent Debate via Game-Theoretic Equilibrium
Yuqiao Meng, Sakshi Sunil Narvekar, Luoxi Tang +4
Multi-agent debate (MAD) systems increasingly rely on shared memory to support long-horizon reasoning, but this convenience opens a critical vulnerability: a single corrupted entry…
The Value of Variance: Mitigating Debate Collapse in Multi-Agent Systems via Uncertainty-Driven Policy Optimization
Luoxi Tang, Yuqiao Meng, Joseph Costa +3
Multi-agent debate (MAD) systems improve LLM reasoning through iterative deliberation, but remain vulnerable to debate collapse, a failure type where final agent decisions are comp…
Adversarial Network Imagination: Causal LLMs and Digital Twins for Proactive Telecom Mitigation
Vignesh Sriram, Yuqiao Meng, Luoxi Tang +1
Telecommunication networks experience complex failures such as fiber cuts, traffic overloads, and cascading outages. Existing monitoring and digital twin systems are largely reacti…
Small Agent Group is the Future of Digital Health
Yuqiao Meng, Luoxi Tang, Dazheng Zhang +5
The rapid adoption of large language models (LLMs) in digital health has been driven by a "scaling-first" philosophy, i.e., the assumption that clinical intelligence increases with…
Smart Privacy Policy Assistant: An LLM-Powered System for Transparent and Actionable Privacy Notices
Sriharshini Kalvakuntla, Luoxi Tang, Yuqiao Meng +1
Most users agree to online privacy policies without reading or understanding them, even though these documents govern how personal data is collected, shared, and monetized. Privacy…
SafeGPT: Preventing Data Leakage and Unethical Outputs in Enterprise LLM Use
Pratyush Desai, Luoxi Tang, Yuqiao Meng +1
Large Language Models (LLMs) are transforming enterprise workflows but introduce security and ethics challenges when employees inadvertently share confidential data or generate pol…
RiskBridge: Turning CVEs into Business-Aligned Patch Priorities
Yelena Mujibur Sheikh, Awez Akhtar Khatik, Luoxi Tang +2
Enterprises are confronted with an unprecedented escalation in cybersecurity vulnerabilities, with thousands of new CVEs disclosed each month. Conventional prioritization framework…
Schema-Grounded LLM Extraction for FHIR Patient Digital Twins
Rafael Brens, Yuqiao Meng, Luoxi Tang +1
We revisit the problem of constructing interoperable patient digital twins from unstructured electronic health records (EHRs) and argue that the task is better cast not as a cascad…
Improving Clinical Data Accessibility Through Automated FHIR Data Transformation Tools
Adarsh Pawar, Yuqiao Meng, Luoxi Tang +1
The Fast Healthcare Interoperability Resources (FHIR) standard has emerged as a widely adopted specification for exchanging structured clinical data across healthcare systems. Howe…
POLAR: Automating Cyber Threat Prioritization through LLM-Powered Assessment
Luoxi Tang, Yuqiao Meng, Ankita Patra +3
Large Language Models (LLMs) are intensively used to assist security analysts in counteracting the rapid exploitation of cyber threats, wherein LLMs offer cyber threat intelligence…
Uncovering Vulnerabilities of LLM-Assisted Cyber Threat Intelligence
Yuqiao Meng, Luoxi Tang, Feiyang Yu +4
Large language models (LLMs) are increasingly used to help security analysts manage the surge of cyber threats, automating tasks from vulnerability assessment to incident response.…
Benchmarking LLM-Assisted Blue Teaming via Standardized Threat Hunting
Yuqiao Meng, Luoxi Tang, Feiyang Yu +4
As cyber threats continue to grow in scale and sophistication, blue team defenders increasingly require advanced tools to proactively detect and mitigate risks. Large Language Mode…
From Test-taking to Cognitive Scaffolding: A Pedagogical Diagnostic Benchmark for LLMs on English Standardized Tests
Luoxi Tang, Tharunya Sundar, Yuqiao Meng +7
As large language models (LLMs) are increasingly integrated into educational tools, current evaluations on standardized tests predominantly focus on binary outcome accuracy. Instea…
On the Eligibility of LLMs for Counterfactual Reasoning: A Decompositional Study
Shuai Yang, Qi Yang, Luoxi Tang +4
Counterfactual reasoning has emerged as a crucial technique for generalizing the reasoning capabilities of large language models (LLMs). By generating and analyzing counterfactual…