Jun Wu

Towards Domain Generalized Neural Architecture Search via Language-Guided Visual Augmentation

Evidence-in-the-Loop: Trace-Driven Optimization for Customer-Service LLM Agents

The paper contributes three reusable deployment patterns: hybrid RAG evidence construction, multi-channel retrieval and reranking produce auditable FAQ candidates, and trace-driven RAG and reranker improvement, where reranker fine-tuning is evaluated not only for in-domain gain but also for forgetting risk.

SoK: Intent-Oriented Systematization of Multi-Turn LLM Jailbreaks

This work develops a four-part, intent-oriented taxonomy that organizes multi-turn jailbreaks by adversarial intent structure and finds that effectiveness is driven by how deliberately intent is organized across turns rather than by context length or query count.

Stateful Cooperative Agents Safeguarding LLMs Against Evolving Multi-Turn Attacks

This paper presents a proactive defense framework for securing LLMs against evolving multi-turn adversarial attacks that combines disruption, misdirection, and adaptation across successive interaction turns and employs a cooperative multi-agent architecture.