Author

Xun-Zhu Tang

3 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Sep 2026

BMA: Backchain Memory Attacks Create Unauthorized Control Paths in LLM Agents

Persistent memory enables LLM agents to reuse prior experience, but creates a new security boundary: what an agent may remember is not what it should act on. We expose an unauthorized control path where edited low-trust evidence is consolidated into persistent memory, retrieved on a clean task, and used to drive a prot...

Kai-Sheng Fan, Yi-Shu Gao, Xun-Zhu Tang et al. · 0 citations

Preprint Sep 2026

LENS: The Sum Is Worse Than the Parts for Set-Level Poisoning in Retrieval-Augmented Generation

Retrieval-augmented generation (RAG) aggregates evidence from multiple external documents, yet this joint integration creates an underexamined vulnerability: attack effects absent in individual documents can emerge through set-level composition. Existing coordinated attacks do not explicitly enforce that every proper s...

Kai-Sheng Fan, Yi-Shu Gao, Xun-Zhu Tang et al. · 0 citations

#artificial intelligence May 2026

BoostAPR: Boosting Automated Program Repair via Execution-Grounded Reinforcement Learning with Dual Reward Models

BoostAPR is presented, a three-stage framework addressing challenges of supervised fine-tuning on execution-verified demonstrations with reasoning traces, training dual reward models from execution outcomes, and PPO optimization where the line-level model redistributes rewards to critical edit regions.

Yuan-Hao Li, Hong-Bo Wang, Xiaotang Shang et al. · arXiv.org · 3 citations · ⚡1