Hongxiang Zhang

Purdue, Lafayette, IN, USA.

prof_pic.jpg

Hi, I am Hongxiang Zhang (张鸿翔). I’m a Ph.D. student in the Department of Computer Science at Purdue University, advised by Prof. Tianyi Zhang.

I am looking for research internship positions. Feel free to contact me at hxxzhang@gmail.com.

My research focuses on reliable and efficient AI systems, with an emphasis on LLM reasoning, multi-agent communication, hallucination mitigation, and AI for code. I am broadly interested in robust agentic workflows that combine alignment, decoding, and lightweight diagnostic methods across software engineering, security, and generative AI applications.

News

May 27, 2026 Check out our new work FLARE, an efficient LLM code-refinement framework that uses lightweight fault localization to guide targeted repairs.
Apr 27, 2026 Check out our new work AGENT-RADAR, a training-free attention steering method for multi-agent systems that improves context management and inter-agent coordination.
Feb 27, 2026 Check out our new work Attention-Aligned Reasoning, a reasoning-time alignment method that keeps LLMs focused on prompts and intermediate goals through step-by-step attention alignment.
Jan 06, 2026 Our work LLAMAFUZZ: Large Language Model Enhanced Greybox Fuzzing has been accepted to AST 2026.
Oct 03, 2025 Check out the project page for our work Active Layer-Contrastive Decoding Reduces Hallucination in Large Language Model Generation.

Selected Publications

  1. agent-radar.png
    Enhancing Multi-Agent Communication through Attention Steering with Context Relevance
    Multi-agent systems; Attention Alignment; Context Management
    Hongxiang Zhang, Yuan Tian, and Tianyi Zhang
    2026
    Under review
    arXiv
  2. flare.png
    FLARE: Fine-Grained Diagnostic Feedback for LLM Code Refinement
    Code Refinement; Fault Localization; Test-time Scaling
    Yinsheng Yao, Hongxiang Zhang, Weixi Tong, and 1 more author
    2026
    Under review
    arXiv
  3. attention_aligned_reasoning.png
    Attention-Aligned Reasoning for Large Language Models
    LLM Reasoning; Attention Alignment; Prompt Engineering
    Hongxiang Zhang, Yuan Tian, and Tianyi Zhang
    arXiv preprint arXiv:2510.03223, 2025
    Under review
    arXiv
  4. actlcd.png
    Active Layer-Contrastive Decoding Reduces Hallucination in Large Language Model Generation
    Hallucination Mitigation; Decoding; Reinforcement Learning
    Hongxiang Zhang, Hao Chen, Muhao Chen, and 1 more author
    In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025
    EMNLP 2025 Main
    arXiv Code Website
  5. llamafuzz.png
    LLAMAFUZZ: Large Language Model Enhanced Greybox Fuzzing
    LLM for Systems; Greybox Fuzzing; Software Testing
    Hongxiang Zhang, Yuyang Rong, Yifeng He, and 1 more author
    In Proceedings of the 2026 IEEE/ACM International Conference on Automation of Software Test, 2026
    AST 2026
    arXiv
  6. SteerDiff: Steering towards Safe Text-to-Image Diffusion Models
    Safe Generative AI; Prompt Steering; Diffusion Models
    Hongxiang Zhang, Yifeng He, and Hao Chen
    2024
    arXiv