Research — Quan Liu

I'm Quan Liu, an LLM & agent research scientist and tech lead at Accenture's Center for Advanced AI. I build production-grade multi-agent systems — the kind that have to keep working past the demo.

My research and engineering sit at the intersection of agent orchestration, tool use (MCP-style grounding), retrieval, and post-training alignment. As a founding member of our agentic systems team, I lead a team building a coding agent and an automated agent-generation pipeline, and I've contributed core features to AIRefinery, Accenture's enterprise agent platform. I publish on tool-using agents and LLM unlearning at venues like ICLR and NeurIPS.

I did my Ph.D. in Computer Science at Vanderbilt University. If any of this overlaps with what you're working on, I'd love to talk.

Areas

Research interests

Bibliography

Publications

Clustered by year, 2023–present — from LLM agents and unlearning to medical imaging and computational vision. First-author papers are flagged.

All on Google Scholar

2026

ICLR 2026 · NeurIPS 2025 Workshop

MCP-Bench: Benchmarking Tool-Using LLM Agents with Complex Real-World Tasks via MCP Servers

Zhenting Wang, Qi Chang, Hemani Patel, Shashank Biju, Cheng-En Wu, Quan Liu, Aolin Ding, Alireza Rezazadeh, Ankit Shah, Yujia Bao, Eugene Siow

ICLR 2026

DRAGON: Guard LLM Unlearning in Context via Negative Detection and Reasoning

Yaxuan Wang, Chris Yuhao Liu, Quan Liu, Jinglong Pang, Wei Wei, Yujia Bao, Yang Liu

2025

arXiv preprint

PromptBridge: Cross-Model Prompt Transfer for Large Language Models

Yaxuan Wang, Quan Liu, Zhenting Wang, Zichao Li, Wei Wei, Yang Liu, Yujia Bao

ICLR 2025

LLM Unlearning via Loss Adjustment with Only Forget Data

Yaxuan Wang, Jiaheng Wei, Chris Yuhao Liu, Jinlong Pang, Quan Liu, Ankit Parag Shah, Yujia Bao, Yang Liu, Wei Wei