Skip to content

Author

Mingxuan Du

We have 6 of 13 papers

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.

Jul 2026

BM25 Wins at Scale: A Scaling Study of Retrieval-Augmented Generation Paradigms

Overall, corpus growth increasingly favors global candidate ranking: lexical retrieval is the strongest scalable default, while agentic reasoning works best after ranked discovery rather than in place of it.

Pengyu Wang, Benfeng Xu, Shaohan Wang et al. · 1 citation
Jul 2026

Beyond Borrowed Histories: Person-Aligned User Simulation for Interactive Role-Playing Evaluation

Role-playing agents (RPAs) have become one of the most important consumer applications of large language models. Users engage in multi-turn conversations with RPAs for experiences such as emotional comfort, making reliable evaluation essential for measuring capability, comparing systems, and guiding further improvement...

Yuhan Zhu, Ming-Xuan Du, Benfeng Xu et al. · 0 citations
Preprint Aug 2026

When Your Agent Opens the Chat App: Agent-Controlled Search over Raw Chat Logs Rivals Structured Memory

The results indicate that for precise, evidence-grounded questions over chat archives, much of the benefit credited to elaborate memory structures is recoverable by giving an agent controllable search over the unmodified record, with no LLM-based index construction at all.

Ruizhe Li, L. Zhang, Benfeng Xu et al. · 1 citation
Book Open access Jul 2026

GraphSynthQA: Knowledge-Graph-Guided Query Synthesis and Step-Level Preference Optimization for Web Agents

GraphSynthQA, a knowledge-graph)—guided synthesis framework in an open-web setting, which iteratively retrieves and verifies evidence from the internet to expand a KG, then synthesizes complex, answer-verifiable queries grounded in multi-evidence dependencies.

Chiwei Zhu, Mingxuan Du, Benfeng Xu et al. · 0 citations
Jul 2026

Keep It InMind: Benchmarking the Implicit-Association Blind Spot in Agent Memory

This work introduces InMind, a 125-task, expert-verified benchmark spanning ten life domains, with 113 tasks grounded in citable public sources, and calls this failure mode the implicit-association blind spot, and introduces a minimal diagnostic probe that keeps memory visible before the query arrives recovers most of...

Ruizhe Li, Mingxuan Du, Benfeng Xu et al. · 0 citations
Jul 2026

MPIE-Bench: Benchmarking Anatomically Plausible Multi-Person Interaction Editing

This work introduces MPIE-Bench, a 2,500-sample benchmark of video-mined editing triplets spanning 405 scenes, 14 interaction categories, and four contact densities, and proposes MPIE-Eval, whose two new axes score contact-time geometry from a frozen public multi-person mesh reconstruction.

Jiajia Lin, Mingxuan Du, Tuowen Zhou et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.