Skip to content

Author

Huaimin Wang

We have 3 of 63 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.

Preprint Jul 2026

MCPEvol-Bench: Benchmarking LLM Agent Performance Across Dynamic Evolutions of MCP Servers

A novel benchmark for evaluating the task-solving capabilities of LLM agents under dynamic toolset evolution, and proposes 11 mutation operators to simulate realistic tool evolution within 123 MCP servers, establishing MCPEvol-Bench as a standard for evaluating agent adaptability in dynamic tool environments.

Huanxi Liu, Kun Hu, Jiaqi Liao et al. · 0 citations
Review Jul 2026

From Objectives to Applications: Aligning Architectural Biases in Audio Self-Supervised Learning

This paper examines audio self-supervised learning through the alignment between pretraining objectives, architectural inductive biases, and downstream applications, and relates these demands to the biases of CNNs, recurrent and State Space Models, Transformers, and hybrid architectures.

Kele Xu, Yu Fang, Boda Zhou et al. · 0 citations
Preprint Aug 2026

ReFrame: Evidence-Guided Test-Time Safety Alignment in Multimodal Large Language Models

ReFrame is a training-free multimodal input reframing framework where two agents share a lightweight locally deployed MLLM: the evidence-generation agent constructs complementary risk and utility evidence, and the rewrite-and-routing agent converts it into a safe proxy prompt and image-routing decision before calling the downstream MLLM, without modifying it or accessing its internal information.

Wenzheng Jiang, Xuankun Rong, Yuanzhao Zhai et al. · 0 citations