AOEB: Benchmarking Agent-Oriented Multimodal Embeddings
ICML 2026
Evaluating multimodal embeddings against the retrieval needs of LLM agents, including code, tools, reasoning, and memory.

I’m a master’s student in Computer Technology at Harbin Institute of Technology, Shenzhen, advised by 我目前在哈尔滨工业大学(深圳)攻读计算机技术硕士学位,导师是Prof. Meishan Zhang张梅山教授.。
My research focuses on information retrieval for LLM agents, particularly efficient reranking, agent-oriented evaluation, and long-horizon memory retrieval.我的研究聚焦于面向大语言模型智能体的信息检索,尤其是高效重排序、面向智能体的评测,以及长程记忆检索。
ICML 2026
Evaluating multimodal embeddings against the retrieval needs of LLM agents, including code, tools, reasoning, and memory.
Preprint, 2026
An efficient reranker that separates offline passage encoding from online query processing while retaining expressive cross-attention.
Preprint, 2026
A benchmark for long-horizon memory retrieval: 22 datasets and 193 retrieval tasks spanning episodic, dialogue, semantic, and procedural memory.
Harbin Institute of Technology, Shenzhen哈尔滨工业大学(深圳)