#agent

DeskCraft: Benchmarking Desktop Agents on Professional Workflows and Human-in-the-Loop Collaboration

2026-06-01 Wenkai Wang*, Tao Xiong*, Jingchen Ni*, Yunpeng Bao*, Xiyun Li, Tianqi Liu, Hongcan Guo, Zilong Huang, Shengyu Zhang Under review at EMNLP 2026 (THU-A)

#Agent #GUI #Benchmark

A desktop GUI agent benchmark targeting long-horizon professional workflows and proactive human-agent collaboration.

View

Cognitive Kernel-Pro: A Framework for Deep Research Agents and Agent Foundation Models Training

2026-04-01 Tianqing Fang, Zhisong Zhang, Xiaoyang Wang, Rui Wang, Can Qin, Yuxuan Wan, Jun-Yu Ma, Ce Zhang, Jiaqi Chen, Xiyun Li, Yonglin Wang, Jingchen Ni, Tianshi Zheng, Chun Chen, Wenhao Yu, Zhenwen Liang, Hongming Zhang, Haitao Mi, Dong Yu Technical Report 2026

#Agent #Framework #Open Source

A fully open-source multi-module agent framework for deep research agents and agent foundation models training.

View

AdaMem: Adaptive User-Centric Memory for Long-Horizon Dialogue Agents

2026-03-01 Shannan Yan*, Jingchen Ni*, Leqi Zheng, Jiajun Zhang, Peixi Wu, Dacheng Yin, Jing Lyu, Chun Yuan, Fengyun Rao Under review at EMNLP 2026 (THU-A)

#Agent #Memory #Dialogue

An adaptive user-centric memory framework for long-horizon dialogue agents.

View

Natural-Language Agent Harnesses

2026-03-01 Linyue Pan, Lexiao Zou, Shuo Guo, Jingchen Ni, Hai-Tao Zheng Under review at NeurIPS 2026 (CCF-A)

#Agent #NLP #Framework

Externalizing agent harness control logic as portable natural-language artifacts with a shared runtime.

View

Alibaba Cloud Data+AI Global Challenge — Research Agent Track

#Agent #Competition #LLM

Built an end-to-end Research Agent achieving 4th place out of 1,028 teams.

View