arXiv AI June 19, 2026 By Wei Yu, Suxing Liu, Minjie Yu, Jiahao Wang, Zhijian Zheng, Haocheng Deng, Bing Li

MetaResearcher: Scaling Deep Research via Self-Reflective Reinforcement Learning in Adversarial Virtual Environments

arXiv:2606. 19893v1 Announce Type: new Abstract: Deep research agents have demonstrated remarkable capabilities in autonomous information gathering and synthesis, yet their training remains constrained by the static nature of simulated environments, the limits of fact-retrieval-only task designs, and the inefficiency of outcome-based reinforcement learning.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

arXiv AI

Jun 4

Self-Evolving Deep Research via Joint Generation and Evaluation

arXiv:2606. 04507v1 Announce Type: cross Abstract: Large Language Models (LLMs) have become increasingly adopted in daily applications, with deep research standing out as a particularly important capability.

By Han Zhu, Chengkun Cai, Yuanfeng Song, Xing Chen, Sirui Han, Yike Guo

llms agents reinforcement-learning benchmarks

arXiv AI

Jul 24

AREX: Towards a Recursively Self-Improving Agent for Deep Research

arXiv:2607. 21461v1 Announce Type: new Abstract: Deep research requires agents to find answers that jointly satisfy multiple constraints.

By Shuqi Lu, Chaofan Li, Kun Luo, Zhang Zhang, Hui Wang, Hongwang Xiao, Zheng Liu, Lei Xiong, Jiahao Wang, Sen Wang, Xiyan Jiang, Wanli Li, Yuyang Hu, Hongjin Qian, Bingyu Yan, Ziyi Xia, Yingxia Shao, Kang Liu, Zhicheng Dou, Di He, Chaozhuo Li, Qiwei Ye, Zhongyuan Wang, Zheng Liu

agents reinforcement-learning benchmarks

Hugging Face Trending Papers

Jun 3

Self-Evolving Deep Research via Joint Generation and Evaluation

Large Language Models (LLMs) have become increasingly adopted in daily applications, with deep research standing out as a particularly important capability. Unlike traditional question-answering (QA) tasks, deep research report generation lacks definitive ground-truth, making reward design inherently unverifiable and limiting effective reinforcement learning.

llms agents reinforcement-learning benchmarks

arXiv AI

Jun 16

S1-DeepResearch: Beyond Search, Toward Real-World Long-Horizon Research Agents

arXiv:2606. 15367v1 Announce Type: new Abstract: Deep research agents aim to solve complex knowledge-intensive tasks through long-horizon planning, evidence gathering, reasoning, and report generation.

By Yao Dong, Xinglin Xiao, Liwei Dong, Xinlong Jin, Zhengbo Li, Heng Zhang, Duyun Wang, Nan Xu

agents nlp benchmarks

arXiv Machine Learning

Aug 12

SearchArt: Training Long-Horizon Search Agent with Scalable Synthetic and Verified Task

arXiv:2607. 24850v2 Announce Type: replace-cross Abstract: Recent advances in large language models (LLMs) have enabled search agents to autonomously tackle complex tasks across extended search and reasoning horizons.

By Lang Mei, Xiaohan Yu, Chong Chen, Liyan Liu, Xiangnan Chen, Jinchao Ma, Chao Feng, Li Huang, Siyu Mo, Sichen Kang, Yunkun Xu, Zhihan Yang, Zhujun Xue, Jingren Zhang, Qing He, Yingdi Huang, Hao Jiang, Ziao Ma, Zewei Pan, Minhao Sun, Zhuo Tao, Jinzhao Xiao, Gangtao Xin, Huanyao Zhang, Wenjian Zhang, Jiangshan Zhang, Guojie Zhu, Fangzhou Zou, Jiaxin Mao, Wentao Zhang

llms agents reinforcement-learning fine-tuning benchmarks

arXiv AI

Jun 15

Hybrid Open-Ended Tri-Evolution Makes Better Deep Researcher

arXiv:2606. 13710v1 Announce Type: new Abstract: Deep research and agent evolution serve as de-facto tasks for AI agents in real-world applications toward artificial general intelligence.

By Hongming Piao, Chi Liu, Mengzhuo Chen, Yan Shu, Derek Li, Ying Wei, Bryan Dai

agents reinforcement-learning benchmarks

Related stories

Self-Evolving Deep Research via Joint Generation and Evaluation

AREX: Towards a Recursively Self-Improving Agent for Deep Research

Self-Evolving Deep Research via Joint Generation and Evaluation

S1-DeepResearch: Beyond Search, Toward Real-World Long-Horizon Research Agents

SearchArt: Training Long-Horizon Search Agent with Scalable Synthetic and Verified Task

Hybrid Open-Ended Tri-Evolution Makes Better Deep Researcher