{
  "date": "2026-10-01",
  "papers": [
    {
      "url": "https://arxiv.org/abs/2603.01152",
      "title": "DeepResearch-9K: A Challenging Benchmark Dataset of Deep-Research Agent",
      "authors": "Tongzhou Wu, Yuhao Wang, Xinyu Ma, Xiuqiang He, Shuaiqiang Wang, Dawei Yin, Xiangyu Zhao",
      "date": "2026-03-03",
      "abstract": "Deep-research agents are capable of executing multi-step web exploration, targeted retrieval, and sophisticated question answering. Despite their powerful capabilities, deep-research agents face two critical bottlenecks: (1) the lack of large-scale, challenging datasets with real-world difficulty, and (2) the absence of accessible, open-source frameworks for data synthesis and agent training. To bridge these gaps, we first construct DeepResearch-9K, a large-scale challenging dataset specifically designed for deep-research scenarios built from open-source multi-hop question-answering (QA) datasets via a low-cost autonomous pipeline."
    },
    {
      "url": "https://arxiv.org/abs/2606.02060",
      "title": "Where Do Deep-Research Agents Go Wrong? Span-Level Error Localization in Agent Trajectories",
      "authors": "Jiaming Wang, Ziteng Feng, Jiangtao Wu, Ruihao Li, Qianqian Xie, Yuxiang Ren, He Zhu, Xueming Han, Fanyu Meng, Junlan Feng, Jiaheng Liu",
      "date": "2026-06-03",
      "abstract": "Deep-research agents solve tasks through long trajectories of search, tool use, evidence inspection, and answer synthesis. Evaluation based on final answers shows whether an agent succeeds, but not which parts of the trajectory make the answer unreliable. We study span-level error localization for deep-research agents. We collect 2,790 real trajectories from two agent frameworks, three backbone models, and three benchmarks, convert raw logs into semantic spans, and annotate harmful error spans through LLM-assisted expert review."
    },
    {
      "url": "https://arxiv.org/abs/2504.03160",
      "title": "DeepResearcher: Scaling Deep Research via Reinforcement Learning in Real-world Environments",
      "authors": "Yuxiang Zheng, Dayuan Fu, Xiangkun Hu, Xiaojie Cai, Lyumanshan Ye, Pengrui Lu, Pengfei Liu",
      "date": "2025-04-06",
      "abstract": "Large Language Models (LLMs) equipped with web search capabilities have demonstrated impressive potential for deep research tasks. However, current approaches predominantly rely on either manually engineered prompts (prompt engineering-based) with brittle performance or reinforcement learning within controlled Retrieval-Augmented Generation (RAG) environments (RAG-based) that fail to capture the complexities of real-world interaction. In this paper, we introduce DeepResearcher, the first comprehensive framework for end-to-end training of LLM-based deep research agents through scaling reinforcement learning (RL) in real-world environments with authentic web search interactions."
    },
    {
      "url": "https://arxiv.org/abs/2503.20201",
      "title": "Open Deep Search: Democratizing Search with Open-source Reasoning Agents",
      "authors": "Salaheddin Alzubi, Creston Brooks, Purva Chiniya, Edoardo Contente, Chiara von Gerlach, Lucas Irwin, Yihan Jiang, Arda Kaz, Windsor Nguyen, Sewoong Oh, Himanshu Tyagi, Pramod Viswanath",
      "date": "2025-03-27",
      "abstract": "We introduce Open Deep Search (ODS) to close the increasing gap between the proprietary search AI solutions, such as Perplexity s Sonar Reasoning Pro and OpenAI s GPT-4o Search Preview, and their open-source counterparts. The main innovation introduced in ODS is to augment the reasoning capabilities of the latest open-source LLMs with reasoning agents that can judiciously use web search tools to answer queries."
    },
    {
      "url": "https://arxiv.org/abs/2510.05145",
      "title": "Efficient Tree-Structured Deep Research with Adaptive Resource Allocation",
      "authors": "Lunyiu Nie, Nedim Lipka, Ryan A. Rossi, Swarat Chaudhuri",
      "date": "2025-10-09",
      "abstract": "Deep research agents, which synthesize information across diverse sources, are significantly constrained by the sequential nature of reasoning. This bottleneck results in high latency, poor runtime adaptability, and inefficient resource allocation, making today s deep research systems impractical for interactive applications. To overcome this, we introduce ParallelResearch, a novel framework for efficient deep research that transforms sequential processing into parallel, runtime orchestration by dynamically decomposing complex queries into tree-structured sub-tasks."
    }
  ],
  "repo": {
    "url": "https://github.com/camel-ai/camel",
    "name": "camel-ai/camel",
    "description": "CAMEL: Communicative Agents for \"Mind\" Exploration of Large Language Model Society",
    "graft_analysis_path": "profiles/r-and-d/raw_evidence/camel_graft_map.txt",
    "stats": "1156 files, 8727 symbols, ~2.5M tokens saved via graft"
  }
}