arXiv:2607. 20891v1 Announce Type: new Abstract: Deep Research agents extend LLM-based assistants into long-horizon workflows involving planning, retrieval, evidence synthesis, and report generation, yet their reliability in open information environments remains underexplored.
arXiv:2607. 17291v1 Announce Type: new Abstract: Deep research agents increasingly operate over the open web, where relevant records coexist with redundant summaries, outdated reports, and misleading documents.
arXiv:2609.36344v1 Announce Type: new Abstract: Deep-research agents conduct long-horizon investigations through iterative search, evidence evaluation, belief revision, and synthesis. However, they m...
Mind2Report is a cognitive deep research agent designed to produce expert-level commercial reports from large, noisy web sources. It first clarifies detailed commercial intent to build a structured outline, then recursively gathers and validates evidence into a research memory that evolves with the outline, enabling iterative synthesis of comprehensive reports. The authors also introduce QRC‑Eval, a benchmark of 200 real-world commercial tasks, and show through extensive experiments that Mind2Report outperforms existing proprietary and open-source deep research agents, with ablation studies confirming the contribution of each component.
arXiv:2607. 21461v1 Announce Type: new Abstract: Deep research requires agents to find answers that jointly satisfy multiple constraints.
Deep Research Bench II is a new benchmark designed to evaluate Deep Research Agents (DRAs) by requiring them to produce research reports for 132 grounded tasks across 22 domains. Each report is assessed using 9,430 fine‑grained binary rubrics that cover information recall, analysis, and presentation, all derived from expert‑written investigative articles through a rigorous LLM‑plus‑human pipeline. Evaluation of current state‑of‑the‑art DRAs shows that even the best models satisfy fewer than 50% of these rubrics, highlighting a significant gap between automated agents and human experts.
LongCat-DeepResearch is a deep research system that merges an enhanced LongCat model with a multi‑agent workflow to produce comprehensive, evidence‑grounded reports. The workflow separates global planning from detailed investigation, using planning agents to create a ResearchSpec and research agents to draft sections in parallel, followed by targeted local revisions guided by global review. The system achieves strong benchmark scores, including 55.25 on DeepResearchBench and 79.83 on ResearchRubrics, and shows benefits from combining planning perspectives and additional editing for readability.
arXiv:2606. 11337v1 Announce Type: new Abstract: Scientific AI agents increasingly retrieve evidence, reason across sources, and synthesize conclusions used in consequential decisions.
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.
arXiv:2606. 02060v1 Announce Type: new Abstract: Deep-research agents solve tasks through long trajectories of search, tool use, evidence inspection, and answer synthesis.
IDRBench is a benchmark designed to evaluate the interactive capabilities of deep research agents that use large language models. It introduces controlled opportunities for clarification within a common workflow, comparing autonomous and interactive trajectories by measuring task‑specific report alignment and interaction cost. Experiments on 100 tasks with seven LLMs show that interaction consistently improves alignment, though its effectiveness varies depending on the agents’ questions and feedback integration.
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.
arXiv:2606. 05241v1 Announce Type: cross Abstract: Public benchmarks enable fair and reproducible evaluation of LLM reasoning, but they become fragile for deep research agents that actively search the web during inference.