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.
DAGent introduces an Evaluate‑then‑Grow planning approach for deep research agents, building directed acyclic graphs incrementally based on confidence and uncertainty from completed tasks. The framework includes a hierarchical context layer for efficient query handling and a structural reinforcement learning component, DAGRPO, that rewards topology‑conditioned execution. Experiments on BrowseComp‑Plus, GAIA, and xbench‑DeepSearch show DAGent outperforming strong baselines across multiple backbones and scaling to large language models.
arXiv:2610.15910v2 Announce Type: replace Abstract: Deep Research agents rely on long-horizon reasoning and iterative tool use to solve complex information-seeking tasks. However, adaptive decision-m...
arXiv:2607. 21461v1 Announce Type: new Abstract: Deep research requires agents to find answers that jointly satisfy multiple constraints.
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:2605.11388v2 Announce Type: replace Abstract: Humans intuitively solve complex problems by flexibly shifting among reasoning modes: they plan, execute, revise intermediate goals, resolve ambigu...
arXiv:2607. 11228v1 Announce Type: cross Abstract: While Large Vision-Language Models (LVLMs) demonstrate remarkable capabilities, they remain highly susceptible to embedded social biases.
Vision-Language Models (VLMs) still struggle on tasks requiring complex visual understanding. We argue that the core issue is not high-level reasoning, but instead failing to locate critical details i...
arXiv:2606. 07603v1 Announce Type: cross Abstract: Large language models (LLMs) exhibit strong reasoning capabilities, yet most LLM-based agents are statically deployed and unable to improve through task interactions.
LOC I (Locator‑Critic) is a training‑free framework that separates visual search from evidence verification in Vision‑Language Models. It uses a Locator agent to propose candidate visual evidence and a Critic agent to assess its relevance, engaging in an iterative refinement loop that progressively improves the evidence until it is sufficient to answer a question. The approach yields state‑of‑the‑art results on several complex visual benchmarks, boosting accuracy for both open‑weight models like Qwen3‑VL and proprietary models such as Gemini 2.5 Pro.
G-ReAct is a reasoning framework that frames deep search as state evolution over a fixed-topology query graph, enabling explicit tracking of search progress and constraint preservation. It generates high-quality trajectories for fine-tuning and provides structured guidance during inference without extra fine-tuning. Experiments show that with only 1.9K generated trajectories, a Qwen3 model achieves strong accuracy on BrowseComp-ZH and XBench, outperforming larger open-source baselines, and consistently improves existing LLMs on deep-search tasks.