arXiv AI
VeriTrace: Evolving Mental Models for Deep Research Agents
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Computation and Language
Sep 30
DeepRewind: Predicting and Repairing Premature Commitments in Deep Research Agents
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...
arXiv Computation and Language
Aug 27
Mind2Report: Expert-Level Commercial Report Synthesis via Cognitive Deep Research Agent
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 AI
Oct 1
DAGent: Evaluate-then-Grow Planning for Deep Research Agents
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 Computation and Language
Oct 27
RIVO: Lightweight Adaptive Rerouting for Deep Research Agents
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 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.
arXiv AI
Sep 25
IDRBench: Benchmarking the Interactive Capabilities of Deep Research Agents
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.