Cover Image

How Far Are We from Genuinely Useful Deep Research Agents?

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhang, Dingling, Zhu, He, Ren, Jincheng, Song, Kangqi, Zhou, Xinran, Feng, Boyu, Liu, Shudong, Luo, Jiabin, Xie, Weihao, Wang, Zhaohui, Qin, Tianrui, Zhu, King, Wang, Yuqing, Chen, Qianben, Jiang, Yuchen Eleanor, Wang, Wei, Liu, Jiaheng, Zhou, Wangchunshu
Format:	Preprint
Published:	2025
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Flash-Searcher: Fast and Effective Web Agents via DAG-Based Parallel Execution
by: Qin, Tianrui, et al.
Published: (2025)

TaskCraft: Automated Generation of Agentic Tasks
by: Shi, Dingfeng, et al.
Published: (2025)

O-Mem: Omni Memory System for Personalized, Long Horizon, Self-Evolving Agents
by: Wang, Piaohong, et al.
Published: (2025)

Search More, Think Less: Rethinking Long-Horizon Agentic Search for Efficiency and Generalization
by: Chen, Qianben, et al.
Published: (2026)

A$^2$FM: An Adaptive Agent Foundation Model for Tool-Aware Hybrid Reasoning
by: Chen, Qianben, et al.
Published: (2025)

ACADREASON: Exploring the Limits of Reasoning Models with Academic Research Problems
by: Gui, Xin, et al.
Published: (2025)

EcoGym: Evaluating LLMs for Long-Horizon Plan-and-Execute in Interactive Economies
by: Hu, Xavier, et al.
Published: (2026)

MiCoTA: Bridging the Learnability Gap with Intermediate CoT and Teacher Assistants
by: Ding, Dongyi, et al.
Published: (2025)

PersonaFeedback: A Large-scale Human-annotated Benchmark For Personalization
by: Tao, Meiling, et al.
Published: (2025)

Towards Faithful and Controllable Personalization via Critique-Post-Edit Reinforcement Learning
by: Zhu, Chenghao, et al.
Published: (2025)

SEAL: Can Saturated Benchmarks Be Revived by LLM-as-a-Meta-Judge?
by: Chen, Jiamin, et al.
Published: (2026)

O-Researcher: An Open Ended Deep Research Model via Multi-Agent Distillation and Agentic RL
by: Yao, Yi, et al.
Published: (2026)

An improved maximum tangential stress criterion for an inclined crack in uniaxial compression considering T‐stress and crack parameter
by: Hongyan Liu, et al.
Published: (2024)

AI PERSONA: Towards Life-long Personalization of LLMs
by: Wang, Tiannan, et al.
Published: (2024)

Chain-of-Agents: End-to-End Agent Foundation Models via Multi-Agent Distillation and Agentic RL
by: Li, Weizhen, et al.
Published: (2025)

PopAlign: Diversifying Contrasting Patterns for a More Comprehensive Alignment
by: Wang, Zekun Moore, et al.
Published: (2024)

Scaling Test-time Compute for LLM Agents
by: Zhu, King, et al.
Published: (2025)

Efficient Agents: Building Effective Agents While Reducing Cost
by: Wang, Ningning, et al.
Published: (2025)

A Centrality-independent Framework for Revealing Genuine Higher-Order Cumulants in Heavy-Ion Collisions
by: Wang, Zhaohui, et al.
Published: (2025)

Oxygen‐Rich Carbon Nitride Quantum Dots Engineered Bismuth Vanadate Photoanode Surface to Achieve Highly Efficient Solar Water Oxidation
by: Ziming Wang, et al.
Published: (2025)

Towards Personalized Deep Research: Benchmarks and Evaluations
by: Liang, Yuan, et al.
Published: (2025)

OAgents: An Empirical Study of Building Effective Agents
by: Zhu, He, et al.
Published: (2025)

Substrate Adaptability Enabled by Remote Noncovalent Interactions: How Far Are We?
by: Yuhao Zhu, et al.
Published: (2025)

How Far Are We From AGI: Are LLMs All We Need?
by: Feng, Tao, et al.
Published: (2024)

Next-to-leading order QCD corrections to electromagnetic production and decay of fully charm tetraquarks
by: Liu, Xinran, et al.
Published: (2025)

La lectura y el aprendizaje de gramática a través de teléfonos móviles
by: Shudong Wang
Published: (2016)

MambaOut: Do We Really Need Mamba for Vision?
by: Yu, Weihao, et al.
Published: (2024)

The AI Hippocampus: How Far are We From Human Memory?
by: Jia, Zixia, et al.
Published: (2026)

Model Editing for LLMs4Code: How Far are We?
by: Li, Xiaopeng, et al.
Published: (2024)

Genuine pair density wave order on the kagome lattice
by: Liu, Han-Yang, et al.
Published: (2026)

The Digital Cybersecurity Expert: How Far Have We Come?
by: Wang, Dawei, et al.
Published: (2025)

A High Precision Time Measurement Method Based on Frequency-domain Phase-Fitting for Nuclear Pulse Detection
by: Wang, Jianjun, et al.
Published: (2024)

FedMP: Tackling Medical Feature Heterogeneity in Federated Learning from a Manifold Perspective
by: Zhou, Zhekai, et al.
Published: (2025)

Feature-Aware One-Shot Federated Learning via Hierarchical Token Sequences
by: Liu, Shudong, et al.
Published: (2026)

Fighting Spurious Correlations in Text Classification via a Causal Learning Perspective
by: Zhou, Yuqing, et al.
Published: (2024)

Agent KB: Leveraging Cross-Domain Experience for Agentic Problem Solving
by: Tang, Xiangru, et al.
Published: (2025)

When MoE Meets Blockchain: A Trustworthy Distributed Framework of Large Models
by: Zhu, Weihao, et al.
Published: (2025)

WildDoc: How Far Are We from Achieving Comprehensive and Robust Document Understanding in the Wild?
by: Wang, An-Lan, et al.
Published: (2025)

Representation Learning for Stack Overflow Posts: How Far are We?
by: He, Junda, et al.
Published: (2023)

Optimization-based Proof of Useful Work: Framework, Modeling, and Security Analysis
by: Cao, Weihang, et al.
Published: (2024)