SciAgentArena is a new interactive benchmark for AI agents on scientific tasks that finds agents handle clear data-analysis workflows but struggle with novel insights, self-directed exploration, and open-ended questions.
hub
Deep research: A survey of autonomous research agents.arXiv preprint arXiv:2508.12752, 2025a
20 Pith papers cite this work. Polarity classification is still indexing.
20
Pith papers citing it
abstract
The rapid advancement of large language models (LLMs) has driven the development of agentic systems capable of autonomously performing complex tasks. Despite their impressive capabilities, LLMs remain constrained by their internal knowledge boundaries. To overcome these limitations, the paradigm of deep research has been proposed, wherein agents actively engage in planning, retrieval, and synthesis to generate comprehensive and faithful analytical reports grounded in web-based evidence. In this survey, we provide a systematic overview of the deep research pipeline, which comprises four core stages: planning, question developing, web exploration, and report generation. For each stage, we analyze the key technical challenges and categorize representative methods developed to address them. Furthermore, we summarize recent advances in optimization techniques and benchmarks tailored for deep research. Finally, we discuss open challenges and promising research directions, aiming to chart a roadmap toward building more capable and trustworthy deep research agents.
hub tools
citation-role summary
background 3
citation-polarity summary
years
2026 20roles
background 3polarities
background 3representative citing papers
VeriTrip is a new benchmark using a Multimodal Retrieval Base and Verifiable Knowledge Base to evaluate evidence-grounded reasoning and factual reliability in travel planning agents over unstructured multimodal web data.
DataPRM is an environment-aware generative process reward model that improves LLM data analysis agents by 7-11% on benchmarks via active verification and reflection-aware ternary rewards.
GTA-2 benchmark shows frontier models achieve below 50% on atomic tool tasks and only 14.39% success on realistic long-horizon workflows, with execution harnesses like Manus providing substantial gains.
SAGE with MHFA improves failure recovery in autonomous research agents, raising metrics-bearing outputs from 42% to 92% on a 12-topic benchmark versus single-reflection baselines.
The paper introduces SafeClawArena, a 406-task benchmark evaluating security failures in three Claw-like agent platforms across skill supply-chain, state exploitation, data flow, and prompt injection surfaces.
BioInsight is a multi-agent orchestration system that converts disease-associated protein tables into interactive evidence dashboards with typed artifact contracts, improving reported traceability and ranking over baselines given the same retrieved evidence.
Persistent decision history plus role-separated redacted evaluation lets agents continually improve skills across sessions and outperform commercial deep-research and prior skill-evolution baselines.
Deep research agents exhibit widespread search-time contamination on six public benchmarks, with three defined leakage types inflating performance by up to 4%.
Helicase proposes an autonomous multi-agent LLM framework for uncertainty-guided supply chain knowledge graph construction evaluated on the new SCQA benchmark of 80 queries.
Memory-equipped LLM agents exhibit increasing safety violation rates as memory accumulates across independent tasks, termed temporal memory contamination, detected via a new trigger-probe protocol.
MemSearch-o1 mitigates memory dilution in agentic LLM search through reasoning-aligned token-level memory growth, retracing with a contribution function, and path reorganization, improving reasoning activation on benchmarks.
TREX automates the LLM training lifecycle via collaborative agents and tree-based exploration, delivering consistent performance gains across 10 real-world fine-tuning tasks in FT-Bench.
DuMate-DeepResearch introduces a multi-agent deep research system with graph-based planning, recursive execution, and rubric optimization that reports new state-of-the-art scores of 58.03% and 61.95% on two benchmarks.
DataCOPE uses verifier-guided contrastive distillation from agent trajectories to discover skills, yielding average gains of 9.71% on report-style and 32.30% on reasoning-style data analysis tasks across four model settings.
ViDR treats source figures as retrievable and verifiable evidence objects in multimodal deep research reports and introduces MMR Bench+ to measure improvements in visual integration and verifiability.
PDR is a user-context-aware framework for LLM research agents that improves report relevance over static baselines, supported by a new dataset and hybrid evaluation.
MemOCR renders structured memory as images with adaptive visual density to improve long-horizon reasoning under tight context budgets.
VaseMuseum is a training-free multimodal agent that combines DeepResearch-style retrieval, source/response reliability control, and best-of-K reranking to improve citation validity and reduce hallucination for museum VQA on ancient Greek pottery.
Argues that parametric attention forms are necessary for lifelong in-context learning in transformers to maintain constant memory footprint over arbitrary sequence lengths.
citing papers explorer
-
Benchmarking AI Agents for Addressing Scientific Challenges Across Scales
SciAgentArena is a new interactive benchmark for AI agents on scientific tasks that finds agents handle clear data-analysis workflows but struggle with novel insights, self-directed exploration, and open-ended questions.
-
VeriTrip: A Verifiable Benchmark for Travel Planning Agents over Unstructured Web Corpora
VeriTrip is a new benchmark using a Multimodal Retrieval Base and Verifiable Knowledge Base to evaluate evidence-grounded reasoning and factual reliability in travel planning agents over unstructured multimodal web data.
-
Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis
DataPRM is an environment-aware generative process reward model that improves LLM data analysis agents by 7-11% on benchmarks via active verification and reflection-aware ternary rewards.
-
GTA-2: Benchmarking General Tool Agents from Atomic Tool-Use to Open-Ended Workflows
GTA-2 benchmark shows frontier models achieve below 50% on atomic tool tasks and only 14.39% success on realistic long-horizon workflows, with execution harnesses like Manus providing substantial gains.
-
One Reflection Is Not Enough: Self-Correcting Autonomous Research via Multi-Hypothesis Failure Attribution
SAGE with MHFA improves failure recovery in autonomous research agents, raising metrics-bearing outputs from 42% to 92% on a 12-topic benchmark versus single-reflection baselines.
-
Understanding and Evaluating Claw-like Agent Security Through a Computer-Systems Lens
The paper introduces SafeClawArena, a 406-task benchmark evaluating security failures in three Claw-like agent platforms across skill supply-chain, state exploitation, data flow, and prompt injection surfaces.
-
BioInsight: Multi-Agent Orchestration for Interactive Biomedical Knowledge Discovery
BioInsight is a multi-agent orchestration system that converts disease-associated protein tables into interactive evidence dashboards with typed artifact contracts, improving reported traceability and ranking over baselines given the same retrieved evidence.
-
SkillHone: A Harness for Continual Agent Skill Evolution Through Persistent Decision History
Persistent decision history plus role-separated redacted evaluation lets agents continually improve skills across sessions and outperform commercial deep-research and prior skill-evolution baselines.
-
Search-Time Contamination in Deep Research Agents: Measuring Performance Inflation in Public Benchmark Evaluation
Deep research agents exhibit widespread search-time contamination on six public benchmarks, with three defined leakage types inflating performance by up to 4%.
-
Helicase: Uncertainty-Guided Supply Chain Knowledge Graph Construction with Autonomous Multi-Agent LLMs
Helicase proposes an autonomous multi-agent LLM framework for uncertainty-guided supply chain knowledge graph construction evaluated on the new SCQA benchmark of 80 queries.
-
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents
Memory-equipped LLM agents exhibit increasing safety violation rates as memory accumulates across independent tasks, termed temporal memory contamination, detected via a new trigger-probe protocol.
-
MemSearch-o1: Empowering Large Language Models with Reasoning-Aligned Memory Growth in Agentic Search
MemSearch-o1 mitigates memory dilution in agentic LLM search through reasoning-aligned token-level memory growth, retracing with a contribution function, and path reorganization, improving reasoning activation on benchmarks.
-
TREX: Automating LLM Fine-tuning via Agent-Driven Tree-based Exploration
TREX automates the LLM training lifecycle via collaborative agents and tree-based exploration, delivering consistent performance gains across 10 real-world fine-tuning tasks in FT-Bench.
-
DuMate-DeepResearch: An Auditable Multi-Agent System with Recursive Search and Rubric-Grounded Reasoning
DuMate-DeepResearch introduces a multi-agent deep research system with graph-based planning, recursive execution, and rubric optimization that reports new state-of-the-art scores of 58.03% and 61.95% on two benchmarks.
-
Unsupervised Skill Discovery for Agentic Data Analysis
DataCOPE uses verifier-guided contrastive distillation from agent trajectories to discover skills, yielding average gains of 9.71% on report-style and 32.30% on reasoning-style data analysis tasks across four model settings.
-
ViDR: Grounding Multimodal Deep Research Reports in Source Visual Evidence
ViDR treats source figures as retrievable and verifiable evidence objects in multimodal deep research reports and introduces MMR Bench+ to measure improvements in visual integration and verifiability.
-
Personalized Deep Research: A User-Centric Framework, Dataset, and Hybrid Evaluation for Knowledge Discovery
PDR is a user-context-aware framework for LLM research agents that improves report relevance over static baselines, supported by a new dataset and hybrid evaluation.
-
MemOCR: Layout-Aware Visual Memory for Efficient Long-Horizon Reasoning
MemOCR renders structured memory as images with adaptive visual density to improve long-horizon reasoning under tight context budgets.
-
VaseMuseum: Digital Intelligent Museum for Ancient Greek Pottery
VaseMuseum is a training-free multimodal agent that combines DeepResearch-style retrieval, source/response reliability control, and best-of-K reranking to improve citation validity and reduce hallucination for museum VQA on ancient Greek pottery.
-
Lifelong In-Context Learning with Transformers Requires Parametric Forms of Attention
Argues that parametric attention forms are necessary for lifelong in-context learning in transformers to maintain constant memory footprint over arbitrary sequence lengths.