Pith. sign in

REVIEW 23 cited by

Deep Research: A Survey of Autonomous Research Agents

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2508.12752 v1 pith:RTG2365K submitted 2025-08-18 cs.IR

Deep Research: A Survey of Autonomous Research Agents

classification cs.IR
keywords researchdeepagentscapablechallengesllmsplanningsurvey
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original 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.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 23 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Benchmarking AI Agents for Addressing Scientific Challenges Across Scales

    cs.AI 2026-06 unverdicted novelty 7.0

    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.

  2. VeriTrip: A Verifiable Benchmark for Travel Planning Agents over Unstructured Web Corpora

    cs.AI 2026-05 unverdicted novelty 7.0

    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.

  3. Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis

    cs.CL 2026-04 unverdicted novelty 7.0

    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.

  4. Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis

    cs.CL 2026-04 unverdicted novelty 7.0

    DataPRM is a new process reward model for data analysis agents that detects silent errors via environment interaction and ternary rewards, yielding 7-11% gains on benchmarks and further RL improvements.

  5. GTA-2: Benchmarking General Tool Agents from Atomic Tool-Use to Open-Ended Workflows

    cs.CL 2026-04 conditional novelty 7.0

    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.

  6. One Reflection Is Not Enough: Self-Correcting Autonomous Research via Multi-Hypothesis Failure Attribution

    cs.AI 2026-06 unverdicted novelty 6.0

    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.

  7. Understanding and Evaluating Claw-like Agent Security Through a Computer-Systems Lens

    cs.CR 2026-06 unverdicted novelty 6.0

    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.

  8. SkillHone: A Harness for Continual Agent Skill Evolution Through Persistent Decision History

    cs.LG 2026-06 conditional novelty 6.0

    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.

  9. Search-Time Contamination in Deep Research Agents: Measuring Performance Inflation in Public Benchmark Evaluation

    cs.CR 2026-06 unverdicted novelty 6.0

    Deep research agents exhibit widespread search-time contamination on six public benchmarks, with three defined leakage types inflating performance by up to 4%.

  10. Helicase: Uncertainty-Guided Supply Chain Knowledge Graph Construction with Autonomous Multi-Agent LLMs

    cs.AI 2026-05 unverdicted novelty 6.0

    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.

  11. Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents

    cs.AI 2026-05 unverdicted novelty 6.0

    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.

  12. MemSearch-o1: Empowering Large Language Models with Reasoning-Aligned Memory Growth in Agentic Search

    cs.IR 2026-04 unverdicted novelty 6.0

    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.

  13. MemSearch-o1: Empowering Large Language Models with Reasoning-Aligned Memory Growth in Agentic Search

    cs.IR 2026-04 unverdicted novelty 6.0

    MemSearch-o1 uses reasoning-aligned memory growth from seed tokens, retracing via contribution functions, and path reorganization to mitigate memory dilution in LLM agentic search.

  14. TREX: Automating LLM Fine-tuning via Agent-Driven Tree-based Exploration

    cs.AI 2026-04 unverdicted novelty 6.0

    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.

  15. SkillHone: A Harness for Continual Agent Skill Evolution Through Persistent Decision History

    cs.LG 2026-06 unverdicted novelty 5.0

    SkillHone introduces a harness that maintains persistent decision histories to support continual evolution of language-model agent skills, reporting 15.8-point gains on GAIA over a commercial deep-research agent.

  16. DuMate-DeepResearch: An Auditable Multi-Agent System with Recursive Search and Rubric-Grounded Reasoning

    cs.AI 2026-06 unverdicted novelty 5.0

    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.

  17. Unsupervised Skill Discovery for Agentic Data Analysis

    cs.AI 2026-06 unverdicted novelty 5.0

    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.

  18. ViDR: Grounding Multimodal Deep Research Reports in Source Visual Evidence

    cs.CV 2026-05 unverdicted novelty 5.0

    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.

  19. Personalized Deep Research: A User-Centric Framework, Dataset, and Hybrid Evaluation for Knowledge Discovery

    cs.IR 2026-05 conditional novelty 5.0

    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.

  20. MemOCR: Layout-Aware Visual Memory for Efficient Long-Horizon Reasoning

    cs.AI 2026-01 unverdicted novelty 5.0

    MemOCR renders structured memory as images with adaptive visual density to improve long-horizon reasoning under tight context budgets.

  21. VaseMuseum: Digital Intelligent Museum for Ancient Greek Pottery

    cs.CV 2026-07 conditional novelty 4.0

    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 ...

  22. BioInsight: Multi-Agent Orchestration for Interactive Biomedical Knowledge Discovery

    cs.AI 2026-06 unverdicted novelty 4.0

    BioInsight is a multi-agent system that generates interactive, provenance-preserving biomedical evidence interfaces from disease names and protein data.

  23. Lifelong In-Context Learning with Transformers Requires Parametric Forms of Attention

    cs.LG 2026-06 unverdicted novelty 3.0

    Argues that parametric attention forms are necessary for lifelong in-context learning in transformers to maintain constant memory footprint over arbitrary sequence lengths.