# Deep Research: A Systematic Survey

arXiv: https://arxiv.org/abs/2512.02038 · HTML: https://mlsanity.com/paper/2512.02038/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Nov 2025.

## Built on by (most cited first, 27 of 27)

- [RubricEM: Meta-RL with Rubric-guided Policy Decomposition beyond Verifiable Rewards](https://mlsanity.com/paper/2605.10899/) (2026)
- [Rethinking Agentic Search with Pi-Serini: Is Lexical Retrieval Sufficient?](https://mlsanity.com/paper/2605.10848/) (2026)
- [Advancing General-Purpose Reasoning Models with Modular Gradient Surgery](https://mlsanity.com/paper/2602.02301/) (2026)
- [ResidualKV: Residual-Based KV Cache Compression for Efficient Long-Context Inference](https://mlsanity.com/paper/2602.08005/) (2026)
- [Diversity Collapse in Multi-Agent LLM Systems: Structural Coupling and Collective Failure in Open-Ended Idea Generation](https://mlsanity.com/paper/2604.18005/) (2026)
- [JADE: Bridging the Strategic-Operational Gap in Dynamic Agentic RAG](https://mlsanity.com/paper/2601.21916/) (2026)
- [LegalOne: A Family of Foundation Models for Reliable Legal Reasoning](https://mlsanity.com/paper/2602.00642/) (2026)
- [DR-Venus: Towards Frontier Edge-Scale Deep Research Agents with Only 10K Open Data](https://mlsanity.com/paper/2604.19859/) (2026)
- [BeamPERL: Parameter-Efficient RL with Verifiable Rewards Specializes Compact LLMs for Structured Beam Mechanics Reasoning](https://mlsanity.com/paper/2603.04124/) (2026)
- [Can Deep Research Agents Retrieve and Organize? Evaluating the Synthesis Gap with Expert Taxonomies](https://mlsanity.com/paper/2601.12369/) (2026)
- [Learning to Retrieve from Agent Trajectories](https://mlsanity.com/paper/2604.04949/) (2026)
- [TVIR: Building Deep Research Agents Towards Text-Visual Interleaved Report Generation](https://mlsanity.com/paper/2606.02320/) (2026)
- [Think Big, Search Small: Where Capacity Matters in Hierarchical Search Agents?](https://mlsanity.com/paper/2607.07548/) (2026)
- [TodoEvolve: Learning to Architect Agent Planning Systems](https://mlsanity.com/paper/2602.07839/) (2026)
- [How Long Reasoning Chains Influence LLMs' Judgment of Answer Factuality](https://mlsanity.com/paper/2604.06756/) (2026)
- [MemoNoveltyAgent: A Historical Research Memory-Aware Agent Workflow for Paper Novelty Assessment](https://mlsanity.com/paper/2603.20884/) (2026)
- [LLM-Oriented Information Retrieval: A Denoising-First Perspective](https://mlsanity.com/paper/2605.00505/) (2026)
- [MetaResearcher: Scaling Deep Research via Self-Reflective Reinforcement Learning in Adversarial Virtual Environments](https://mlsanity.com/paper/2606.19893/) (2026)
- [SearchJev: A Fast and Calibrated System-1 Model for Search Agents](https://mlsanity.com/paper/2610.05107/) (2026)
- [Knowledge Integration Decay in Search-Augmented Reasoning of Large Language Models](https://mlsanity.com/paper/2602.09517/) (2026)
- [Story2Proposal: A Scaffold for Structured Scientific Paper Writing](https://mlsanity.com/paper/2603.27065/) (2026)
- [Detoxification for LLM: From Dataset Itself](https://mlsanity.com/paper/2604.19124/) (2026)
- [Struct-Searcher: Agentic Structural Thinking Advances Multimodal Deep Information Seeking](https://mlsanity.com/paper/2606.07689/) (2026)
- [Foundation Agents Meet Agentic Deep Research: Evidence-Grounded Clinical Code Forecasting](https://mlsanity.com/paper/2608.17075/) (2026)
- [Thinking Beyond Videos: Unifying Video Reasoning and Deep Research for Open-World Video Agents](https://mlsanity.com/paper/2608.23329/) (2026)
- [Reflective Prompt Optimization of a Deep-Research Agent: A Topic-Disjoint, Multi-Seed Protocol for Measuring Transferable Gains and Prompt-Level Overfitting](https://mlsanity.com/paper/2610.12601/) (2026)
- [From Structure to Validity: Mechanism-Guided Generation and Refinement of LLM Rubrics](https://mlsanity.com/paper/2610.13375/) (2026)

## Abstract (arXiv)

Large language models (LLMs) have rapidly evolved from text generators into powerful problem solvers. Yet, many open tasks demand critical thinking, multi-source, and verifiable outputs, which are beyond single-shot prompting or standard retrieval-augmented generation. Recently, numerous studies have explored Deep Research (DR), which aims to combine the reasoning capabilities of LLMs with external tools, such as search engines, thereby empowering LLMs to act as research agents capable of completing complex, open-ended tasks. This survey presents a comprehensive and systematic overview of deep research systems, including a clear roadmap, foundational components, practical implementation techniques, important challenges, and future directions. Specifically, our main contributions are as follows: (i) we formalize a three-stage roadmap and distinguish deep research from related paradigms; (ii) we introduce four key components: query planning, information acquisition, memory management, and answer generation, each paired with fine-grained sub-taxonomies; (iii) we summarize optimization techniques, including prompting, supervised fine-tuning, and agentic reinforcement learning; and (iv) we consolidate evaluation criteria and open challenges, aiming to guide and facilitate future development. As the field of deep research continues to evolve rapidly, we are committed to continuously updating this survey to reflect the latest progress in this area.