# Can Deep Research Agents Retrieve and Organize? Evaluating the Synthesis Gap with Expert Taxonomies

arXiv: https://arxiv.org/abs/2601.12369 · HTML: https://mlsanity.com/paper/2601.12369/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use.
- Builds on 26 of its 39 references that are in the map.
- First posted on arXiv 18 Jan 2026.

## Placed in

- LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/)

## Builds on (most cited first, 26 of 26)

- [Mind2Web: Towards a Generalist Agent for the Web](https://mlsanity.com/paper/2306.06070/) (2023)
- [DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models](https://mlsanity.com/paper/2512.02556/) (2025)
- [C-Pack: Packed Resources For General Chinese Embeddings](https://mlsanity.com/paper/2309.07597/) (2023)
- [Fact or Fiction: Verifying Scientific Claims](https://mlsanity.com/paper/2004.14974/) (2020)
- [Agent Laboratory: Using LLM Agents as Research Assistants](https://mlsanity.com/paper/2501.04227/) (2025)
- [WebThinker: Empowering Large Reasoning Models with Deep Research Capability](https://mlsanity.com/paper/2504.21776/) (2025)
- [DeepResearcher: Scaling Deep Research via Reinforcement Learning in Real-world Environments](https://mlsanity.com/paper/2504.03160/) (2025)
- [DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents](https://mlsanity.com/paper/2506.11763/) (2025)
- [WebWalker: Benchmarking LLMs in Web Traversal](https://mlsanity.com/paper/2501.07572/) (2025)
- [AutoSurvey: Large Language Models Can Automatically Write Surveys](https://mlsanity.com/paper/2406.10252/) (2024)
- [Competitive Programming with Large Reasoning Models](https://mlsanity.com/paper/2502.06807/) (2025)
- [Jasper and Stella: distillation of SOTA embedding models](https://mlsanity.com/paper/2412.19048/) (2024)
- [ResearchRubrics: A Benchmark of Prompts and Rubrics For Evaluating Deep Research Agents](https://mlsanity.com/paper/2511.07685/) (2025)
- [From Web Search towards Agentic Deep Research: Incentivizing Search with Reasoning Agents](https://mlsanity.com/paper/2506.18959/) (2025)
- [SurveyForge: On the Outline Heuristics, Memory-Driven Generation, and Multi-dimensional Evaluation for Automated Survey Writing](https://mlsanity.com/paper/2503.04629/) (2025)
- [ReportBench: Evaluating Deep Research Agents via Academic Survey Tasks](https://mlsanity.com/paper/2508.15804/) (2025)
- [MedBrowseComp: Benchmarking Medical Deep Research and Computer Use](https://mlsanity.com/paper/2505.14963/) (2025)
- [Deep Research: A Systematic Survey](https://mlsanity.com/paper/2512.02038/) (2025)
- [MedResearcher-R1: Expert-Level Medical Deep Researcher via A Knowledge-Informed Trajectory Synthesis Framework](https://mlsanity.com/paper/2508.14880/) (2025)
- [Automated Justification Production for Claim Veracity in Fact Checking: A Survey on Architectures and Approaches](https://mlsanity.com/paper/2407.12853/) (2024)
- [Taxonomy Tree Generation from Citation Graph](https://mlsanity.com/paper/2410.03761/) (2024)
- [How Far Are We from Genuinely Useful Deep Research Agents?](https://mlsanity.com/paper/2512.01948/) (2025)
- [OpenNovelty: An LLM-powered Agentic System for Verifiable Scholarly Novelty Assessment](https://mlsanity.com/paper/2601.01576/) (2026)
- [SurveyBench: Can LLM(-Agents) Write Academic Surveys that Align with Reader Needs?](https://mlsanity.com/paper/2510.03120/) (2025)
- [STED and Consistency Scoring: A Framework for Evaluating LLM Structured Output Reliability](https://mlsanity.com/paper/2512.23712/) (2025)
- [TaxoAlign: Scholarly Taxonomy Generation Using Language Models](https://mlsanity.com/paper/2510.17263/) (2025)

## Built on by (most cited first, 3 of 3)

- [AI Can Learn Scientific Taste](https://mlsanity.com/paper/2603.14473/) (2026)
- [SciAtlas: A Computable Atlas of Science for Knowledge-Grounded AI Research](https://mlsanity.com/paper/2605.22878/) (2026)
- [How Is Automated Research Evaluated? A Survey of Benchmarks and Evaluation Practices](https://mlsanity.com/paper/2610.11877/) (2026)

## Abstract (arXiv)

Deep Research Agents increasingly automate survey writing, yet existing benchmarks do not jointly test whether they retrieve the papers experts consider essential and organize those papers into paper-grounded taxonomies. We introduce TaxoBench, a benchmark built from 72 highly cited LLM surveys, 3,815 cited papers, and their expert-authored taxonomies. TaxoBench evaluates systems in two settings: Deep Research mode measures end-to-end retrieval and organization from a topic, while Bottom-Up mode provides the expert paper set and isolates organization. We evaluate leaf-level assignments with ARI and V-Measure and hierarchy-level structure with US-TED, US-NTED, and Sem-Path. Across 7 Deep Research Agents and 16 LLM configurations, the best agent retrieves only 20.92% of expert-cited papers, and none of 70 standard Bottom-Up runs reaches the experts' average depth of 4.86. A controlled probe shows that models which match this depth do so by fragmenting the taxonomy, reducing alignment with the expert reference. We further find that raw Sem-Path remains near a no-organization floor even when a newer model generation gains 3.68 pp ARI; after depth matching, humans lead on all 10 matched surveys by 13.27 pp. These results identify retrieval and hierarchical organization as separate bottlenecks and show why hierarchy metrics must be calibrated before they are used to compare models.