# DeepResearch Bench II: Diagnosing Deep Research Agents via Rubrics from Expert Reports

arXiv: https://arxiv.org/abs/2601.08536 · HTML: https://mlsanity.com/paper/2601.08536/

## Key facts

- Cited by 34 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 22 of its 62 references that are in the map.
- First posted on arXiv 13 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, 22 of 22)

- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Large Language Models Encode Clinical Knowledge](https://mlsanity.com/paper/2212.13138/) (2022)
- [A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions](https://mlsanity.com/paper/2311.05232/) (2023)
- [A Survey on LLM-as-a-Judge](https://mlsanity.com/paper/2411.15594/) (2024)
- [BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agents](https://mlsanity.com/paper/2504.12516/) (2025)
- [HealthBench: Evaluating Large Language Models Towards Improved Human Health](https://mlsanity.com/paper/2505.08775/) (2025)
- [PaperBench: Evaluating AI's Ability to Replicate AI Research](https://mlsanity.com/paper/2504.01848/) (2025)
- [DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents](https://mlsanity.com/paper/2506.11763/) (2025)
- [LLMs instead of Human Judges? A Large Scale Empirical Study across 20 NLP Evaluation Tasks](https://mlsanity.com/paper/2406.18403/) (2024)
- [WildBench: Benchmarking LLMs with Challenging Tasks from Real Users in the Wild](https://mlsanity.com/paper/2406.04770/) (2024)
- [Judging the Judges: Evaluating Alignment and Vulnerabilities in LLMs-as-Judges](https://mlsanity.com/paper/2406.12624/) (2024)
- [MultiChallenge: A Realistic Multi-Turn Conversation Evaluation Benchmark Challenging to Frontier LLMs](https://mlsanity.com/paper/2501.17399/) (2025)
- [Art or Artifice? Large Language Models and the False Promise of Creativity](https://mlsanity.com/paper/2309.14556/) (2023)
- [LLM-Rubric: A Multidimensional, Calibrated Approach to Automated Evaluation of Natural Language Texts](https://mlsanity.com/paper/2501.00274/) (2024)
- [ResearchRubrics: A Benchmark of Prompts and Rubrics For Evaluating Deep Research Agents](https://mlsanity.com/paper/2511.07685/) (2025)
- [LiveResearchBench: A Live Benchmark for User-Centric Deep Research in the Wild](https://mlsanity.com/paper/2510.14240/) (2025)
- [Deep Research Bench: Evaluating AI Web Research Agents](https://mlsanity.com/paper/2506.06287/) (2025)
- [Automated Creativity Evaluation for Large Language Models: A Reference-Based Approach](https://mlsanity.com/paper/2504.15784/) (2025)
- [The Silent Judge: Unacknowledged Shortcut Bias in LLM-as-a-Judge](https://mlsanity.com/paper/2509.26072/) (2025)
- [Advancing the Search Frontier with AI Agents](https://mlsanity.com/paper/2311.01235/) (2023)
- [Towards Long Context Hallucination Detection](https://mlsanity.com/paper/2504.19457/) (2025)
- [Evaluating LLMs with Multiple Problems at once](https://mlsanity.com/paper/2406.10786/) (2024)

## Built on by (most cited first, 30 of 34)

- [Learning Query-Specific Rubrics from Human Preferences for DeepResearch Report Generation](https://mlsanity.com/paper/2602.03619/) (2026)
- [DRACO: a Cross-Domain Benchmark for Deep Research Accuracy, Completeness, and Objectivity](https://mlsanity.com/paper/2602.11685/) (2026)
- [Nanbeige4.2-3B: Unlocking Agentic Capabilities in a Compact Model](https://mlsanity.com/paper/2607.22083/) (2026)
- [Can LLM-as-a-Judge Reliably Verify Rubrics in Agentic Scenarios?](https://mlsanity.com/paper/2606.29920/) (2026)
- [Why Your Deep Research Agent Fails? On Hallucination Evaluation in Full Research Trajectory](https://mlsanity.com/paper/2601.22984/) (2026)
- [Deep Research, Shallow Evaluation: A Case Study in Meta-Evaluation for Long-Form QA Benchmarks](https://mlsanity.com/paper/2603.06942/) (2026)
- [S1-DeepResearch: Beyond Search, Toward Real-World Long-Horizon Research Agents](https://mlsanity.com/paper/2606.15367/) (2026)
- [DEEPRUBRIC: Evidence-Tree Rubric Supervision for Efficient Reinforcement Learning of Deep Research Agents](https://mlsanity.com/paper/2606.17029/) (2026)
- [ScholarGym: Benchmarking Large Language Model Capabilities in the Information-Gathering Stage of Deep Research](https://mlsanity.com/paper/2601.21654/) (2026)
- [LH-Bench: Skill-Grounded Evaluation of Long-Horizon Agents on Subjective Enterprise Tasks](https://mlsanity.com/paper/2603.22744/) (2026)
- [TVIR: Building Deep Research Agents Towards Text-Visual Interleaved Report Generation](https://mlsanity.com/paper/2606.02320/) (2026)
- [A Survey on Rubric-Guided Reinforcement Learning for Language Models](https://mlsanity.com/paper/2608.27505/) (2026)
- [Deep FinResearch Bench: Evaluating AI's Ability to Conduct Professional Financial Investment Research](https://mlsanity.com/paper/2604.21006/) (2026)
- [Rethinking Reasoning-Intensive Retrieval: Evaluating and Advancing Retrievers in Agentic Search Systems](https://mlsanity.com/paper/2605.04018/) (2026)
- [DuMate-DeepResearch: An Auditable Multi-Agent System with Recursive Search and Rubric-Grounded Reasoning](https://mlsanity.com/paper/2606.07299/) (2026)
- [FinanceHarness: Autonomous Financial Deep Research Framework](https://mlsanity.com/paper/2607.27853/) (2026)
- [DR3-Eval: Towards Realistic and Reproducible Deep Research Evaluation](https://mlsanity.com/paper/2604.14683/) (2026)
- [DRACULA: Hunting for the Actions Users Want Deep Research Agents to Execute](https://mlsanity.com/paper/2604.23815/) (2026)
- [ViDR: Grounding Multimodal Deep Research Reports in Source Visual Evidence](https://mlsanity.com/paper/2605.13034/) (2026)
- [DeepWeb-Bench: A Deep Research Benchmark Demanding Massive Cross-Source Evidence and Long-Horizon Derivation](https://mlsanity.com/paper/2605.21482/) (2026)
- [Who is the Agent to Blame? Localizing Faithfulness and Citation Mistakes in Agentic Deep Research](https://mlsanity.com/paper/2608.24306/) (2026)
- [SGR-Bench: Benchmarking Search Agents on State-Gated Retrieval](https://mlsanity.com/paper/2605.22219/) (2026)
- [Multi-Turn Evaluation of Deep Research Agents Under Process-Level Feedback](https://mlsanity.com/paper/2606.09748/) (2026)
- [DailyReport: An Open-ended Benchmark for Evaluating Search Agents on Daily Search Tasks](https://mlsanity.com/paper/2606.12871/) (2026)
- [Beyond Score Prediction: LLM-Based Essay Scoring and Feedback Generation via Reinforcement Learning with Rubric Rewards](https://mlsanity.com/paper/2607.19219/) (2026)
- [From Simple QA to Deep Research: A Verifiable Benchmark Constructed through Iterative Task Evolution](https://mlsanity.com/paper/2608.02163/) (2026)
- [Beyond Fault Localization: A Trajectory-Level Study of LLM Agents for Microservice Root Cause Analysis](https://mlsanity.com/paper/2608.21310/) (2026)
- [Redesigning and Auditing Deep Research Writing for Faithful Reports](https://mlsanity.com/paper/2608.28643/) (2026)
- [Learning to Evaluate Before Improving: Automatic Rubric Induction for Automatic Research Agents](https://mlsanity.com/paper/2608.31076/) (2026)
- [SearchAtlas: Analyzing Agentic Search Strategies via Evidential Query Graphs](https://mlsanity.com/paper/2609.10901/) (2026)

## Abstract (arXiv)

Deep Research Agents (DRA) aim to help users search the web, synthesize information, and deliver comprehensive investigative reports. Prior benchmarks often either under-evaluate a system's ability to produce meaningful insights and high-quality writing, or adopt coarse or LLM-defined criteria that are hard to verify and can diverge from human expert judgment. To address these issues, we introduce Deep Research Bench II, a new benchmark for evaluating DRAs. It contains 132 grounded research tasks across 22 domains; for each task, an agent must produce a research report that is evaluated by a set of 9,430 fine-grained binary rubrics in total, covering three dimensions: information recall, analysis, and presentation. All rubrics are derived from carefully selected expert-written investigative articles and are constructed through a four-stage LLM+human pipeline that combines automatic extraction with over 400 human-hours of expert review, ensuring that the criteria are verifiable and aligned with human expert judgment. We evaluate several state-of-the-art deep-research agents on Deep Research Bench II and find that even the strongest models satisfy fewer than 50% of the rubrics, revealing a substantial gap between current DRAs and human experts. We release the benchmark, evaluation scripts, and all rubrics at https://github.com/imlrz/DeepResearch-Bench-II to facilitate future research on deep-rearch agents.