# DeepTRACE: Auditing Deep Research AI Systems for Tracking Reliability Across Citations and Evidence

arXiv: https://arxiv.org/abs/2509.04499 · HTML: https://mlsanity.com/paper/2509.04499/

## Key facts

- Cited by 10 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 30 of its 44 references that are in the map.
- First posted on arXiv 2 Sep 2025.

## 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, 30 of 30)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [WebGPT: Browser-assisted question-answering with human feedback](https://mlsanity.com/paper/2112.09332/) (2021)
- [A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions](https://mlsanity.com/paper/2311.05232/) (2023)
- [Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering](https://mlsanity.com/paper/2007.01282/) (2020)
- [Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexity](https://mlsanity.com/paper/2403.14403/) (2024)
- [Ragas: Automated Evaluation of Retrieval Augmented Generation](https://mlsanity.com/paper/2309.15217/) (2023)
- [SummaC: Re-Visiting NLI-based Models for Inconsistency Detection in Summarization](https://mlsanity.com/paper/2111.09525/) (2021)
- [Evaluating Verifiability in Generative Search Engines](https://mlsanity.com/paper/2304.09848/) (2023)
- [MiniCheck: Efficient Fact-Checking of LLMs on Grounding Documents](https://mlsanity.com/paper/2404.10774/) (2024)
- [DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents](https://mlsanity.com/paper/2506.11763/) (2025)
- [BrowseComp-Plus: A More Fair and Transparent Evaluation Benchmark of Deep-Research Agent](https://mlsanity.com/paper/2508.06600/) (2025)
- [Deep Research Agents: A Systematic Examination And Roadmap](https://mlsanity.com/paper/2506.18096/) (2025)
- [Improving the Domain Adaptation of Retrieval Augmented Generation (RAG) Models for Open Domain Question Answering](https://mlsanity.com/paper/2210.02627/) (2022)
- [MLGym: A New Framework and Benchmark for Advancing AI Research Agents](https://mlsanity.com/paper/2502.14499/) (2025)
- [RAG vs Fine-tuning: Pipelines, Tradeoffs, and a Case Study on Agriculture](https://mlsanity.com/paper/2401.08406/) (2024)
- [Are You Sure? Challenging LLMs Leads to Performance Drops in The FlipFlop Experiment](https://mlsanity.com/paper/2311.08596/) (2023)
- [FABLES: Evaluating faithfulness and content selection in book-length summarization](https://mlsanity.com/paper/2404.01261/) (2024)
- [Do LVLMs Understand Charts? Analyzing and Correcting Factual Errors in Chart Captioning](https://mlsanity.com/paper/2312.10160/) (2023)
- [The Who in XAI: How AI Background Shapes Perceptions of AI Explanations](https://mlsanity.com/paper/2107.13509/) (2021)
- [GenAI Against Humanity: Nefarious Applications of Generative Artificial Intelligence and Large Language Models](https://mlsanity.com/paper/2310.00737/) (2023)
- [RAGEval: Scenario Specific RAG Evaluation Dataset Generation Framework](https://mlsanity.com/paper/2408.01262/) (2024)
- [LLMs as Factual Reasoners: Insights from Existing Benchmarks and Beyond](https://mlsanity.com/paper/2305.14540/) (2023)
- [Deep Research Bench: Evaluating AI Web Research Agents](https://mlsanity.com/paper/2506.06287/) (2025)
- [A Sociotechnical View of Algorithmic Fairness](https://mlsanity.com/paper/2110.09253/) (2021)
- [Evaluation of RAG Metrics for Question Answering in the Telecom Domain](https://mlsanity.com/paper/2407.12873/) (2024)
- [Evaluating Large Language Models for Health-related Queries with Presuppositions](https://mlsanity.com/paper/2312.08800/) (2023)
- [We Should Evaluate Real-World Impact](https://mlsanity.com/paper/2507.05973/) (2025)
- [AMRFact: Enhancing Summarization Factuality Evaluation with AMR-Driven Negative Samples Generation](https://mlsanity.com/paper/2311.09521/) (2023)
- [Towards a Holistic Approach: Understanding Sociodemographic Biases in NLP Models using an Interdisciplinary Lens](https://mlsanity.com/paper/2308.13089/) (2023)

## Built on by (most cited first, 10 of 10)

- [MMDeepResearch-Bench: A Benchmark for Multimodal Deep Research Agents](https://mlsanity.com/paper/2601.12346/) (2026)
- [The Need for a Socially-Grounded Persona Framework for User Simulation](https://mlsanity.com/paper/2601.07110/) (2026)
- [From Fluent to Verifiable: Claim-Level Auditability for Deep Research Agents](https://mlsanity.com/paper/2602.13855/) (2026)
- [Don't Stop Early: Scalable Enterprise Deep Research with Controlled Information Flow and Evidence-Aware Termination](https://mlsanity.com/paper/2604.24978/) (2026)
- [Language Models Don't Know What You Want: Evaluating Personalization in Deep Research Needs Real Users](https://mlsanity.com/paper/2603.16120/) (2026)
- [What if AI systems weren't chatbots?](https://mlsanity.com/paper/2605.07896/) (2026)
- [Agents in the Wild: Where Research Meets Deployment](https://mlsanity.com/paper/2607.19336/) (2026)
- [Mint-Agent: Introducing Finance-Native Agentic Foundation Models](https://mlsanity.com/paper/2608.16386/) (2026)
- [Redesigning and Auditing Deep Research Writing for Faithful Reports](https://mlsanity.com/paper/2608.28643/) (2026)
- [LongCat-DeepResearch Technical Report](https://mlsanity.com/paper/2609.36071/) (2026)

## Abstract (arXiv)

Generative search engines and deep research LLM agents promise trustworthy, source-grounded synthesis, yet users regularly encounter overconfidence, weak sourcing, and confusing citation practices. We introduce DeepTRACE, a novel sociotechnically grounded audit framework that turns prior community-identified failure cases into eight measurable dimensions spanning answer text, sources, and citations. DeepTRACE uses statement-level analysis (decomposition, confidence scoring) and builds citation and factual-support matrices to audit how systems reason with and attribute evidence end-to-end. Using automated extraction pipelines for popular public models (e.g., GPT-4.5/5, You.com, Perplexity, Copilot/Bing, Gemini) and an LLM-judge with validated agreement to human raters, we evaluate both web-search engines and deep-research configurations. Our findings show that generative search engines and deep research agents frequently produce one-sided, highly confident responses on debate queries and include large fractions of statements unsupported by their own listed sources. Deep-research configurations reduce overconfidence and can attain high citation thoroughness, but they remain highly one-sided on debate queries and still exhibit large fractions of unsupported statements, with citation accuracy ranging from 40--80% across systems.