# AgenticRAGTracer: A Hop-Aware Benchmark for Diagnosing Multi-Step Retrieval Reasoning in Agentic RAG

arXiv: https://arxiv.org/abs/2602.19127 · HTML: https://mlsanity.com/paper/2602.19127/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning.
- Builds on 25 of its 36 references that are in the map.
- First posted on arXiv 22 Feb 2026.

## Placed in

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

## Builds on (most cited first, 25 of 25)

- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [DeepSeek-V3 Technical Report](https://mlsanity.com/paper/2412.19437/) (2024)
- [Graph Retrieval-Augmented Generation: A Survey](https://mlsanity.com/paper/2408.08921/) (2024)
- [MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries](https://mlsanity.com/paper/2401.15391/) (2024)
- [Agentic Retrieval-Augmented Generation: A Survey on Agentic RAG](https://mlsanity.com/paper/2501.09136/) (2025)
- [ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning](https://mlsanity.com/paper/2503.19470/) (2025)
- [A Survey of Multimodal Large Language Model from A Data-centric Perspective](https://mlsanity.com/paper/2405.16640/) (2024)
- [UniCTokens: Boosting Personalized Understanding and Generation via Unified Concept Tokens](https://mlsanity.com/paper/2505.14671/) (2025)
- [MC-LLaVA: Multi-Concept Personalized Vision-Language Model](https://mlsanity.com/paper/2411.11706/) (2024)
- [Perceive Anything: Recognize, Explain, Caption, and Segment Anything in Images and Videos](https://mlsanity.com/paper/2506.05302/) (2025)
- [Are Video Models Ready as Zero-Shot Reasoners? An Empirical Study with the MME-CoF Benchmark](https://mlsanity.com/paper/2510.26802/) (2025)
- [Modular RAG: Transforming RAG Systems into LEGO-like Reconfigurable Frameworks](https://mlsanity.com/paper/2407.21059/) (2024)
- [MM-Verify: Enhancing Multimodal Reasoning with Chain-of-Thought Verification](https://mlsanity.com/paper/2502.13383/) (2025)
- [MoreHopQA: More Than Multi-hop Reasoning](https://mlsanity.com/paper/2406.13397/) (2024)
- [R-Search: Empowering LLM Reasoning with Search via Multi-Reward Reinforcement Learning](https://mlsanity.com/paper/2506.04185/) (2025)
- [DataFlow: An LLM-Driven Framework for Unified Data Preparation and Workflow Automation in the Era of Data-Centric AI](https://mlsanity.com/paper/2512.16676/) (2025)
- [MINTQA: A Multi-Hop Question Answering Benchmark for Evaluating LLMs on New and Tail Knowledge](https://mlsanity.com/paper/2412.17032/) (2024)
- [Reasoning RAG via System 1 or System 2: A Survey on Reasoning Agentic Retrieval-Augmented Generation for Industry Challenges](https://mlsanity.com/paper/2506.10408/) (2025)
- [Let's Verify Math Questions Step by Step](https://mlsanity.com/paper/2505.13903/) (2025)
- [Text2SQL-Flow: A Robust SQL-Aware Data Augmentation Framework for Text-to-SQL](https://mlsanity.com/paper/2511.10192/) (2025)
- [Synth-Empathy: Towards High-Quality Synthetic Empathy Data](https://mlsanity.com/paper/2407.21669/) (2024)
- [PAS: Data-Efficient Plug-and-Play Prompt Augmentation System](https://mlsanity.com/paper/2407.06027/) (2024)
- [SynthVLM: Towards High-Quality and Efficient Synthesis of Image-Caption Datasets for Vision-Language Models](https://mlsanity.com/paper/2407.20756/) (2024)

## Built on by (most cited first, 5 of 5)

- [Scaling Multi-Hop Training Data via Graph-Constrained Path Selection](https://mlsanity.com/paper/2605.31238/) (2026)
- [LayerRAG-Bench: A Cross-Layer Reliability Benchmark for Agentic Retrieval-Augmented Generation](https://mlsanity.com/paper/2607.27353/) (2026)
- [Does the Selected Object Reach the Reader? Auditing Identity Handoffs in Grounded Language-Model Pipelines](https://mlsanity.com/paper/2609.04579/) (2026)
- [The Missing Complement: State-Conditioned Minimal Sufficient Evidence for Coding Agents](https://mlsanity.com/paper/2609.20050/) (2026)
- [AgentHop: A Diagnostic Benchmark for Agentic Multi-Hop Scientific Question Answering](https://mlsanity.com/paper/2609.34428/) (2026)

## Abstract (arXiv)

With the rapid advancement of agent-based methods in recent years, Agentic RAG has undoubtedly become an important research direction. Multi-hop reasoning, which requires models to engage in deliberate thinking and multi-step interaction, serves as a critical testbed for assessing such capabilities. However, existing benchmarks typically provide only final questions and answers, while lacking the intermediate hop-level questions that gradually connect atomic questions to the final multi-hop query. This limitation prevents researchers from analyzing at which step an agent fails and restricts more fine-grained evaluation of model capabilities. Moreover, most current benchmarks are manually constructed, which is both time-consuming and labor-intensive, while also limiting scalability and generalization. To address these challenges, we introduce AgenticRAGTracer, the first Agentic RAG benchmark that is primarily constructed automatically by large language models and designed to support step-by-step validation. Our benchmark spans multiple domains, contains 1,305 data points, and has no overlap with existing mainstream benchmarks. Extensive experiments demonstrate that even the best large language models perform poorly on our dataset. For instance, GPT-5 attains merely 22.6% EM accuracy on the hardest portion of our dataset. Hop-aware diagnosis reveals that failures are primarily driven by distorted reasoning chains -- either collapsing prematurely or wandering into over-extension. This highlights a critical inability to allocate steps consistent with the task's logical structure, providing a diagnostic dimension missing in traditional evaluations. We believe our work will facilitate research in Agentic RAG and inspire further meaningful progress in this area. Our code and data are available at https://github.com/YqjMartin/AgenticRAGTracer.