arXiv AI June 12, 2026 By Mahdi Astaraki, Mohammad Arshi Saloot, Ali Shiraee Kasmaee, Hamidreza Mahyar, Soheila Samiee

When Iterative RAG Beats Ideal Evidence: A Diagnostic Study in Scientific Multi-hop Question Answering

arXiv:2601. 19827v4 Announce Type: replace-cross Abstract: Retrieval-Augmented Generation (RAG) extends large language models (LLMs) beyond parametric knowledge, yet it is unclear when iterative retrieval-reasoning loops meaningfully outperform static RAG, particularly in scientific domains with multi-hop reasoning, sparse domain knowledge, and heterogeneous evidence.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

arXiv AI

Aug 11

To Memorize or to Retrieve: Scaling the Interaction Between Pretraining and Retrieval

arXiv:2604. 00715v2 Announce Type: replace-cross Abstract: Retrieval-augmented generation (RAG) improves language model (LM) performance by providing relevant context at test time for knowledge-intensive situations.

By Karan Singh, Michael Yu, Varun Gangal, Zhuofu Tao, Sachin Kumar, Emmy Liu, Steven Y. Feng

llms rag benchmarks

arXiv AI

Aug 5

SciRet: A Compute-Aware Empirical Study of Retrieval and Reranking for Scientific RAG

arXiv:2608. 03860v1 Announce Type: cross Abstract: We introduce SciRet, a compute-aware empirical study of retrieval-augmented generation for scientific question answering over CORD-19.

By Kaysarul Anas Apurba, Md. Hasibul Hasan, Rofiqul Alam Shehab, Asab Azad

rag nlp benchmarks

arXiv AI

Jun 10

RAG over Thinking Traces Can Improve Reasoning Tasks

arXiv:2605. 03344v2 Announce Type: replace-cross Abstract: Retrieval-augmented generation (RAG) has proven effective for knowledge-intensive tasks, but is widely believed to offer limited benefit for reasoning-intensive problems such as math and code generation.

By Negar Arabzadeh, Wenjie Ma, Sewon Min, Matei Zaharia

llms rag benchmarks

arXiv AI

1d ago

GraphLoom: Reliability-Calibrated Graph Evidence Routing for Multimodal KG-RAG

arXiv:2608. 15056v1 Announce Type: new Abstract: Multimodal retrieval-augmented generation (RAG) systems often rely on long unstructured contexts or aggressively expanded evidence graphs, which can introduce noisy evidence, weaken multi-hop reasoning, and increase unsupported generation.

By Zafar Ali, Asad Khan, Aalia Malik, Pavlos Kefalas

llms rag multimodal

arXiv AI

Jul 10

Understanding Axes of Difficulty For Long Context Tasks Via PredicateLongBench

arXiv:2607. 08284v1 Announce Type: new Abstract: Large language models (LLMs) have demonstrated rapidly improving long-context capabilities, prompting a wave of benchmarks designed to evaluate them.

By Siddhartha Jain, Ameya Velingker

llms nlp benchmarks

arXiv AI

Jul 14

CRiT-QA: Evaluating Multi-hop Reasoning with Counterfactual Chains and Distractor Traps

arXiv:2607. 10562v1 Announce Type: new Abstract: Evaluating the multi-hop reasoning capabilities of large language models remains a significant challenge.

By JungMin Yun, JuneHyoung Kwon, YoungBin Kim

llms nlp

Related stories

To Memorize or to Retrieve: Scaling the Interaction Between Pretraining and Retrieval

SciRet: A Compute-Aware Empirical Study of Retrieval and Reranking for Scientific RAG

RAG over Thinking Traces Can Improve Reasoning Tasks

GraphLoom: Reliability-Calibrated Graph Evidence Routing for Multimodal KG-RAG

Understanding Axes of Difficulty For Long Context Tasks Via PredicateLongBench

CRiT-QA: Evaluating Multi-hop Reasoning with Counterfactual Chains and Distractor Traps