Rethinking Reasoning-Intensive Retrieval: Evaluating and Advancing Retrievers in Agentic Search Systems

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Zhao, Yilun, Wei, Jinbiao, Song, Tingyu, Zhang, Siyue, Zhao, Chen, Cohan, Arman
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computation and Language Information Retrieval
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

LimRank: Less is More for Reasoning-Intensive Information Reranking
di: Song, Tingyu, et al.
Pubblicazione: (2025)

A Survey of Reasoning-Intensive Retrieval: Progress and Challenges
di: Wei, Yiyang, et al.
Pubblicazione: (2026)

MRMR: A Realistic and Expert-Level Multidisciplinary Benchmark for Reasoning-Intensive Multimodal Retrieval
di: Zhang, Siyue, et al.
Pubblicazione: (2025)

SAGE: Benchmarking and Improving Retrieval for Deep Research Agents
di: Hu, Tiansheng, et al.
Pubblicazione: (2026)

Rethinking Composed Image Retrieval Evaluation: A Fine-Grained Benchmark from Image Editing
di: Song, Tingyu, et al.
Pubblicazione: (2026)

IFIR: A Comprehensive Benchmark for Evaluating Instruction-Following in Expert-Domain Information Retrieval
di: Song, Tingyu, et al.
Pubblicazione: (2025)

Investigating Retrieval-Augmented Generation Systems on Unanswerable, Uncheatable, Realistic, Multi-hop Queries
di: Liu, Gabrielle Kaili-May, et al.
Pubblicazione: (2025)

Agentic-R: Learning to Retrieve for Agentic Search
di: Liu, Wenhan, et al.
Pubblicazione: (2026)

Rethinking Agentic Search with Pi-Serini: Is Lexical Retrieval Sufficient?
di: Hsu, Tz-Huan, et al.
Pubblicazione: (2026)

Rethinking the Role of Token Retrieval in Multi-Vector Retrieval
di: Lee, Jinhyuk, et al.
Pubblicazione: (2023)

Frustratingly Simple Retrieval Improves Challenging, Reasoning-Intensive Benchmarks
di: Lyu, Xinxi, et al.
Pubblicazione: (2025)

ReasonEmbed: Enhanced Text Embeddings for Reasoning-Intensive Document Retrieval
di: Chen, Jianlyu, et al.
Pubblicazione: (2025)

Beyond Sequential Reranking: Reranker-Guided Search Improves Reasoning Intensive Retrieval
di: Xu, Haike, et al.
Pubblicazione: (2025)

Retro*: Optimizing LLMs for Reasoning-Intensive Document Retrieval
di: Lan, Junwei, et al.
Pubblicazione: (2025)

SUCEA: Reasoning-Intensive Retrieval for Adversarial Fact-checking through Claim Decomposition and Editing
di: Liu, Hongjun, et al.
Pubblicazione: (2025)

FollowIR: Evaluating and Teaching Information Retrieval Models to Follow Instructions
di: Weller, Orion, et al.
Pubblicazione: (2024)

Thought-Retriever: Don't Just Retrieve Raw Data, Retrieve Thoughts for Memory-Augmented Agentic Systems
di: Feng, Tao, et al.
Pubblicazione: (2026)

Beyond Relevance: Evaluate and Improve Retrievers on Perspective Awareness
di: Zhao, Xinran, et al.
Pubblicazione: (2024)

BRIGHT: A Realistic and Challenging Benchmark for Reasoning-Intensive Retrieval
di: Su, Hongjin, et al.
Pubblicazione: (2024)

LegalSearchLM: Rethinking Legal Case Retrieval as Legal Elements Generation
di: Kim, Chaeeun, et al.
Pubblicazione: (2025)

When do Generative Query and Document Expansions Fail? A Comprehensive Study Across Methods, Retrievers, and Datasets
di: Weller, Orion, et al.
Pubblicazione: (2023)

Event-enhanced Retrieval in Real-time Search
di: Zhang, Yanan, et al.
Pubblicazione: (2024)

Evaluating Retrieval Quality in Retrieval-Augmented Generation
di: Salemi, Alireza, et al.
Pubblicazione: (2024)

Silver Retriever: Advancing Neural Passage Retrieval for Polish Question Answering
di: Rybak, Piotr, et al.
Pubblicazione: (2023)

Navigating Through Paper Flood: Advancing LLM-based Paper Evaluation through Domain-Aware Retrieval and Latent Reasoning
di: Zheng, Wuqiang, et al.
Pubblicazione: (2025)

Cost-Aware Retrieval-Augmentation Reasoning Models with Adaptive Retrieval Depth
di: Hashemi, Helia, et al.
Pubblicazione: (2025)

From Web Search towards Agentic Deep Research: Incentivizing Search with Reasoning Agents
di: Zhang, Weizhi, et al.
Pubblicazione: (2025)

TURA: Tool-Augmented Unified Retrieval Agent for AI Search
di: Zhao, Zhejun, et al.
Pubblicazione: (2025)

InfoDeepSeek: Benchmarking Agentic Information Seeking for Retrieval-Augmented Generation
di: Xi, Yunjia, et al.
Pubblicazione: (2025)

mFollowIR: a Multilingual Benchmark for Instruction Following in Retrieval
di: Weller, Orion, et al.
Pubblicazione: (2025)

Agentic Conversational Search with Contextualized Reasoning via Reinforcement Learning
di: Mo, Fengran, et al.
Pubblicazione: (2026)

Rethinking Schema Linking: A Context-Aware Bidirectional Retrieval Approach for Text-to-SQL
di: Nahid, Md Mahadi Hasan, et al.
Pubblicazione: (2025)

RAR-b: Reasoning as Retrieval Benchmark
di: Xiao, Chenghao, et al.
Pubblicazione: (2024)

OASES: Outcome-Aligned Search-Evaluation Co-Training for Agentic Search
di: Zhang, Erhan, et al.
Pubblicazione: (2026)

Open-World Evaluation for Retrieving Diverse Perspectives
di: Chen, Hung-Ting, et al.
Pubblicazione: (2024)

FeB4RAG: Evaluating Federated Search in the Context of Retrieval Augmented Generation
di: Wang, Shuai, et al.
Pubblicazione: (2024)

MCTS-RAG: Enhancing Retrieval-Augmented Generation with Monte Carlo Tree Search
di: Hu, Yunhai, et al.
Pubblicazione: (2025)

Evaluating the Retrieval Component in LLM-Based Question Answering Systems
di: Alinejad, Ashkan, et al.
Pubblicazione: (2024)

Experience Retrieval-Augmentation with Electronic Health Records Enables Accurate Discharge QA
di: Ou, Justice, et al.
Pubblicazione: (2025)

Revela: Dense Retriever Learning via Language Modeling
di: Cai, Fengyu, et al.
Pubblicazione: (2025)