Tutorial Materials

• Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks. (Lewis et al. NeurIPS 2020.)
• REPLUG: Retrieval-Augmented Black-Box Language Models. (Shi et al. NAACL 2024.)
• Atlas: Few-shot Learning with Retrieval Augmented Language Models. (Izacard et al. JMLR 2023.)

• A Definition of Relevance for Information Retrieval. (Cooper. Information Storage and Retrieval 1971.)
• Relevance: A Review of and a Framework for the Thinking on the Notion in Information Science. (Saracevic. JASIS 1975.)
• Relevance Reconsidered. (Saracevic. CoLIS 1996.)
• A Study of Information Seeking and Retrieving. I. Background and Methodology. (Saracevic et al. JASIS 1988.)

• Click Data as Implicit Relevance Feedback in Web Search. (Jung et al. IP&M 2007.)
• Display Time as Implicit Feedback: Understanding Task Effects. (Kelly. SIGIR 2004.)
• Segment-Level Display Time as Implicit Feedback: A Comparison to Eye Tracking. (Buscher et al. SIGIR 2009.)
• Does Document Relevance Affect the Searcher's Perception of Time? (Luo et al. WSDM 2017.)
• More than Relevance: High Utility Query Recommendation by Mining Users' Search Behaviors. (Zhu et al. CIKM 2012.)
• Beyond Ranking: Optimizing Whole-Page Presentation. (Wang et al. WSDM 2016.)

• LLM-Oriented Information Retrieval: A Denoising-First Perspective. (Dai et al. SIGIR 2026.)

Factoid QA

• Are Large Language Models Good at Utility Judgments? (Zhang et al. SIGIR 2024.)
• Evaluating Retrieval Quality in Retrieval-Augmented Generation. (Salemi et al. SIGIR 2024.)

Non-Factoid and Complex QA

• WebGLM: Towards an Efficient Web-Enhanced Question Answering System with Human Preferences. (Liu et al. KDD 2023.)
• DR Tulu: Reinforcement Learning with Evolving Rubrics for Deep Research. (Shao et al. ICML 2026.)

Fact Verification and Classification

• From Relevance to Utility: Evidence Retrieval with Feedback for Fact Verification. (Zhang et al. EMNLP 2023.)
• Read It Twice: Towards Faithfully Interpretable Fact Verification by Revisiting Evidence. (Hu et al. SIGIR 2023.)

Code Generation

• Preference-Guided Refactored Tuning for Retrieval Augmented Code Generation. (Gao et al. ASE 2024.)
• SelfRACG: Enabling LLMs to Self-Express and Retrieve for Code Generation. (Dong et al. EMNLP 2025.)

Tool and Skill Retrieval

• Tool-to-Agent Retrieval: Bridging Tools and Agents for Scalable LLM Multi-Agent Systems. (Lumer et al. 2025.)
• Skill Retrieval Augmentation for Agentic AI. (Su et al. 2026.)
• Multi-Field Tool Retrieval. (Tang et al. 2026.)
• SkillResolve-Bench: Measuring and Resolving Same-Capability Ambiguity in Agent Skill Retrieval. (Ding et al. 2026.)

LLM-Agnostic Utility

• Are Large Language Models Good at Utility Judgments? (Zhang et al. SIGIR 2024.)
• An Iterative Utility Judgment Framework via LLMs Inspired by Relevance in Philosophy. (Zhang et al. ACL 2026.)

LLM-Specific Utility

• LLM-Specific Utility: A New Perspective for Retrieval-Augmented Generation. (Zhang et al. 2025.)
• SePer: Measure Retrieval Utility Through the Lens of Semantic Perplexity Reduction. (Dai et al. ICLR 2025.)
• Uplift-RAG: Uplift-Driven Knowledge Preference Alignment for Retrieval-Augmented Generation. (Qu et al. EMNLP 2025.)

Pointwise Utility

• REPLUG: Retrieval-Augmented Black-Box Language Models. (Shi et al. NAACL 2024.)
• Atlas: Few-shot Learning with Retrieval Augmented Language Models. (Izacard et al. JMLR 2023.)
• SePer: Measure Retrieval Utility Through the Lens of Semantic Perplexity Reduction. (Dai et al. ICLR 2025.)
• Uplift-RAG: Uplift-Driven Knowledge Preference Alignment for Retrieval-Augmented Generation. (Qu et al. EMNLP 2025.)

Set-Level Utility

• DIVERGE: Diversity-Enhanced Retrieval-Augmented Generation for Open-Ended Information Seeking. (Hu et al. 2026.)
• DF-RAG: Query-Aware Diversity for Retrieval-Augmented Generation. (Khan et al. ACL 2026.)
• Modeling Contextual Passage Utility for Multihop Question Answering. (Jain et al. IJCNLP 2025.)
• Distilling a Small Utility-Based Passage Selector to Enhance Retrieval-Augmented Generation. (Zhang et al. SIGIR-AP 2025.)
• Shifting from Ranking to Set Selection for Retrieval Augmented Generation. (Lee et al. ACL 2025.)
• OptiSet: Unified Optimizing Set Selection and Ranking for Retrieval-Augmented Generation. (Jiang et al. 2026.)
• BGM: Bridging the Preference Gap between Retrievers and LLMs. (Ke et al. ACL 2024.)

• Relevance to Utility: Process-Supervised Rewrite for RAG. (Kim et al. ACL 2026.)
• ECoRAG: Evidentiality-Guided Compression for Long Context RAG. (Jeong et al. ACL 2025.)
• Parametric Retrieval-Augmented Generation. (Su et al. SIGIR 2025.)
• Chain-of-Note: Enhancing Robustness in Retrieval-Augmented Language Models. (Yu et al. EMNLP 2024.)
• Injecting External Knowledge into the Reasoning Process Enhances Retrieval-Augmented Generation. (Tang et al. SIGIR-AP 2025.)
• The Last Human-Written Paper: Agent-Native Research Artifacts. (Liu et al. 2026.)

Signal A: Verbalized LLM Utility Judgment (no ground-truth answer required)

• Are Large Language Models Good at Utility Judgments? (Zhang et al. SIGIR 2024.)
• An Iterative Utility Judgment Framework via LLMs Inspired by Relevance in Philosophy. (Zhang et al. ACL 2026.)
• Bridging Relevance and Reasoning: Rationale Distillation in Retrieval-Augmented Generation. (Jia et al. ACL 2025.)

Signal B: Attention / Reader-Derived Signals (no ground-truth answer required)

• FiD: Distilling Knowledge from Reader to Retriever for Question Answering. (Izacard et al. ICLR 2021.)
• Atlas: Few-shot Learning with Retrieval Augmented Language Models. (Izacard et al. JMLR 2023.)
• LLM-Specific Utility: A New Perspective for Retrieval-Augmented Generation. (Zhang et al. 2025.)

Signal C: Likelihood and Perplexity (ground-truth answer required)

• REPLUG: Retrieval-Augmented Black-Box Language Models. (Shi et al. NAACL 2024.)
• Aligning Dense Retrievers with LLM Utility via Distillation. (Sandhu et al. 2026.)
• Atlas: Few-shot Learning with Retrieval Augmented Language Models. (Izacard et al. JMLR 2023.)
• Predicting Retrieval Utility and Answer Quality in Retrieval-Augmented Generation. (Tian et al. ECIR 2026.)
• SEER: Self-Aligned Evidence Extraction for Retrieval-Augmented Generation. (Zhao et al. EMNLP 2024.)
• Utility-Oriented Visual Evidence Selection for Multimodal Retrieval-Augmented Generation. (Luo et al. ACL 2026.)
• Training a Utility-based Retriever Through Shared Context Attribution for Retrieval-Augmented Language Models. (Xu et al. EMNLP 2025.)

Signal D: Downstream Performance (ground-truth answer required)

• Similarity Is Not All You Need: Endowing Retrieval-Augmented Generation with Multi-Layered Thoughts. (Gan et al. 2024.)
• LLM-Specific Utility: A New Perspective for Retrieval-Augmented Generation. (Zhang et al. 2025.)

Level 1: Small Candidate Sets (10–20) — High-Fidelity Judgments

• Are Large Language Models Good at Utility Judgments? (Zhang et al. SIGIR 2024.)
• An Iterative Utility Judgment Framework via LLMs Inspired by Relevance in Philosophy. (Zhang et al. ACL 2026.)
• LLM-Specific Utility: A New Perspective for Retrieval-Augmented Generation. (Zhang et al. 2025.)

Level 2: Medium Candidate Sets (dozens to hundreds) — Selectors and Rerankers

• Distilling a Small Utility-Based Passage Selector to Enhance Retrieval-Augmented Generation. (Zhang et al. SIGIR-AP 2025.)
• Predicting Retrieval Utility and Answer Quality in Retrieval-Augmented Generation. (Tian et al. ECIR 2026.)
• From Relevance to Utility: Evidence Retrieval with Feedback for Fact Verification. (Zhang et al. EMNLP 2023.)
• Read It Twice: Towards Faithfully Interpretable Fact Verification by Revisiting Evidence. (Hu et al. SIGIR 2023.)
• Modeling Contextual Passage Utility for Multihop Question Answering. (Jain et al. IJCNLP 2025.)
• Bridging Relevance and Reasoning: Rationale Distillation in Retrieval-Augmented Generation. (Jia et al. ACL 2025.)
• RAG-DDR: Optimizing Retrieval-Augmented Generation Using Differentiable Data Rewards. (Li et al. ICLR 2025.)
• Retrieve What You Need: A Mutual Learning Framework for Open-Domain Question Answering. (Wang et al. TACL 2024.)
• Optimizing RAG Rerankers with LLM Feedback via Reinforcement Learning. (Wu et al. ACL 2026.)

Level 3: Corpus-Scale — Utility-Oriented Retrievers

• Utility-Focused LLM Annotation for Retrieval and Retrieval-Augmented Generation. (Zhang et al. EMNLP 2025.)
• Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks. (Lewis et al. NeurIPS 2020.)
• Stochastic RAG: End-to-End Retrieval-Augmented Generation through Expected Utility Maximization. (Zamani et al. SIGIR 2024.)
• REPLUG: Retrieval-Augmented Black-Box Language Models. (Shi et al. NAACL 2024.)
• Aligning Dense Retrievers with LLM Utility via Distillation. (Sandhu et al. 2026.)
• GripRank: Bridging the Gap between Retrieval and Generation via Generative Knowledge Improved Passage Ranking. (Bai et al. CIKM 2023.)
• FiD: Distilling Knowledge from Reader to Retriever for Question Answering. (Izacard et al. ICLR 2021.)
• Atlas: Few-shot Learning with Retrieval Augmented Language Models. (Izacard et al. JMLR 2023.)
• Training a Utility-based Retriever Through Shared Context Attribution for Retrieval-Augmented Language Models. (Xu et al. EMNLP 2025.)
• RRAML: Reinforced Retrieval Augmented Machine Learning. (Bacciu et al. 2023.)

• eRAG: Evaluating Retrieval Quality in Retrieval-Augmented Generation. (Salemi et al. SIGIR 2024.)
• RARE: Redundancy-Aware Retrieval Evaluation Framework for High-Similarity Corpora. (Cho et al. ACL 2026.)
• UsefulBench: Towards Decision-Useful Information as a Target for Information Retrieval. (Schimanski et al. 2026.)

• Active Retrieval Augmented Generation. (Jiang et al. EMNLP 2023.)
• DRAGIN: Dynamic Retrieval Augmented Generation Based on the Real-Time Information Needs of Large Language Models. (Su et al. ACL 2024.)
• Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning. (Jin et al. COLM 2025.)
• AgentIR: Reasoning-Aware Retrieval for Deep Research Agents. (Chen et al. 2026.)
• SubSearch: Intermediate Rewards for Unsupervised Guided Reasoning in Complex Retrieval. (Petcu et al. 2026.)

• Revisiting Text Ranking in Deep Research. (Meng et al. SIGIR 2026.)
• Agentic-R: Learning to Retrieve for Agentic Search. (Liu et al. ACL 2026.)
• Learning to Retrieve from Agent Trajectories. (Zhou et al. SIGIR 2026.)
• Rethinking Reasoning-Intensive Retrieval: Evaluating and Advancing Retrievers in Agentic Search Systems. (Zhao et al. ACL 2026.)

• StepSearch: Igniting LLMs Search Ability via Step-Wise Proximal Policy Optimization. (Zheng et al. EMNLP 2025.)
• Information Gain-Based Policy Optimization: A Simple and Effective Approach for Multi-Turn Search Agents. (Wang et al. ICLR 2026.)
• Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models Through Question Complexity. (Jeong et al. NAACL 2024.)
• Beyond Monolithic Architectures: A Multi-Agent Search and Knowledge Optimization Framework for Agentic Search. (Chen et al. 2026.)
• Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interaction. (Li et al. 2026.)