{"total":158,"rows":[{"id":"2501.19393","title":"s1: Simple test-time scaling","created":"2025-01-31","cited_by_count":1341,"area":"lr"},{"id":"2508.06600","title":"BrowseComp-Plus: A More Fair and Transparent Evaluation Benchmark of Deep-Research Agent","created":"2025-08-08","cited_by_count":200,"area":"agents"},{"id":"2505.08638","title":"TRAIL: Trace Reasoning and Agentic Issue Localization","created":"2025-05-13","cited_by_count":104,"area":"lr"},{"id":"2508.21038","title":"On the Theoretical Limitations of Embedding-Based Retrieval","created":"2025-08-28","cited_by_count":104,"area":null},{"id":"2409.15700","title":"Making Text Embedders Few-Shot Learners","created":"2024-09-24","cited_by_count":79,"area":null},{"id":"2504.20595","title":"ReasonIR: Training Retrievers for Reasoning Tasks","created":"2025-04-29","cited_by_count":77,"area":"lr"},{"id":"2502.18418","title":"Rank1: Test-Time Compute for Reranking in Information Retrieval","created":"2025-02-25","cited_by_count":70,"area":"lr"},{"id":"2503.06034","title":"Rank-R1: Enhancing Reasoning in LLM-based Document Rerankers via Reinforcement Learning","created":"2025-03-08","cited_by_count":60,"area":"lr"},{"id":"2410.07176","title":"Astute RAG: Overcoming Imperfect Retrieval Augmentation and Knowledge Conflicts for Large Language Models","created":"2024-10-09","cited_by_count":58,"area":"rag"},{"id":"2603.04370","title":"$\\tau$-Knowledge: Evaluating Conversational Agents over Unstructured Knowledge","created":"2026-03-04","cited_by_count":39,"area":null},{"id":"2603.08655","title":"OfficeQA Pro: An Enterprise Benchmark for End-to-End Grounded Reasoning","created":"2026-03-09","cited_by_count":39,"area":"lr"},{"id":"2411.00142","title":"JudgeRank: Leveraging Large Language Models for Reasoning-Intensive Reranking","created":"2024-10-31","cited_by_count":34,"area":"lr"},{"id":"2412.12591","title":"LLMs are Also Effective Embedding Models: An In-depth Overview","created":"2024-12-17","cited_by_count":32,"area":null},{"id":"2503.12759","title":"RAG-RL: Advancing Retrieval-Augmented Generation via RL and Curriculum Learning","created":"2025-03-17","cited_by_count":30,"area":"rag"},{"id":"2508.04183","title":"Characterizing Deep Research: A Benchmark and Formal Definition","created":"2025-08-06","cited_by_count":30,"area":null},{"id":"2505.14432","title":"Rank-K: Test-Time Reasoning for Listwise Reranking","created":"2025-05-20","cited_by_count":29,"area":"lr"},{"id":"2504.18838","title":"Toward Generalizable Evaluation in the LLM Era: A Survey Beyond Benchmarks","created":"2025-04-26","cited_by_count":28,"area":null},{"id":"2505.18405","title":"RaDeR: Reasoning-aware Dense Retrieval Models","created":"2025-05-23","cited_by_count":27,"area":"lr"},{"id":"2502.12442","title":"HopRAG: Multi-Hop Reasoning for Logic-Aware Retrieval-Augmented Generation","created":"2025-02-18","cited_by_count":24,"area":"lr"},{"id":"2505.20046","title":"REARANK: Reasoning Re-ranking Agent via Reinforcement Learning","created":"2025-05-26","cited_by_count":24,"area":"lr"},{"id":"2410.01428","title":"Can We Further Elicit Reasoning in LLMs? Critic-Guided Planning with Retrieval-Augmentation for Solving Challenging Tasks","created":"2024-10-02","cited_by_count":22,"area":"lr"},{"id":"2510.16724","title":"A Comprehensive Survey on Reinforcement Learning-based Agentic Search: Foundations, Roles, Optimizations, Evaluations, and Applications","created":"2025-10-19","cited_by_count":22,"area":"rag"},{"id":"2412.15540","title":"MRAG: A Modular Retrieval Framework for Time-Sensitive Question Answering","created":"2024-12-20","cited_by_count":17,"area":null},{"id":"2503.04644","title":"IFIR: A Comprehensive Benchmark for Evaluating Instruction-Following in Expert-Domain Information Retrieval","created":"2025-03-06","cited_by_count":16,"area":null},{"id":"2510.08252","title":"ReasonEmbed: Enhanced Text Embeddings for Reasoning-Intensive Document Retrieval","created":"2025-10-09","cited_by_count":16,"area":null},{"id":"2504.03598","title":"EnrichIndex: Using LLMs to Enrich Retrieval Indices Offline","created":"2025-04-04","cited_by_count":15,"area":null},{"id":"2504.10471","title":"MIEB: Massive Image Embedding Benchmark","created":"2025-04-14","cited_by_count":15,"area":null},{"id":"2504.13128","title":"FreshStack: Building Realistic Benchmarks for Evaluating Retrieval on Technical Documents","created":"2025-04-17","cited_by_count":15,"area":null},{"id":"2501.05382","title":"Large Physics Models: Towards a collaborative approach with Large Language Models and Foundation Models","created":"2025-01-09","cited_by_count":14,"area":null},{"id":"2502.20377","title":"PhantomWiki: On-Demand Datasets for Reasoning and Retrieval Evaluation","created":"2025-02-27","cited_by_count":14,"area":"lr"},{"id":"2504.00573","title":"Training a Utility-based Retriever Through Shared Context Attribution for Retrieval-Augmented Language Models","created":"2025-04-01","cited_by_count":13,"area":"rag"},{"id":"2504.07439","title":"LLM4Ranking: An Easy-to-use Framework of Utilizing Large Language Models for Document Reranking","created":"2025-04-10","cited_by_count":12,"area":null},{"id":"2504.04332","title":"IMPersona: Evaluating Individual Level LM Impersonation","created":"2025-04-06","cited_by_count":11,"area":null},{"id":"2506.00249","title":"MIR: Methodology Inspiration Retrieval for Scientific Research Problems","created":"2025-05-30","cited_by_count":11,"area":"lr"},{"id":"2506.11603","title":"TongSearch-QR: Reinforced Query Reasoning for Retrieval","created":"2025-06-13","cited_by_count":11,"area":"lr"},{"id":"2503.23427","title":"CoRanking: Collaborative Ranking with Small and Large Ranking Agents","created":"2025-03-30","cited_by_count":10,"area":"agents"},{"id":"2506.08354","title":"Position: Text Embeddings Should Capture Implicit Semantics, Not Just Surface Meaning","created":"2025-06-10","cited_by_count":10,"area":null},{"id":"2605.13137","title":"LeanSearch v2: Global Premise Retrieval for Lean 4 Theorem Proving","created":"2026-05-13","cited_by_count":10,"area":null},{"id":"2410.05168","title":"ReasoningRank: Teaching Student Models to Rank through Reasoning-Based Knowledge Distillation","created":"2024-10-07","cited_by_count":9,"area":"lr"},{"id":"2505.21439","title":"Towards Better Instruction Following Retrieval Models","created":"2025-05-27","cited_by_count":9,"area":null},{"id":"2506.20051","title":"Controlled Retrieval-augmented Context Evaluation for Long-form RAG","created":"2025-06-24","cited_by_count":9,"area":"rag"},{"id":"2510.14321","title":"Large Reasoning Embedding Models: Towards Next-Generation Dense Retrieval Paradigm","created":"2025-10-16","cited_by_count":9,"area":"lr"},{"id":"2411.11767","title":"Drowning in Documents: Consequences of Scaling Reranker Inference","created":"2024-11-18","cited_by_count":8,"area":null},{"id":"2505.18512","title":"AcuRank: Uncertainty-Aware Adaptive Computation for Listwise Reranking","created":"2025-05-24","cited_by_count":8,"area":null},{"id":"2511.09980","title":"Modeling Uncertainty Trends for Timely Retrieval in Dynamic RAG","created":"2025-11-13","cited_by_count":8,"area":"rag"},{"id":"2602.19961","title":"Unlocking Multimodal Document Intelligence: From Current Triumphs to Future Frontiers of Visual Document Retrieval","created":"2026-02-23","cited_by_count":8,"area":null},{"id":"2605.06235","title":"OBLIQ-Bench: Exposing Overlooked Bottlenecks in Modern Retrievers with Latent and Implicit Queries","created":"2026-05-07","cited_by_count":8,"area":null},{"id":"2506.11117","title":"ScIRGen: Synthesize Realistic and Large-Scale RAG Dataset for Scientific Research","created":"2025-06-09","cited_by_count":7,"area":null},{"id":"2509.24869","title":"Retro*: Optimizing LLMs for Reasoning-Intensive Document Retrieval","created":"2025-09-29","cited_by_count":7,"area":"lr"},{"id":"2509.26378","title":"MR$^2$-Bench: Going Beyond Matching to Reasoning in Multimodal Retrieval","created":"2025-09-30","cited_by_count":7,"area":null},{"id":"2602.05975","title":"SAGE: Benchmarking and Improving Retrieval for Deep Research Agents","created":"2026-02-05","cited_by_count":7,"area":"agents"},{"id":"2602.21456","title":"Revisiting Text Ranking in Deep Research","created":"2026-02-25","cited_by_count":7,"area":null},{"id":"2505.15585","title":"MIRB: Mathematical Information Retrieval Benchmark","created":"2025-05-21","cited_by_count":6,"area":null},{"id":"2506.11066","title":"CoQuIR: A Comprehensive Benchmark for Code Quality-Aware Information Retrieval","created":"2025-05-31","cited_by_count":6,"area":null},{"id":"2509.00520","title":"ERank: Fusing Supervised Fine-Tuning and Reinforcement Learning for Effective and Efficient Text Reranking","created":"2025-08-30","cited_by_count":6,"area":"lr"},{"id":"2510.07083","title":"All Claims Are Equal, but Some Claims Are More Equal Than Others: Importance-Sensitive Factuality Evaluation of LLM Generations","created":"2025-10-08","cited_by_count":6,"area":null},{"id":"2601.09523","title":"TEMPO: A Realistic Multi-Domain Benchmark for Temporal Reasoning-Intensive Retrieval","created":"2026-01-14","cited_by_count":6,"area":"lr"},{"id":"2602.12192","title":"Query-focused and Memory-aware Reranker for Long Context Processing","created":"2026-02-12","cited_by_count":6,"area":null},{"id":"2502.16766","title":"ATEB: Evaluating and Improving Advanced NLP Tasks for Text Embedding Models","created":"2025-02-24","cited_by_count":5,"area":null},{"id":"2504.14858","title":"Retrieval is Not Enough: Enhancing RAG Reasoning through Test-Time Critique and Optimization","created":"2025-04-21","cited_by_count":5,"area":"lr"},{"id":"2505.19800","title":"MOLE: Metadata Extraction and Validation in Scientific Papers Using LLMs","created":"2025-05-26","cited_by_count":5,"area":null},{"id":"2509.07163","title":"Beyond Sequential Reranking: Reranker-Guided Search Improves Reasoning Intensive Retrieval","created":"2025-09-08","cited_by_count":5,"area":"lr"},{"id":"2511.07581","title":"Think Before You Retrieve: Learning Test-Time Adaptive Search with Small Language Models","created":"2025-11-10","cited_by_count":5,"area":"lr"},{"id":"2511.19314","title":"PRInTS: Reward Modeling for Long-Horizon Information Seeking","created":"2025-11-24","cited_by_count":5,"area":"alignment"},{"id":"2512.01020","title":"Evaluating Legal Reasoning Traces with Legal Issue Tree Rubrics","created":"2025-11-30","cited_by_count":5,"area":"lr"},{"id":"2606.14885","title":"Dr-DCI: Scaling Direct Corpus Interaction via Dynamic Workspace Expansion","created":"2026-06-12","cited_by_count":5,"area":"agents"},{"id":"2608.12875","title":"The Embedder's Dilemma: LLMs Are Better, but at What Cost?","created":"2026-08-13","cited_by_count":5,"area":"lr"},{"id":"2503.05860","title":"Benchmarking AI Models in Software Engineering: A Review, Search Tool, and Unified Approach for Elevating Benchmark Quality","created":"2025-03-07","cited_by_count":4,"area":null},{"id":"2503.23239","title":"Beyond Contrastive Learning: Synthetic Data Enables List-wise Training with Multiple Levels of Relevance","created":"2025-03-29","cited_by_count":4,"area":"synth"},{"id":"2506.05579","title":"When Models Know More Than They Can Explain: Quantifying Knowledge Transfer in Human-AI Collaboration","created":"2025-06-05","cited_by_count":4,"area":null},{"id":"2506.14086","title":"InsertRank: LLMs can reason over BM25 scores to Improve Listwise Reranking","created":"2025-06-17","cited_by_count":4,"area":"lr"},{"id":"2509.00285","title":"OpinioRAG: Towards Generating User-Centric Opinion Highlights from Large-scale Online Reviews","created":"2025-08-30","cited_by_count":4,"area":null},{"id":"2510.13217","title":"LLM-guided Hierarchical Search for End-to-end Reasoning Intensive Retrieval","created":"2025-10-15","cited_by_count":4,"area":"lr"},{"id":"2510.22733","title":"E2Rank: Unifying Text Embedding and Listwise Reranking for Effective and Efficient Search","created":"2025-10-26","cited_by_count":4,"area":null},{"id":"2601.20131","title":"Taxonomy of the Retrieval System Framework: Pitfalls and Paradigms","created":"2026-01-27","cited_by_count":4,"area":null},{"id":"2604.03676","title":"Are LLM-Based Retrievers Worth Their Cost? An Empirical Study of Efficiency, Robustness, and Reasoning Overhead","created":"2026-04-04","cited_by_count":4,"area":"lr"},{"id":"2503.17860","title":"Enhancing Retrieval Systems with Inference-Time Logical Reasoning","created":"2025-03-22","cited_by_count":3,"area":"lr"},{"id":"2506.16552","title":"Revela: Dense Retriever Learning via Language Modeling","created":"2025-06-19","cited_by_count":3,"area":null},{"id":"2507.06223","title":"Efficiency-Effectiveness Reranking FLOPs for LLM-based Rerankers","created":"2025-07-08","cited_by_count":3,"area":null},{"id":"2508.15437","title":"Test-time Corpus Feedback: From Retrieval to RAG","created":"2025-08-21","cited_by_count":3,"area":"rag"},{"id":"2510.23544","title":"LimRank: Less is More for Reasoning-Intensive Information Reranking","created":"2025-10-27","cited_by_count":3,"area":"lr"},{"id":"2511.11653","title":"GroupRank: A Groupwise Paradigm for Effective and Efficient Passage Reranking with LLMs","created":"2025-11-10","cited_by_count":3,"area":"lr"},{"id":"2602.16932","title":"RankEvolve: Automating the Discovery of Retrieval Algorithms via LLM-Driven Evolution","created":"2026-02-18","cited_by_count":3,"area":null},{"id":"2607.19747","title":"Beyond Relevance-Centric Retrieval: Rubric-Oriented Document Set Selection and Ranking","created":"2026-07-22","cited_by_count":3,"area":null},{"id":"2607.24223","title":"A New Role for Relevance: Guiding Corpus Interaction in Agentic Search","created":"2026-07-27","cited_by_count":3,"area":"agents"},{"id":"2408.16296","title":"Rethinking Sparse Lexical Representations for Image Retrieval in the Age of Rising Multi-Modal Large Language Models","created":"2024-08-29","cited_by_count":2,"area":"lr"},{"id":"2505.23059","title":"From Token to Action: State Machine Reasoning to Mitigate Overthinking in Information Retrieval","created":"2025-05-29","cited_by_count":2,"area":"lr"},{"id":"2506.04583","title":"SUCEA: Reasoning-Intensive Retrieval for Adversarial Fact-checking through Claim Decomposition and Editing","created":"2025-06-05","cited_by_count":2,"area":"lr"},{"id":"2506.07116","title":"BRIGHT+: Upgrading the BRIGHT Benchmark with MARCUS, a Multi-Agent RAG Clean-Up Suite","created":"2025-06-08","cited_by_count":2,"area":"rag"},{"id":"2508.17400","title":"Retrieval Capabilities of Large Language Models Scale with Pretraining FLOPs","created":"2025-08-24","cited_by_count":2,"area":null},{"id":"2508.21762","title":"Reasoning-Intensive Regression","created":"2025-08-29","cited_by_count":2,"area":"lr"},{"id":"2509.00276","title":"Exploring Reasoning-Infused Text Embedding with Large Language Models for Zero-Shot Dense Retrieval","created":"2025-08-29","cited_by_count":2,"area":"lr"},{"id":"2509.22713","title":"RAR$^2$: Retrieval-Augmented Medical Reasoning via Thought-Driven Retrieval","created":"2025-09-24","cited_by_count":2,"area":"lr"},{"id":"2511.13726","title":"Refine Thought: A Test-Time Inference Method for Embedding Model Reasoning","created":"2025-10-14","cited_by_count":2,"area":"lr"},{"id":"2603.10332","title":"Does Reasoning Make Search More Fair? Comparing Fairness in Reasoning and Non-Reasoning Rerankers","created":"2026-03-11","cited_by_count":2,"area":null},{"id":"2603.10913","title":"LLM2Vec-Gen: Generative Embeddings from Large Language Models","created":"2026-03-11","cited_by_count":2,"area":"safety"},{"id":"2603.17386","title":"PJB: A Reasoning-Aware Benchmark for Person-Job Retrieval","created":"2026-03-18","cited_by_count":2,"area":null},{"id":"2603.29247","title":"MemRerank: Preference Memory for Personalized Product Reranking","created":"2026-03-31","cited_by_count":2,"area":null},{"id":"2605.04018","title":"Rethinking Reasoning-Intensive Retrieval: Evaluating and Advancing Retrievers in Agentic Search Systems","created":"2026-05-05","cited_by_count":2,"area":"agents"},{"id":"2605.26352","title":"RICE-PO: Turning Retrieval Interactions into Credit Signals for Reasoning Agents","created":"2026-05-25","cited_by_count":2,"area":"lr"}],"next_cursor":"100"}