{"list":"other","total":66,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","created":"2024-02-05","cited_by_count":9379},{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"2210.03629","title":"ReAct: Synergizing Reasoning and Acting in Language Models","created":"2022-10-06","cited_by_count":8695},{"id":"2501.12948","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","created":"2025-01-22","cited_by_count":6330},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"2412.15115","title":"Qwen2.5 Technical Report","created":"2024-12-19","cited_by_count":4942},{"id":"1910.01108","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","created":"2019-10-02","cited_by_count":4307},{"id":"2004.04906","title":"Dense Passage Retrieval for Open-Domain Question Answering","created":"2020-04-10","cited_by_count":3824},{"id":"1809.09600","title":"HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering","created":"2018-09-25","cited_by_count":3754},{"id":"1705.03551","title":"TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension","created":"2017-05-09","cited_by_count":2955},{"id":"2002.08909","title":"REALM: Retrieval-Augmented Language Model Pre-Training","created":"2020-02-10","cited_by_count":2141},{"id":"2202.03629","title":"Survey of Hallucination in Natural Language Generation","created":"2022-02-08","cited_by_count":2075},{"id":"2409.19256","title":"HybridFlow: A Flexible and Efficient RLHF Framework","created":"2024-09-28","cited_by_count":2057},{"id":"2112.09332","title":"WebGPT: Browser-assisted question-answering with human feedback","created":"2021-12-17","cited_by_count":1745},{"id":"2503.09516","title":"Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning","created":"2025-03-12","cited_by_count":1444},{"id":"2011.01060","title":"Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps","created":"2020-11-02","cited_by_count":1282},{"id":"2212.03533","title":"Text Embeddings by Weakly-Supervised Contrastive Pre-training","created":"2022-12-07","cited_by_count":1253},{"id":"2210.03350","title":"Measuring and Narrowing the Compositionality Gap in Language Models","created":"2022-10-07","cited_by_count":1075},{"id":"2212.10509","title":"Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions","created":"2022-12-20","cited_by_count":923},{"id":"2108.00573","title":"MuSiQue: Multihop Questions via Single-hop Question Composition","created":"2021-08-02","cited_by_count":916},{"id":"2302.00093","title":"Large Language Models Can Be Easily Distracted by Irrelevant Context","created":"2023-01-31","cited_by_count":841},{"id":"2309.01219","title":"Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models","created":"2023-09-03","cited_by_count":698},{"id":"2305.06983","title":"Active Retrieval Augmented Generation","created":"2023-05-11","cited_by_count":516},{"id":"2310.06839","title":"LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compression","created":"2023-10-10","cited_by_count":453},{"id":"2501.05366","title":"Search-o1: Agentic Search-Enhanced Large Reasoning Models","created":"2025-01-09","cited_by_count":433},{"id":"2305.15294","title":"Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergy","created":"2023-05-24","cited_by_count":346},{"id":"2503.05592","title":"R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning","created":"2025-03-07","cited_by_count":336},{"id":"2504.03160","title":"DeepResearcher: Scaling Deep Research via Reinforcement Learning in Real-world Environments","created":"2025-04-04","cited_by_count":286},{"id":"2403.10131","title":"RAFT: Adapting Language Model to Domain Specific RAG","created":"2024-03-15","cited_by_count":262},{"id":"2310.04408","title":"RECOMP: Improving Retrieval-Augmented LMs with Compression and Selective Augmentation","created":"2023-10-06","cited_by_count":256},{"id":"2411.02337","title":"WebRL: Training LLM Web Agents via Self-Evolving Online Curriculum Reinforcement Learning","created":"2024-11-04","cited_by_count":256},{"id":"2502.14802","title":"From RAG to Memory: Non-Parametric Continual Learning for Large Language Models","created":"2025-02-20","cited_by_count":231},{"id":"2505.04588","title":"ZeroSearch: Incentivize the Search Capability of LLMs without Searching","created":"2025-05-07","cited_by_count":208},{"id":"2406.02818","title":"Chain of Agents: Large Language Models Collaborating on Long-Context Tasks","created":"2024-06-04","cited_by_count":206},{"id":"2505.16421","title":"WebAgent-R1: Training Web Agents via End-to-End Multi-Turn Reinforcement Learning","created":"2025-05-22","cited_by_count":165},{"id":"2410.05983","title":"Long-Context LLMs Meet RAG: Overcoming Challenges for Long Inputs in RAG","created":"2024-10-08","cited_by_count":123},{"id":"2502.04644","title":"Agentic Reasoning: A Streamlined Framework for Enhancing LLM Reasoning with Agentic Tools","created":"2025-02-07","cited_by_count":106},{"id":"2207.06300","title":"Re2G: Retrieve, Rerank, Generate","created":"2022-07-13","cited_by_count":102},{"id":"2305.15047","title":"Ghostbuster: Detecting Text Ghostwritten by Large Language Models","created":"2023-05-24","cited_by_count":91},{"id":"2407.01370","title":"Summary of a Haystack: A Challenge to Long-Context LLMs and RAG Systems","created":"2024-07-01","cited_by_count":87},{"id":"2502.04413","title":"MedRAG: Enhancing Retrieval-augmented Generation with Knowledge Graph-Elicited Reasoning for Healthcare Copilot","created":"2025-02-06","cited_by_count":83},{"id":"2504.20595","title":"ReasonIR: Training Retrievers for Reasoning Tasks","created":"2025-04-29","cited_by_count":77},{"id":"2404.13081","title":"SuRe: Summarizing Retrievals using Answer Candidates for Open-domain QA of LLMs","created":"2024-04-17","cited_by_count":67},{"id":"2410.04343","title":"Inference Scaling for Long-Context Retrieval Augmented Generation","created":"2024-10-06","cited_by_count":65},{"id":"2405.18414","title":"Don't Forget to Connect! Improving RAG with Graph-based Reranking","created":"2024-05-28","cited_by_count":49},{"id":"2503.20201","title":"Open Deep Search: Democratizing Search with Open-source Reasoning Agents","created":"2025-03-26","cited_by_count":49},{"id":"2408.15232","title":"Into the Unknown Unknowns: Engaged Human Learning through Participation in Language Model Agent Conversations","created":"2024-08-27","cited_by_count":43},{"id":"2406.12430","title":"PlanRAG: A Plan-then-Retrieval Augmented Generation for Generative Large Language Models as Decision Makers","created":"2024-06-18","cited_by_count":42},{"id":"2502.01142","title":"DeepRAG: Thinking to Retrieve Step by Step for Large Language Models","created":"2025-02-03","cited_by_count":38},{"id":"2506.04185","title":"R-Search: Empowering LLM Reasoning with Search via Multi-Reward Reinforcement Learning","created":"2025-06-04","cited_by_count":34},{"id":"2501.07861","title":"ReARTeR: Retrieval-Augmented Reasoning with Trustworthy Process Rewarding","created":"2025-01-14","cited_by_count":32},{"id":"2505.17005","title":"R1-Searcher++: Incentivizing the Dynamic Knowledge Acquisition of LLMs via Reinforcement Learning","created":"2025-05-22","cited_by_count":30},{"id":"2504.15909","title":"Synergizing RAG and Reasoning: A Systematic Review","created":"2025-04-22","cited_by_count":27},{"id":"2412.02830","title":"RARE: Retrieval-Augmented Reasoning Enhancement for Large Language Models","created":"2024-12-03","cited_by_count":25},{"id":"2508.12800","title":"Atom-Searcher: Enhancing Agentic Deep Research via Fine-Grained Atomic Thought Reward","created":"2025-08-18","cited_by_count":25},{"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},{"id":"2501.11551","title":"PIKE-RAG: sPecIalized KnowledgE and Rationale Augmented Generation","created":"2025-01-20","cited_by_count":18},{"id":"2503.08275","title":"Beyond Outlining: Heterogeneous Recursive Planning for Adaptive Long-form Writing with Language Models","created":"2025-03-11","cited_by_count":16},{"id":"2408.11875","title":"Hierarchical Retrieval-Augmented Generation Model with Rethink for Multi-hop Question Answering","created":"2024-08-20","cited_by_count":14},{"id":"2503.21729","title":"ReaRAG: Knowledge-guided Reasoning Enhances Factuality of Large Reasoning Models with Iterative Retrieval Augmented Generation","created":"2025-03-27","cited_by_count":13},{"id":"2210.17525","title":"Query Refinement Prompts for Closed-Book Long-Form Question Answering","created":"2022-10-31","cited_by_count":12},{"id":"2410.20753","title":"Plan*RAG: Efficient Test-Time Planning for Retrieval Augmented Generation","created":"2024-10-28","cited_by_count":11},{"id":"2502.15684","title":"An Agent Framework for Real-Time Financial Information Searching with Large Language Models","created":"2024-12-14","cited_by_count":5},{"id":"2508.07956","title":"Careful Queries, Credible Results: Teaching RAG Models Advanced Web Search Tools with Reinforcement Learning","created":"2025-08-11","cited_by_count":4},{"id":"2409.09322","title":"A Compressive Memory-based Retrieval Approach for Event Argument Extraction","created":"2024-09-14","cited_by_count":3}],"next_cursor":null}