{"list":"other","total":52,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"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":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"2501.12948","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","created":"2025-01-22","cited_by_count":6330},{"id":"2412.15115","title":"Qwen2.5 Technical Report","created":"2024-12-19","cited_by_count":4942},{"id":"2302.04761","title":"Toolformer: Language Models Can Teach Themselves to Use Tools","created":"2023-02-09","cited_by_count":4182},{"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":"2210.11416","title":"Scaling Instruction-Finetuned Language Models","created":"2022-10-20","cited_by_count":3024},{"id":"1705.03551","title":"TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension","created":"2017-05-09","cited_by_count":2955},{"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":"2009.13081","title":"What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Exams","created":"2020-09-28","cited_by_count":1356},{"id":"1909.06146","title":"PubMedQA: A Dataset for Biomedical Research Question Answering","created":"2019-09-13","cited_by_count":1288},{"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":"1712.09913","title":"Visualizing the Loss Landscape of Neural Nets","created":"2017-12-28","cited_by_count":1130},{"id":"2212.10511","title":"When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories","created":"2022-12-20","cited_by_count":1128},{"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":"2301.12652","title":"REPLUG: Retrieval-Augmented Black-Box Language Models","created":"2023-01-30","cited_by_count":792},{"id":"2302.00083","title":"In-Context Retrieval-Augmented Language Models","created":"2023-01-31","cited_by_count":702},{"id":"2507.20534","title":"Kimi K2: Open Agentic Intelligence","created":"2025-07-28","cited_by_count":567},{"id":"2203.14371","title":"MedMCQA : A Large-scale Multi-Subject Multi-Choice Dataset for Medical domain Question Answering","created":"2022-03-27","cited_by_count":543},{"id":"2501.05366","title":"Search-o1: Agentic Search-Enhanced Large Reasoning Models","created":"2025-01-09","cited_by_count":433},{"id":"2503.05592","title":"R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning","created":"2025-03-07","cited_by_count":336},{"id":"2402.13178","title":"Benchmarking Retrieval-Augmented Generation for Medicine","created":"2024-02-20","cited_by_count":331},{"id":"1911.02590","title":"Optimizing Millions of Hyperparameters by Implicit Differentiation","created":"2019-11-06","cited_by_count":304},{"id":"2402.00157","title":"Large Language Models for Mathematical Reasoning: Progresses and Challenges","created":"2024-01-31","cited_by_count":284},{"id":"2403.10131","title":"RAFT: Adapting Language Model to Domain Specific RAG","created":"2024-03-15","cited_by_count":262},{"id":"1602.05179","title":"Equilibrium Propagation: Bridging the Gap Between Energy-Based Models and Backpropagation","created":"2016-02-16","cited_by_count":259},{"id":"2010.07962","title":"Bilevel Optimization: Convergence Analysis and Enhanced Design","created":"2020-10-15","cited_by_count":222},{"id":"2305.14283","title":"Query Rewriting for Retrieval-Augmented Large Language Models","created":"2023-05-23","cited_by_count":213},{"id":"2310.01352","title":"RA-DIT: Retrieval-Augmented Dual Instruction Tuning","created":"2023-10-02","cited_by_count":195},{"id":"2307.00589","title":"MedCPT: Contrastive Pre-trained Transformers with Large-scale PubMed Search Logs for Zero-shot Biomedical Information Retrieval","created":"2023-07-02","cited_by_count":185},{"id":"2301.10945","title":"A Fully First-Order Method for Stochastic Bilevel Optimization","created":"2023-01-26","cited_by_count":100},{"id":"2302.05185","title":"On Penalty-based Bilevel Gradient Descent Method","created":"2023-02-10","cited_by_count":87},{"id":"2410.07471","title":"SEAL: Safety-enhanced Aligned LLM Fine-tuning via Bilevel Data Selection","created":"2024-10-09","cited_by_count":64},{"id":"2309.01753","title":"On Penalty Methods for Nonconvex Bilevel Optimization and First-Order Stochastic Approximation","created":"2023-09-04","cited_by_count":51},{"id":"2505.14146","title":"s3: You Don't Need That Much Data to Train a Search Agent via RL","created":"2025-05-20","cited_by_count":42},{"id":"2501.15228","title":"Improving Retrieval-Augmented Generation through Multi-Agent Reinforcement Learning","created":"2025-01-25","cited_by_count":39},{"id":"2205.03076","title":"Beyond backpropagation: bilevel optimization through implicit differentiation and equilibrium propagation","created":"2022-05-06","cited_by_count":26},{"id":"2507.07988","title":"Automating Expert-Level Medical Reasoning Evaluation of Large Language Models","created":"2025-07-10","cited_by_count":22},{"id":"2410.18141","title":"SmartRAG: Jointly Learn RAG-Related Tasks From the Environment Feedback","created":"2024-10-22","cited_by_count":19},{"id":"2505.07233","title":"DynamicRAG: Leveraging Outputs of Large Language Model as Feedback for Dynamic Reranking in Retrieval-Augmented Generation","created":"2025-05-12","cited_by_count":15},{"id":"2601.11888","title":"Agentic-R: Learning to Retrieve for Agentic Search","created":"2026-01-17","cited_by_count":11},{"id":"2605.24218","title":"QUEST: Training Frontier Deep Research Agents with Fully Synthetic Tasks","created":"2026-05-22","cited_by_count":11},{"id":"2505.03075","title":"Direct Retrieval-augmented Optimization: Synergizing Knowledge Selection and Language Models","created":"2025-05-05","cited_by_count":9},{"id":"2507.20400","title":"Beyond Value Functions: Single-Loop Bilevel Optimization under Flatness Conditions","created":"2025-07-27","cited_by_count":9},{"id":"2502.08585","title":"LDC-MTL: Balancing Multi-Task Learning through Scalable Loss Discrepancy Control","created":"2025-02-12","cited_by_count":7}],"next_cursor":null}