{"list":"other","total":117,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"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":"2311.12022","title":"GPQA: A Graduate-Level Google-Proof Q&A Benchmark","created":"2023-11-20","cited_by_count":2879},{"id":"2308.11432","title":"A Survey on Large Language Model based Autonomous Agents","created":"2023-08-22","cited_by_count":2242},{"id":"2312.10997","title":"Retrieval-Augmented Generation for Large Language Models: A Survey","created":"2023-12-18","cited_by_count":2212},{"id":"2310.11511","title":"Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection","created":"2023-10-17","cited_by_count":1839},{"id":"1611.09268","title":"MS MARCO: A Human Generated MAchine Reading COmprehension Dataset","created":"2016-11-28","cited_by_count":1605},{"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":"2402.14008","title":"OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems","created":"2024-02-21","cited_by_count":1136},{"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":"2311.12983","title":"GAIA: a benchmark for General AI Assistants","created":"2023-11-21","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":"2502.12110","title":"A-MEM: Agentic Memory for LLM Agents","created":"2025-02-17","cited_by_count":1063},{"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":"2101.02235","title":"Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategies","created":"2021-01-06","cited_by_count":743},{"id":"2504.12516","title":"BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agents","created":"2025-04-16","cited_by_count":647},{"id":"2009.02252","title":"KILT: a Benchmark for Knowledge Intensive Language Tasks","created":"2020-09-04","cited_by_count":573},{"id":"2004.14974","title":"Fact or Fiction: Verifying Scientific Claims","created":"2020-04-30","cited_by_count":554},{"id":"2305.15294","title":"Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergy","created":"2023-05-24","cited_by_count":346},{"id":"2504.21776","title":"WebThinker: Empowering Large Reasoning Models with Deep Research Capability","created":"2025-04-30","cited_by_count":335},{"id":"2212.14024","title":"Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLP","created":"2022-12-28","cited_by_count":318},{"id":"2401.07339","title":"CodeAgent: Enhancing Code Generation with Tool-Integrated Agent Systems for Real-World Repo-level Coding Challenges","created":"2024-01-14","cited_by_count":282},{"id":"2503.24235","title":"A Survey on Test-Time Scaling in Large Language Models: What, How, Where, and How Well?","created":"2025-03-31","cited_by_count":223},{"id":"2011.03088","title":"HoVer: A Dataset for Many-Hop Fact Extraction And Claim Verification","created":"2020-11-05","cited_by_count":201},{"id":"2106.05707","title":"FEVEROUS: Fact Extraction and VERification Over Unstructured and Structured information","created":"2021-06-10","cited_by_count":167},{"id":"2402.04253","title":"AnyTool: Self-Reflective, Hierarchical Agents for Large-Scale API Calls","created":"2024-02-06","cited_by_count":124},{"id":"2305.13269","title":"Chain-of-Knowledge: Grounding Large Language Models via Dynamic Knowledge Adapting over Heterogeneous Sources","created":"2023-05-22","cited_by_count":122},{"id":"2506.13651","title":"xbench: Tracking Agents Productivity Scaling with Profession-Aligned Real-World Evaluations","created":"2025-06-16","cited_by_count":120},{"id":"2205.12487","title":"End-to-End Multimodal Fact-Checking and Explanation Generation: A Challenging Dataset and Models","created":"2022-05-25","cited_by_count":107},{"id":"2308.13259","title":"Knowledge-Driven CoT: Exploring Faithful Reasoning in LLMs for Knowledge-intensive Question Answering","created":"2023-08-25","cited_by_count":97},{"id":"2507.06229","title":"Agent KB: Leveraging Cross-Domain Experience for Agentic Problem Solving","created":"2025-07-08","cited_by_count":94},{"id":"2308.11131","title":"ReLLa: Retrieval-enhanced Large Language Models for Lifelong Sequential Behavior Comprehension in Recommendation","created":"2023-08-22","cited_by_count":77},{"id":"2403.05313","title":"RAT: Retrieval Augmented Thoughts Elicit Context-Aware Reasoning in Long-Horizon Generation","created":"2024-03-08","cited_by_count":75},{"id":"2506.01062","title":"SealQA: Raising the Bar for Reasoning in Search-Augmented Language Models","created":"2025-06-01","cited_by_count":75},{"id":"2304.14732","title":"Search-in-the-Chain: Interactively Enhancing Large Language Models with Search for Knowledge-intensive Tasks","created":"2023-04-28","cited_by_count":73},{"id":"2503.18968","title":"MedAgent-Pro: Towards Evidence-based Multi-modal Medical Diagnosis via Reasoning Agentic Workflow","created":"2025-03-21","cited_by_count":73},{"id":"2404.10952","title":"Can Language Models Solve Olympiad Programming?","created":"2024-04-16","cited_by_count":72},{"id":"2505.22019","title":"VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning","created":"2025-05-28","cited_by_count":68},{"id":"2407.20183","title":"MindSearch: Mimicking Human Minds Elicits Deep AI Searcher","created":"2024-07-29","cited_by_count":66},{"id":"2410.17236","title":"Large Language Models Empowered Personalized Web Agents","created":"2024-10-22","cited_by_count":66},{"id":"2502.18017","title":"ViDoRAG: Visual Document Retrieval-Augmented Generation via Dynamic Iterative Reasoning Agents","created":"2025-02-25","cited_by_count":66},{"id":"2402.15235","title":"MACRec: a Multi-Agent Collaboration Framework for Recommendation","created":"2024-02-23","cited_by_count":58},{"id":"2502.12018","title":"Atom of Thoughts for Markov LLM Test-Time Scaling","created":"2025-02-17","cited_by_count":54},{"id":"2011.07127","title":"IIRC: A Dataset of Incomplete Information Reading Comprehension Questions","created":"2020-11-13","cited_by_count":53},{"id":"2405.15114","title":"Let Me Do It For You: Towards LLM Empowered Recommendation via Tool Learning","created":"2024-05-24","cited_by_count":51},{"id":"2406.14891","title":"Generate-then-Ground in Retrieval-Augmented Generation for Multi-hop Question Answering","created":"2024-06-21","cited_by_count":51},{"id":"2104.04725","title":"Fool Me Twice: Entailment from Wikipedia Gamification","created":"2021-04-10","cited_by_count":50},{"id":"2506.02839","title":"DeepShop: A Benchmark for Deep Research Shopping Agents","created":"2025-06-03","cited_by_count":46},{"id":"2504.04736","title":"Synthetic Data Generation & Multi-Step RL for Reasoning & Tool Use","created":"2025-04-07","cited_by_count":45},{"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":"2407.13101","title":"Retrieve, Summarize, Plan: Advancing Multi-hop Question Answering with an Iterative Approach","created":"2024-07-18","cited_by_count":40},{"id":"2009.06401","title":"Multi-Hop Fact Checking of Political Claims","created":"2020-09-10","cited_by_count":37},{"id":"2406.13397","title":"MoreHopQA: More Than Multi-hop Reasoning","created":"2024-06-19","cited_by_count":37},{"id":"2310.09754","title":"EX-FEVER: A Dataset for Multi-hop Explainable Fact Verification","created":"2023-10-15","cited_by_count":36},{"id":"2505.06416","title":"ScaleMCP: Dynamic and Auto-Synchronizing Model Context Protocol Tools for LLM Agents","created":"2025-05-09","cited_by_count":36},{"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":"2410.23000","title":"Long$^2$RAG: Evaluating Long-Context & Long-Form Retrieval-Augmented Generation with Key Point Recall","created":"2024-10-30","cited_by_count":32},{"id":"2501.07861","title":"ReARTeR: Retrieval-Augmented Reasoning with Trustworthy Process Rewarding","created":"2025-01-14","cited_by_count":32},{"id":"2505.14963","title":"MedBrowseComp: Benchmarking Medical Deep Research and Computer Use","created":"2025-05-20","cited_by_count":30},{"id":"2506.10821","title":"VideoExplorer: Think With Videos For Agentic Long-Video Understanding","created":"2025-06-12","cited_by_count":29},{"id":"2506.14035","title":"SimpleDoc: Multi-Modal Document Understanding with Dual-Cue Page Retrieval and Iterative Refinement","created":"2025-06-16","cited_by_count":28},{"id":"2411.13154","title":"DMQR-RAG: Diverse Multi-Query Rewriting for RAG","created":"2024-11-20","cited_by_count":27},{"id":"2504.15909","title":"Synergizing RAG and Reasoning: A Systematic Review","created":"2025-04-22","cited_by_count":27},{"id":"2410.01782","title":"Open-RAG: Enhanced Retrieval-Augmented Reasoning with Open-Source Large Language Models","created":"2024-10-02","cited_by_count":25},{"id":"2410.22257","title":"FactBench: A Dynamic Benchmark for In-the-Wild Language Model Factuality Evaluation","created":"2024-10-29","cited_by_count":25},{"id":"2412.14835","title":"Progressive Multimodal Reasoning via Active Retrieval","created":"2024-12-19","cited_by_count":25},{"id":"2506.08500","title":"DRAGged into Conflicts: Detecting and Addressing Conflicting Sources in Search-Augmented LLMs","created":"2025-06-10","cited_by_count":25},{"id":"2404.03746","title":"GenQREnsemble: Zero-Shot LLM Ensemble Prompting for Generative Query Reformulation","created":"2024-04-04","cited_by_count":23},{"id":"2410.14594","title":"Toolshed: Scale Tool-Equipped Agents with Advanced RAG-Tool Fusion and Tool Knowledge Bases","created":"2024-10-18","cited_by_count":23},{"id":"2505.24332","title":"DeepDiver: Adaptive Search Intensity Scaling via Open-Web Reinforcement Learning","created":"2025-05-30","cited_by_count":23},{"id":"2506.23139","title":"Benchmarking Deep Search over Heterogeneous Enterprise Data","created":"2025-06-29","cited_by_count":23},{"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":"2506.02454","title":"Multimodal DeepResearcher: Generating Text-Chart Interleaved Reports From Scratch with Agentic Framework","created":"2025-06-03","cited_by_count":21},{"id":"2506.12364","title":"MM-R5: MultiModal Reasoning-Enhanced ReRanker via Reinforcement Learning for Document Retrieval","created":"2025-06-14","cited_by_count":21},{"id":"2506.11060","title":"Code Researcher: Deep Research Agent for Large Systems Code and Commit History","created":"2025-05-27","cited_by_count":20},{"id":"2104.06077","title":"An Adversarial Imitation Click Model for Information Retrieval","created":"2021-04-13","cited_by_count":18},{"id":"2206.08621","title":"A Graph-Enhanced Click Model for Web Search","created":"2022-06-17","cited_by_count":17},{"id":"2410.23214","title":"Grounding by Trying: LLMs with Reinforcement Learning-Enhanced Retrieval","created":"2024-10-30","cited_by_count":17},{"id":"2407.18553","title":"REAPER: Reasoning based Retrieval Planning for Complex RAG Systems","created":"2024-07-26","cited_by_count":16},{"id":"2502.10996","title":"RAS: Retrieval-And-Structuring for Knowledge-Intensive LLM Generation","created":"2025-02-16","cited_by_count":16},{"id":"2507.02962","title":"RAG-R1: Incentivizing the Search and Reasoning Capabilities of LLMs through Multi-query Parallelism","created":"2025-06-30","cited_by_count":16},{"id":"2406.18960","title":"A Surprisingly Simple yet Effective Multi-Query Rewriting Method for Conversational Passage Retrieval","created":"2024-06-27","cited_by_count":14},{"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":"2506.20100","title":"MIRAGE: A Benchmark for Multimodal Information-Seeking and Reasoning in Agricultural Expert-Guided Conversations","created":"2025-06-25","cited_by_count":13},{"id":"2504.16787","title":"Credible Plan-Driven RAG Method for Multi-Hop Question Answering","created":"2025-04-23","cited_by_count":12},{"id":"2506.21931","title":"ARAG: Agentic Retrieval Augmented Generation for Personalized Recommendation","created":"2025-06-27","cited_by_count":12},{"id":"2206.08604","title":"An F-shape Click Model for Information Retrieval on Multi-block Mobile Pages","created":"2022-06-17","cited_by_count":10},{"id":"2408.05676","title":"Efficiency Unleashed: Inference Acceleration for LLM-based Recommender Systems with Speculative Decoding","created":"2024-08-11","cited_by_count":10},{"id":"2412.16086","title":"Towards Interpretable Radiology Report Generation via Concept Bottlenecks using a Multi-Agentic RAG","created":"2024-12-20","cited_by_count":9},{"id":"2501.10053","title":"AirRAG: Autonomous Strategic Planning and Reasoning Steer Retrieval Augmented Generation","created":"2025-01-17","cited_by_count":9},{"id":"2502.20730","title":"DeepSolution: Boosting Complex Engineering Solution Design via Tree-based Exploration and Bi-point Thinking","created":"2025-02-28","cited_by_count":9},{"id":"2506.12538","title":"RealFactBench: A Benchmark for Evaluating Large Language Models in Real-World Fact-Checking","created":"2025-06-14","cited_by_count":9},{"id":"2503.01642","title":"Graph-Augmented Reasoning: Evolving Step-by-Step Knowledge Graph Retrieval for LLM Reasoning","created":"2025-03-03","cited_by_count":8},{"id":"2506.13784","title":"ScholarSearch: Benchmarking Scholar Searching Ability of LLMs","created":"2025-06-11","cited_by_count":8},{"id":"2507.02652","title":"HiRA: A Hierarchical Reasoning Framework for Decoupled Planning and Execution in Deep Search","created":"2025-07-03","cited_by_count":8},{"id":"2403.19302","title":"Generating Multi-Aspect Queries for Conversational Search","created":"2024-03-28","cited_by_count":7}],"next_cursor":"100"}