{"list":"other","total":103,"rows":[{"id":"2210.03629","title":"ReAct: Synergizing Reasoning and Acting in Language Models","created":"2022-10-06","cited_by_count":8695},{"id":"2103.03874","title":"Measuring Mathematical Problem Solving With the MATH Dataset","created":"2021-03-05","cited_by_count":5371},{"id":"2302.04761","title":"Toolformer: Language Models Can Teach Themselves to Use Tools","created":"2023-02-09","cited_by_count":4182},{"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":"2403.07974","title":"LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code","created":"2024-03-12","cited_by_count":2004},{"id":"2206.04615","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","created":"2022-06-09","cited_by_count":1998},{"id":"2307.16789","title":"ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs","created":"2023-07-31","cited_by_count":1947},{"id":"2209.09513","title":"Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering","created":"2022-09-20","cited_by_count":1919},{"id":"2406.01574","title":"MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark","created":"2024-06-03","cited_by_count":1848},{"id":"2310.11511","title":"Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection","created":"2023-10-17","cited_by_count":1839},{"id":"2112.09332","title":"WebGPT: Browser-assisted question-answering with human feedback","created":"2021-12-17","cited_by_count":1745},{"id":"2311.05232","title":"A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions","created":"2023-11-09","cited_by_count":1601},{"id":"1803.05355","title":"FEVER: a large-scale dataset for Fact Extraction and VERification","created":"2018-03-14","cited_by_count":1375},{"id":"1808.08745","title":"Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization","created":"2018-08-27","cited_by_count":1317},{"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":"2207.01206","title":"WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents","created":"2022-07-04","cited_by_count":1251},{"id":"2010.03768","title":"ALFWorld: Aligning Text and Embodied Environments for Interactive Learning","created":"2020-10-08","cited_by_count":1205},{"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":"2408.06292","title":"The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery","created":"2024-08-12","cited_by_count":1071},{"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":"1710.03957","title":"DailyDialog: A Manually Labelled Multi-turn Dialogue Dataset","created":"2017-10-11","cited_by_count":652},{"id":"1705.04146","title":"Program Induction by Rationale Generation : Learning to Solve and Explain Algebraic Word Problems","created":"2017-05-11","cited_by_count":650},{"id":"2504.12516","title":"BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agents","created":"2025-04-16","cited_by_count":647},{"id":"2503.16419","title":"Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models","created":"2025-03-20","cited_by_count":464},{"id":"2403.14403","title":"Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexity","created":"2024-03-21","cited_by_count":451},{"id":"2501.04227","title":"Agent Laboratory: Using LLM Agents as Research Assistants","created":"2025-01-08","cited_by_count":425},{"id":"1803.06643","title":"The Web as a Knowledge-base for Answering Complex Questions","created":"2018-03-18","cited_by_count":410},{"id":"2109.00110","title":"MiniF2F: a cross-system benchmark for formal Olympiad-level mathematics","created":"2021-08-31","cited_by_count":391},{"id":"2104.06378","title":"QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answering","created":"2021-04-13","cited_by_count":388},{"id":"2310.01558","title":"Making Retrieval-Augmented Language Models Robust to Irrelevant Context","created":"2023-10-02","cited_by_count":369},{"id":"2403.10131","title":"RAFT: Adapting Language Model to Domain Specific RAG","created":"2024-03-15","cited_by_count":262},{"id":"2401.15391","title":"MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries","created":"2024-01-27","cited_by_count":257},{"id":"2502.12067","title":"TokenSkip: Controllable Chain-of-Thought Compression in LLMs","created":"2025-02-17","cited_by_count":249},{"id":"2305.11554","title":"ToolkenGPT: Augmenting Frozen Language Models with Massive Tools via Tool Embeddings","created":"2023-05-19","cited_by_count":240},{"id":"2010.09926","title":"Explainable Automated Fact-Checking for Public Health Claims","created":"2020-10-19","cited_by_count":211},{"id":"2112.08608","title":"QuALITY: Question Answering with Long Input Texts, Yes!","created":"2021-12-16","cited_by_count":208},{"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":"2310.01352","title":"RA-DIT: Retrieval-Augmented Dual Instruction Tuning","created":"2023-10-02","cited_by_count":195},{"id":"1904.09537","title":"PullNet: Open Domain Question Answering with Iterative Retrieval on Knowledge Bases and Text","created":"2019-04-21","cited_by_count":184},{"id":"2311.09210","title":"Chain-of-Note: Enhancing Robustness in Retrieval-Augmented Language Models","created":"2023-11-15","cited_by_count":184},{"id":"2407.01523","title":"MMLongBench-Doc: Benchmarking Long-context Document Understanding with Visualizations","created":"2024-07-01","cited_by_count":183},{"id":"2503.12605","title":"Multimodal Chain-of-Thought Reasoning: A Comprehensive Survey","created":"2025-03-16","cited_by_count":182},{"id":"2501.07572","title":"WebWalker: Benchmarking LLMs in Web Traversal","created":"2025-01-13","cited_by_count":175},{"id":"2311.05997","title":"JARVIS-1: Open-World Multi-task Agents with Memory-Augmented Multimodal Language Models","created":"2023-11-10","cited_by_count":171},{"id":"1906.03741","title":"BIGPATENT: A Large-Scale Dataset for Abstractive and Coherent Summarization","created":"2019-06-10","cited_by_count":156},{"id":"2308.11730","title":"Knowledge Graph Prompting for Multi-Document Question Answering","created":"2023-08-22","cited_by_count":152},{"id":"2504.19314","title":"BrowseComp-ZH: Benchmarking Web Browsing Ability of Large Language Models in Chinese","created":"2025-04-27","cited_by_count":145},{"id":"2503.15478","title":"SWEET-RL: Training Multi-Turn LLM Agents on Collaborative Reasoning Tasks","created":"2025-03-19","cited_by_count":118},{"id":"2502.15589","title":"LightThinker: Thinking Step-by-Step Compression","created":"2025-02-21","cited_by_count":104},{"id":"2110.00768","title":"TopiOCQA: Open-domain Conversational Question Answering with Topic Switching","created":"2021-10-02","cited_by_count":96},{"id":"2202.13296","title":"Subgraph Retrieval Enhanced Model for Multi-hop Knowledge Base Question Answering","created":"2022-02-27","cited_by_count":93},{"id":"1805.00713","title":"CrisisMMD: Multimodal Twitter Datasets from Natural Disasters","created":"2018-05-02","cited_by_count":89},{"id":"2109.01653","title":"CREAK: A Dataset for Commonsense Reasoning over Entity Knowledge","created":"2021-09-03","cited_by_count":88},{"id":"2402.03610","title":"RAP: Retrieval-Augmented Planning with Contextual Memory for Multimodal LLM Agents","created":"2024-02-06","cited_by_count":80},{"id":"2303.08518","title":"UPRISE: Universal Prompt Retrieval for Improving Zero-Shot Evaluation","created":"2023-03-15","cited_by_count":75},{"id":"2305.14128","title":"Dr.ICL: Demonstration-Retrieved In-context Learning","created":"2023-05-23","cited_by_count":72},{"id":"2404.04302","title":"CBR-RAG: Case-Based Reasoning for Retrieval Augmented Generation in LLMs for Legal Question Answering","created":"2024-04-04","cited_by_count":72},{"id":"2406.11200","title":"AvaTaR: Optimizing LLM Agents for Tool Usage via Contrastive Reasoning","created":"2024-06-17","cited_by_count":72},{"id":"2412.18424","title":"LongDocURL: a Comprehensive Multimodal Long Document Benchmark Integrating Understanding, Reasoning, and Locating","created":"2024-12-24","cited_by_count":72},{"id":"2305.13068","title":"Making Language Models Better Tool Learners with Execution Feedback","created":"2023-05-22","cited_by_count":70},{"id":"2503.13964","title":"MDocAgent: A Multi-Modal Multi-Agent Framework for Document Understanding","created":"2025-03-18","cited_by_count":67},{"id":"2407.20183","title":"MindSearch: Mimicking Human Minds Elicits Deep AI Searcher","created":"2024-07-29","cited_by_count":66},{"id":"2409.14924","title":"Retrieval Augmented Generation (RAG) and Beyond: A Comprehensive Survey on How to Make your LLMs use External Data More Wisely","created":"2024-09-23","cited_by_count":66},{"id":"2411.02937","title":"Benchmarking Multimodal Retrieval Augmented Generation with Dynamic VQA Dataset and Self-adaptive Planning Agent","created":"2024-11-05","cited_by_count":65},{"id":"2011.07127","title":"IIRC: A Dataset of Incomplete Information Reading Comprehension Questions","created":"2020-11-13","cited_by_count":53},{"id":"2310.07713","title":"InstructRetro: Instruction Tuning post Retrieval-Augmented Pretraining","created":"2023-10-11","cited_by_count":53},{"id":"2408.01875","title":"Re-Invoke: Tool Invocation Rewriting for Zero-Shot Tool Retrieval","created":"2024-08-03","cited_by_count":52},{"id":"2405.04819","title":"DALK: Dynamic Co-Augmentation of LLMs and KG to answer Alzheimer's Disease Questions with Scientific Literature","created":"2024-05-08","cited_by_count":50},{"id":"2406.02746","title":"RATT: A Thought Structure for Coherent and Correct LLM Reasoning","created":"2024-06-04","cited_by_count":41},{"id":"2406.15187","title":"UDA: A Benchmark Suite for Retrieval Augmented Generation in Real-world Document Analysis","created":"2024-06-21","cited_by_count":40},{"id":"2405.16420","title":"M-RAG: Reinforcing Large Language Model Performance through Retrieval-Augmented Generation with Multiple Partitions","created":"2024-05-26","cited_by_count":38},{"id":"2402.17231","title":"MATHSENSEI: A Tool-Augmented Large Language Model for Mathematical Reasoning","created":"2024-02-27","cited_by_count":34},{"id":"2504.18875","title":"Generative to Agentic AI: Survey, Conceptualization, and Challenges","created":"2025-04-26","cited_by_count":33},{"id":"2504.12330","title":"HM-RAG: Hierarchical Multi-Agent Multimodal Retrieval Augmented Generation","created":"2025-04-13","cited_by_count":31},{"id":"2503.12759","title":"RAG-RL: Advancing Retrieval-Augmented Generation via RL and Curriculum Learning","created":"2025-03-17","cited_by_count":30},{"id":"2410.03227","title":"ALR$^2$: A Retrieve-then-Reason Framework for Long-context Question Answering","created":"2024-10-04","cited_by_count":26},{"id":"2406.14282","title":"Learning to Plan for Retrieval-Augmented Large Language Models from Knowledge Graphs","created":"2024-06-20","cited_by_count":24},{"id":"2410.07071","title":"Retrieval-Augmented Decision Transformer: External Memory for In-context RL","created":"2024-10-09","cited_by_count":21},{"id":"2401.06532","title":"INTERS: Unlocking the Power of Large Language Models in Search with Instruction Tuning","created":"2024-01-12","cited_by_count":20},{"id":"2412.17032","title":"MINTQA: A Multi-Hop Question Answering Benchmark for Evaluating LLMs on New and Tail Knowledge","created":"2024-12-22","cited_by_count":20},{"id":"2501.01945","title":"Cold-Start Recommendation towards the Era of Large Language Models (LLMs): A Comprehensive Survey and Roadmap","created":"2025-01-03","cited_by_count":20},{"id":"2504.18243","title":"DualRAG: A Dual-Process Approach to Integrate Reasoning and Retrieval for Multi-Hop Question Answering","created":"2025-04-25","cited_by_count":20},{"id":"2409.09916","title":"SFR-RAG: Towards Contextually Faithful LLMs","created":"2024-09-16","cited_by_count":19},{"id":"2403.09747","title":"Re-Search for The Truth: Multi-round Retrieval-augmented Large Language Models are Strong Fake News Detectors","created":"2024-03-14","cited_by_count":16},{"id":"2503.10265","title":"SurgRAW: Multi-Agent Workflow with Chain of Thought Reasoning for Robotic Surgical Video Analysis","created":"2025-03-13","cited_by_count":15},{"id":"2310.05388","title":"GROVE: A Retrieval-augmented Complex Story Generation Framework with A Forest of Evidence","created":"2023-10-09","cited_by_count":14},{"id":"2410.22353","title":"RuleRAG: Rule-Guided Retrieval-Augmented Generation with Language Models for Question Answering","created":"2024-10-15","cited_by_count":13},{"id":"2311.09175","title":"Can Query Expansion Improve Generalization of Strong Cross-Encoder Rankers?","created":"2023-11-15","cited_by_count":12},{"id":"2410.16670","title":"CoPS: Empowering LLM Agents with Provable Cross-Task Experience Sharing","created":"2024-10-22","cited_by_count":12},{"id":"2504.16787","title":"Credible Plan-Driven RAG Method for Multi-Hop Question Answering","created":"2025-04-23","cited_by_count":12},{"id":"2412.05838","title":"A Collaborative Multi-Agent Approach to Retrieval-Augmented Generation Across Diverse Data","created":"2024-12-08","cited_by_count":10},{"id":"2501.02727","title":"Tree-based RAG-Agent Recommendation System: A Case Study in Medical Test Data","created":"2025-01-06","cited_by_count":9},{"id":"2408.06520","title":"Retrieval-Augmented Hierarchical in-Context Reinforcement Learning and Hindsight Modular Reflections for Task Planning with LLMs","created":"2024-08-12","cited_by_count":8},{"id":"2502.05867","title":"Self-Training Large Language Models for Tool-Use Without Demonstrations","created":"2025-02-09","cited_by_count":7},{"id":"2505.04253","title":"LLM-Independent Adaptive RAG: Let the Question Speak for Itself","created":"2025-05-07","cited_by_count":7},{"id":"2406.10289","title":"VeraCT Scan: Retrieval-Augmented Fake News Detection with Justifiable Reasoning","created":"2024-06-12","cited_by_count":6}],"next_cursor":"100"}