{"list":"other","total":54,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"2203.11171","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","created":"2022-03-21","cited_by_count":5708},{"id":"2103.03874","title":"Measuring Mathematical Problem Solving With the MATH Dataset","created":"2021-03-05","cited_by_count":5371},{"id":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"id":"2305.20050","title":"Let's Verify Step by Step","created":"2023-05-31","cited_by_count":3789},{"id":"1809.09600","title":"HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering","created":"2018-09-25","cited_by_count":3754},{"id":"2108.07732","title":"Program Synthesis with Large Language Models","created":"2021-08-16","cited_by_count":3637},{"id":"2109.07958","title":"TruthfulQA: Measuring How Models Mimic Human Falsehoods","created":"2021-09-08","cited_by_count":2975},{"id":"1705.03551","title":"TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension","created":"2017-05-09","cited_by_count":2955},{"id":"1911.11641","title":"PIQA: Reasoning about Physical Commonsense in Natural Language","created":"2019-11-26","cited_by_count":2883},{"id":"2111.00396","title":"Efficiently Modeling Long Sequences with Structured State Spaces","created":"2021-10-31","cited_by_count":2465},{"id":"1809.02789","title":"Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering","created":"2018-09-08","cited_by_count":2164},{"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":"2210.09261","title":"Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them","created":"2022-10-17","cited_by_count":1807},{"id":"1905.00537","title":"SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems","created":"2019-05-02","cited_by_count":1729},{"id":"2310.08560","title":"MemGPT: Towards LLMs as Operating Systems","created":"2023-10-12","cited_by_count":1389},{"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":"2409.12122","title":"Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement","created":"2024-09-18","cited_by_count":1090},{"id":"2310.13548","title":"Towards Understanding Sycophancy in Language Models","created":"2023-10-20","cited_by_count":1040},{"id":"2305.05176","title":"FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance","created":"2023-05-09","cited_by_count":853},{"id":"1707.06209","title":"Crowdsourcing Multiple Choice Science Questions","created":"2017-07-19","cited_by_count":765},{"id":"2503.13657","title":"Why Do Multi-Agent LLM Systems Fail?","created":"2025-03-17","cited_by_count":604},{"id":"2306.02561","title":"LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusion","created":"2023-06-05","cited_by_count":564},{"id":"2305.10250","title":"MemoryBank: Enhancing Large Language Models with Long-Term Memory","created":"2023-05-17","cited_by_count":556},{"id":"2503.01743","title":"Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs","created":"2025-03-03","cited_by_count":521},{"id":"2602.02276","title":"Kimi K2.5: Visual Agentic Intelligence","created":"2026-02-02","cited_by_count":501},{"id":"2406.04692","title":"Mixture-of-Agents Enhances Large Language Model Capabilities","created":"2024-06-07","cited_by_count":438},{"id":"2309.13007","title":"ReConcile: Round-Table Conference Improves Reasoning via Consensus among Diverse LLMs","created":"2023-09-22","cited_by_count":309},{"id":"2402.06782","title":"Debating with More Persuasive LLMs Leads to More Truthful Answers","created":"2024-02-09","cited_by_count":266},{"id":"2604.15804","title":"Qwen3.5-Omni Technical Report","created":"2026-04-17","cited_by_count":174},{"id":"2311.08692","title":"Routing to the Expert: Efficient Reward-guided Ensemble of Large Language Models","created":"2023-11-15","cited_by_count":145},{"id":"2403.02884","title":"MathScale: Scaling Instruction Tuning for Mathematical Reasoning","created":"2024-03-05","cited_by_count":144},{"id":"2504.15965","title":"From Human Memory to AI Memory: A Survey on Memory Mechanisms in the Era of LLMs","created":"2025-04-22","cited_by_count":124},{"id":"2407.04622","title":"On scalable oversight with weak LLMs judging strong LLMs","created":"2024-07-05","cited_by_count":99},{"id":"2501.05707","title":"Multiagent Finetuning: Self Improvement with Diverse Reasoning Chains","created":"2025-01-10","cited_by_count":95},{"id":"2402.16823","title":"Language Agents as Optimizable Graphs","created":"2024-02-26","cited_by_count":89},{"id":"2508.17536","title":"Debate or Vote: Which Yields Better Decisions in Multi-Agent Large Language Models?","created":"2025-08-24","cited_by_count":81},{"id":"2509.05396","title":"Talk Isn't Always Cheap: Understanding Failure Modes in Multi-Agent Debate","created":"2025-09-05","cited_by_count":66},{"id":"2503.05061","title":"No Free Labels: Limitations of LLM-as-a-Judge Without Human Grounding","created":"2025-03-07","cited_by_count":54},{"id":"2506.07900","title":"MiniCPM4: Ultra-Efficient LLMs on End Devices","created":"2025-06-09","cited_by_count":52},{"id":"2502.12964","title":"Trust Me, I'm Wrong: LLMs Hallucinate with Certainty Despite Knowing the Answer","created":"2025-02-18","cited_by_count":27},{"id":"2406.08598","title":"Language Model Council: Democratically Benchmarking Foundation Models on Highly Subjective Tasks","created":"2024-06-12","cited_by_count":18},{"id":"2506.15672","title":"SwarmAgentic: Towards Fully Automated Agentic System Generation via Swarm Intelligence","created":"2025-06-18","cited_by_count":18},{"id":"2508.05687","title":"Risk Analysis Techniques for Governed LLM-based Multi-Agent Systems","created":"2025-08-06","cited_by_count":18},{"id":"2508.18321","title":"LLMs Can't Handle Peer Pressure: Crumbling under Multi-Agent Social Interactions","created":"2025-08-24","cited_by_count":16},{"id":"2605.12357","title":"$\\delta$-mem: Efficient Online Memory for Large Language Models","created":"2026-05-12","cited_by_count":13},{"id":"2607.08716","title":"Remember When It Matters: Proactive Memory Agent for Long-Horizon Agents","created":"2026-07-09","cited_by_count":11},{"id":"2601.21742","title":"Epistemic Context Learning: Building Trust the Right Way in LLM-Based Multi-Agent Systems","created":"2026-01-29","cited_by_count":6}],"next_cursor":null}