{"list":"other","total":54,"rows":[{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820},{"id":"2501.12948","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","created":"2025-01-22","cited_by_count":6330},{"id":"2511.21631","title":"Qwen3-VL Technical Report","created":"2025-11-26","cited_by_count":2793},{"id":"2311.12793","title":"ShareGPT4V: Improving Large Multi-Modal Models with Better Captions","created":"2023-11-21","cited_by_count":1005},{"id":"2212.10403","title":"Towards Reasoning in Large Language Models: A Survey","created":"2022-12-20","cited_by_count":596},{"id":"2507.20534","title":"Kimi K2: Open Agentic Intelligence","created":"2025-07-28","cited_by_count":567},{"id":"2507.01006","title":"GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning","created":"2025-07-01","cited_by_count":466},{"id":"2407.11691","title":"VLMEvalKit: An Open-Source Toolkit for Evaluating Large Multi-Modality Models","created":"2024-07-16","cited_by_count":455},{"id":"2102.09542","title":"SLAKE: A Semantically-Labeled Knowledge-Enhanced Dataset for Medical Visual Question Answering","created":"2021-02-18","cited_by_count":449},{"id":"2311.08046","title":"Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding","created":"2023-11-14","cited_by_count":371},{"id":"2402.14762","title":"MT-Bench-101: A Fine-Grained Benchmark for Evaluating Large Language Models in Multi-Turn Dialogues","created":"2024-02-22","cited_by_count":250},{"id":"2407.13168","title":"SciCode: A Research Coding Benchmark Curated by Scientists","created":"2024-07-18","cited_by_count":178},{"id":"2401.04925","title":"The Impact of Reasoning Step Length on Large Language Models","created":"2024-01-10","cited_by_count":153},{"id":"2307.11019","title":"Investigating the Factual Knowledge Boundary of Large Language Models with Retrieval Augmentation","created":"2023-07-20","cited_by_count":147},{"id":"2309.02726","title":"Large Language Models for Automated Open-domain Scientific Hypotheses Discovery","created":"2023-09-06","cited_by_count":100},{"id":"2406.04271","title":"Buffer of Thoughts: Thought-Augmented Reasoning with Large Language Models","created":"2024-06-06","cited_by_count":91},{"id":"2402.08939","title":"Premise Order Matters in Reasoning with Large Language Models","created":"2024-02-14","cited_by_count":72},{"id":"2402.11451","title":"SciAgent: Tool-augmented Language Models for Scientific Reasoning","created":"2024-02-18","cited_by_count":70},{"id":"2404.15522","title":"LogicBench: Towards Systematic Evaluation of Logical Reasoning Ability of Large Language Models","created":"2024-04-23","cited_by_count":68},{"id":"2401.10334","title":"DrugAssist: A Large Language Model for Molecule Optimization","created":"2023-12-28","cited_by_count":59},{"id":"2410.07176","title":"Astute RAG: Overcoming Imperfect Retrieval Augmentation and Knowledge Conflicts for Large Language Models","created":"2024-10-09","cited_by_count":58},{"id":"2406.17626","title":"CoSafe: Evaluating Large Language Model Safety in Multi-Turn Dialogue Coreference","created":"2024-06-25","cited_by_count":51},{"id":"2405.08807","title":"SciFIBench: Benchmarking Large Multimodal Models for Scientific Figure Interpretation","created":"2024-05-14","cited_by_count":48},{"id":"2405.19487","title":"A Full-duplex Speech Dialogue Scheme Based On Large Language Models","created":"2024-05-29","cited_by_count":40},{"id":"2412.17767","title":"ResearchTown: Simulator of Human Research Community","created":"2024-12-23","cited_by_count":37},{"id":"2508.21148","title":"A Survey of Scientific Large Language Models: From Data Foundations to Agent Frontiers","created":"2025-08-28","cited_by_count":37},{"id":"2309.17050","title":"Interpretable Long-Form Legal Question Answering with Retrieval-Augmented Large Language Models","created":"2023-09-29","cited_by_count":35},{"id":"2506.10521","title":"Scientists' First Exam: Probing Cognitive Abilities of MLLM via Perception, Understanding, and Reasoning","created":"2025-06-12","cited_by_count":34},{"id":"2510.22115","title":"Every Activation Boosted: Scaling General Reasoner to 1 Trillion Open Language Foundation","created":"2025-10-25","cited_by_count":34},{"id":"2306.04556","title":"StudentEval: A Benchmark of Student-Written Prompts for Large Language Models of Code","created":"2023-06-07","cited_by_count":32},{"id":"2401.09334","title":"Large Language Models Are Neurosymbolic Reasoners","created":"2024-01-17","cited_by_count":31},{"id":"2502.06563","title":"Large Language Models Meet Symbolic Provers for Logical Reasoning Evaluation","created":"2025-02-10","cited_by_count":28},{"id":"2512.16969","title":"Probing Scientific General Intelligence of LLMs with Scientist-Aligned Workflows","created":"2025-12-18","cited_by_count":28},{"id":"2401.13837","title":"Democratizing Fine-grained Visual Recognition with Large Language Models","created":"2024-01-24","cited_by_count":25},{"id":"2509.01396","title":"DeepResearch Arena: The First Exam of LLMs' Research Abilities via Seminar-Grounded Tasks","created":"2025-09-01","cited_by_count":24},{"id":"2405.20574","title":"Open Ko-LLM Leaderboard: Evaluating Large Language Models in Korean with Ko-H5 Benchmark","created":"2024-05-31","cited_by_count":23},{"id":"2401.08206","title":"Generative Multi-Modal Knowledge Retrieval with Large Language Models","created":"2024-01-16","cited_by_count":22},{"id":"2410.16701","title":"ClimaQA: An Automated Evaluation Framework for Climate Question Answering Models","created":"2024-10-22","cited_by_count":21},{"id":"2406.05540","title":"A Fine-tuning Dataset and Benchmark for Large Language Models for Protein Understanding","created":"2024-06-08","cited_by_count":19},{"id":"2304.03659","title":"Probing Conceptual Understanding of Large Visual-Language Models","created":"2023-04-07","cited_by_count":17},{"id":"2505.23522","title":"OmniEarth-Bench: Towards Holistic Evaluation of Earth's Six Spheres and Cross-Spheres Interactions with Multimodal Observational Earth Data","created":"2025-05-29","cited_by_count":14},{"id":"2505.20538","title":"AstroVisBench: A Code Benchmark for Scientific Computing and Visualization in Astronomy","created":"2025-05-26","cited_by_count":13},{"id":"2506.00022","title":"Scaling Physical Reasoning with the PHYSICS Dataset","created":"2025-05-21","cited_by_count":13},{"id":"2509.21193","title":"Eigen-1: Adaptive Multi-Agent Refinement with Monitor-Based RAG for Scientific Reasoning","created":"2025-09-25","cited_by_count":11},{"id":"2509.21320","title":"SciReasoner: Laying the Scientific Reasoning Ground Across Disciplines","created":"2025-09-25","cited_by_count":11},{"id":"2510.08521","title":"FlowSearch: Advancing deep research with dynamic structured knowledge flow","created":"2025-10-09","cited_by_count":10},{"id":"2507.17311","title":"A Self-Evolving AI Agent System for Climate Science","created":"2025-07-23","cited_by_count":9},{"id":"2508.18124","title":"CMPhysBench: A Benchmark for Evaluating Large Language Models in Condensed Matter Physics","created":"2025-08-25","cited_by_count":9},{"id":"2508.12291","title":"RadarQA: Multi-modal Quality Analysis of Weather Radar Forecasts","created":"2025-08-17","cited_by_count":8},{"id":"2309.06578","title":"Can Large Language Models Discern Evidence for Scientific Hypotheses? Case Studies in the Social Sciences","created":"2023-09-07","cited_by_count":6},{"id":"2511.14366","title":"ATLAS: A High-Difficulty, Multidisciplinary Benchmark for Frontier Scientific Reasoning","created":"2025-11-18","cited_by_count":6},{"id":"2511.21444","title":"EWE: An Agentic Framework for Extreme Weather Analysis","created":"2025-11-26","cited_by_count":4},{"id":"2505.20310","title":"Manalyzer: End-to-end Automated Meta-analysis with Multi-agent System","created":"2025-05-22","cited_by_count":3},{"id":"2401.06233","title":"LEGOBench: Scientific Leaderboard Generation Benchmark","created":"2024-01-11","cited_by_count":2}],"next_cursor":null}