{"list":"other","total":56,"rows":[{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"2103.03874","title":"Measuring Mathematical Problem Solving With the MATH Dataset","created":"2021-03-05","cited_by_count":5371},{"id":"1803.05457","title":"Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge","created":"2018-03-14","cited_by_count":4886},{"id":"2403.05530","title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","created":"2024-03-08","cited_by_count":3224},{"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":"2401.04088","title":"Mixtral of Experts","created":"2024-01-08","cited_by_count":1823},{"id":"2308.00352","title":"MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework","created":"2023-08-01","cited_by_count":1808},{"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":"2403.08295","title":"Gemma: Open Models Based on Gemini Research and Technology","created":"2024-03-13","cited_by_count":916},{"id":"1910.14599","title":"Adversarial NLI: A New Benchmark for Natural Language Understanding","created":"2019-10-31","cited_by_count":807},{"id":"2305.02301","title":"Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes","created":"2023-05-03","cited_by_count":737},{"id":"2309.12284","title":"MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models","created":"2023-09-21","cited_by_count":735},{"id":"2308.10848","title":"AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors","created":"2023-08-21","cited_by_count":598},{"id":"2212.10403","title":"Towards Reasoning in Large Language Models: A Survey","created":"2022-12-20","cited_by_count":596},{"id":"2412.21187","title":"Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs","created":"2024-12-30","cited_by_count":570},{"id":"2501.06322","title":"Multi-Agent Collaboration Mechanisms: A Survey of LLMs","created":"2025-01-10","cited_by_count":431},{"id":"2306.03314","title":"Multi-Agent Collaboration: Harnessing the Power of Intelligent LLM Agents","created":"2023-06-05","cited_by_count":333},{"id":"2402.00157","title":"Large Language Models for Mathematical Reasoning: Progresses and Challenges","created":"2024-01-31","cited_by_count":284},{"id":"2402.13116","title":"A Survey on Knowledge Distillation of Large Language Models","created":"2024-02-20","cited_by_count":284},{"id":"2110.07178","title":"Symbolic Knowledge Distillation: from General Language Models to Commonsense Models","created":"2021-10-14","cited_by_count":270},{"id":"2305.08291","title":"Large Language Model Guided Tree-of-Thought","created":"2023-05-15","cited_by_count":221},{"id":"2402.17193","title":"When Scaling Meets LLM Finetuning: The Effect of Data, Model and Finetuning Method","created":"2024-02-27","cited_by_count":204},{"id":"2311.17311","title":"Universal Self-Consistency for Large Language Model Generation","created":"2023-11-29","cited_by_count":203},{"id":"2407.11511","title":"Multi-Step Reasoning with Large Language Models, a Survey","created":"2024-07-16","cited_by_count":143},{"id":"2306.08543","title":"MiniLLM: On-Policy Distillation of Large Language Models","created":"2023-06-14","cited_by_count":139},{"id":"2401.06805","title":"Exploring the Reasoning Abilities of Multimodal Large Language Models (MLLMs): A Comprehensive Survey on Emerging Trends in Multimodal Reasoning","created":"2024-01-10","cited_by_count":136},{"id":"2310.10701","title":"Theory of Mind for Multi-Agent Collaboration via Large Language Models","created":"2023-10-16","cited_by_count":135},{"id":"1908.08962","title":"Well-Read Students Learn Better: On the Importance of Pre-training Compact Models","created":"2019-08-23","cited_by_count":120},{"id":"2402.03578","title":"LLM Multi-Agent Systems: Challenges and Open Problems","created":"2024-02-05","cited_by_count":120},{"id":"2412.09078","title":"Forest-of-Thought: Scaling Test-Time Compute for Enhancing LLM Reasoning","created":"2024-12-12","cited_by_count":110},{"id":"2503.08026","title":"In Prospect and Retrospect: Reflective Memory Management for Long-term Personalized Dialogue Agents","created":"2025-03-11","cited_by_count":106},{"id":"2312.11562","title":"A Survey of Reasoning with Foundation Models","created":"2023-12-17","cited_by_count":70},{"id":"2403.20046","title":"Can LLMs Learn from Previous Mistakes? Investigating LLMs' Errors to Boost for Reasoning","created":"2024-03-29","cited_by_count":69},{"id":"2405.11106","title":"LLM-based Multi-Agent Reinforcement Learning: Current and Future Directions","created":"2024-05-17","cited_by_count":67},{"id":"2402.17644","title":"Are LLMs Capable of Data-based Statistical and Causal Reasoning? Benchmarking Advanced Quantitative Reasoning with Data","created":"2024-02-27","cited_by_count":63},{"id":"2407.14507","title":"Internal Consistency and Self-Feedback in Large Language Models: A Survey","created":"2024-07-19","cited_by_count":50},{"id":"2410.08115","title":"Optima: Optimizing Effectiveness and Efficiency for LLM-Based Multi-Agent System","created":"2024-10-10","cited_by_count":43},{"id":"2305.14279","title":"Two Failures of Self-Consistency in the Multi-Step Reasoning of LLMs","created":"2023-05-23","cited_by_count":36},{"id":"2312.11508","title":"Rethinking the Instruction Quality: LIFT is What You Need","created":"2023-12-12","cited_by_count":34},{"id":"2411.19865","title":"Reverse Thinking Makes LLMs Stronger Reasoners","created":"2024-11-29","cited_by_count":29},{"id":"2412.06864","title":"Political-LLM: Large Language Models in Political Science","created":"2024-12-09","cited_by_count":27},{"id":"2402.03268","title":"Understanding Reasoning Ability of Language Models From the Perspective of Reasoning Paths Aggregation","created":"2024-02-05","cited_by_count":22},{"id":"2501.06932","title":"Harnessing Large Language Models for Disaster Management: A Survey","created":"2025-01-12","cited_by_count":20},{"id":"2402.01729","title":"Contextualization Distillation from Large Language Model for Knowledge Graph Completion","created":"2024-01-28","cited_by_count":18},{"id":"2310.16271","title":"CycleAlign: Iterative Distillation from Black-box LLM to White-box Models for Better Human Alignment","created":"2023-10-25","cited_by_count":13},{"id":"2505.16225","title":"MAPLE: Many-Shot Adaptive Pseudo-Labeling for In-Context Learning","created":"2025-05-22","cited_by_count":13},{"id":"2406.05322","title":"Teaching-Assistant-in-the-Loop: Improving Knowledge Distillation from Imperfect Teacher Models in Low-Budget Scenarios","created":"2024-06-08","cited_by_count":12},{"id":"2402.08219","title":"BBox-Adapter: Lightweight Adapting for Black-Box Large Language Models","created":"2024-02-13","cited_by_count":11},{"id":"2504.02181","title":"A Survey of Scaling in Large Language Model Reasoning","created":"2025-04-02","cited_by_count":10},{"id":"2312.05979","title":"NovaCOMET: Open Commonsense Foundation Models with Symbolic Knowledge Distillation","created":"2023-12-10","cited_by_count":8},{"id":"2405.13014","title":"QCRD: Quality-guided Contrastive Rationale Distillation for Large Language Models","created":"2024-05-14","cited_by_count":8},{"id":"2412.20995","title":"KARPA: A Training-free Method of Adapting Knowledge Graph as References for Large Language Model's Reasoning Path Aggregation","created":"2024-12-30","cited_by_count":7},{"id":"2405.12939","title":"Aggregation of Reasoning: A Hierarchical Framework for Enhancing Answer Selection in Large Language Models","created":"2024-05-21","cited_by_count":5},{"id":"2503.04873","title":"Are Large Language Models Good In-context Learners for Financial Sentiment Analysis?","created":"2025-03-06","cited_by_count":5},{"id":"2506.12012","title":"Tracing LLM Reasoning Processes with Strategic Games: A Framework for Planning, Revision, and Resource-Constrained Decision Making","created":"2025-06-13","cited_by_count":5}],"next_cursor":null}