{"list":"other","total":81,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2103.03874","title":"Measuring Mathematical Problem Solving With the MATH Dataset","created":"2021-03-05","cited_by_count":5371},{"id":"2410.21276","title":"GPT-4o System Card","created":"2024-10-25","cited_by_count":4588},{"id":"2303.11366","title":"Reflexion: Language Agents with Verbal Reinforcement Learning","created":"2023-03-20","cited_by_count":4276},{"id":"2302.04761","title":"Toolformer: Language Models Can Teach Themselves to Use Tools","created":"2023-02-09","cited_by_count":4182},{"id":"2305.20050","title":"Let's Verify Step by Step","created":"2023-05-31","cited_by_count":3789},{"id":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673},{"id":"2108.07732","title":"Program Synthesis with Large Language Models","created":"2021-08-16","cited_by_count":3637},{"id":"2307.03172","title":"Lost in the Middle: How Language Models Use Long Contexts","created":"2023-07-06","cited_by_count":3455},{"id":"2303.17651","title":"Self-Refine: Iterative Refinement with Self-Feedback","created":"2023-03-30","cited_by_count":3442},{"id":"2310.06770","title":"SWE-bench: Can Language Models Resolve Real-World GitHub Issues?","created":"2023-10-10","cited_by_count":3373},{"id":"2311.12022","title":"GPQA: A Graduate-Level Google-Proof Q&A Benchmark","created":"2023-11-20","cited_by_count":2879},{"id":"2307.08691","title":"FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning","created":"2023-07-17","cited_by_count":2598},{"id":"2303.12712","title":"Sparks of Artificial General Intelligence: Early experiments with GPT-4","created":"2023-03-22","cited_by_count":2592},{"id":"2407.10671","title":"Qwen2 Technical Report","created":"2024-07-15","cited_by_count":2120},{"id":"2308.08155","title":"AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation","created":"2023-08-16","cited_by_count":1988},{"id":"2307.16789","title":"ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs","created":"2023-07-31","cited_by_count":1947},{"id":"2405.15793","title":"SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering","created":"2024-05-06","cited_by_count":1737},{"id":"2403.13372","title":"LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models","created":"2024-03-20","cited_by_count":1464},{"id":"2303.17760","title":"CAMEL: Communicative Agents for \"Mind\" Exploration of Large Language Model Society","created":"2023-03-31","cited_by_count":1395},{"id":"2501.19393","title":"s1: Simple test-time scaling","created":"2025-01-31","cited_by_count":1341},{"id":"2305.04388","title":"Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting","created":"2023-05-07","cited_by_count":1122},{"id":"2408.06292","title":"The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery","created":"2024-08-12","cited_by_count":1071},{"id":"2502.12110","title":"A-MEM: Agentic Memory for LLM Agents","created":"2025-02-17","cited_by_count":1063},{"id":"2407.21787","title":"Large Language Monkeys: Scaling Inference Compute with Repeated Sampling","created":"2024-07-31","cited_by_count":991},{"id":"2209.11895","title":"In-context Learning and Induction Heads","created":"2022-09-24","cited_by_count":964},{"id":"2312.08935","title":"Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations","created":"2023-12-14","cited_by_count":928},{"id":"2307.07924","title":"ChatDev: Communicative Agents for Software Development","created":"2023-07-16","cited_by_count":919},{"id":"2304.06364","title":"AGIEval: A Human-Centric Benchmark for Evaluating Foundation Models","created":"2023-04-13","cited_by_count":716},{"id":"2210.11610","title":"Large Language Models Can Self-Improve","created":"2022-10-20","cited_by_count":664},{"id":"2211.10435","title":"PAL: Program-aided Language Models","created":"2022-11-18","cited_by_count":652},{"id":"2308.10848","title":"AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors","created":"2023-08-21","cited_by_count":598},{"id":"2305.18654","title":"Faith and Fate: Limits of Transformers on Compositionality","created":"2023-05-29","cited_by_count":503},{"id":"2502.03387","title":"LIMO: Less is More for Reasoning","created":"2025-02-05","cited_by_count":498},{"id":"2501.04227","title":"Agent Laboratory: Using LLM Agents as Research Assistants","created":"2025-01-08","cited_by_count":425},{"id":"2403.09629","title":"Quiet-STaR: Language Models Can Teach Themselves to Think Before Speaking","created":"2024-03-14","cited_by_count":301},{"id":"2408.00724","title":"Inference Scaling Laws: An Empirical Analysis of Compute-Optimal Inference for Problem-Solving with Language Models","created":"2024-08-01","cited_by_count":290},{"id":"2310.02226","title":"Think before you speak: Training Language Models With Pause Tokens","created":"2023-10-03","cited_by_count":264},{"id":"2305.11554","title":"ToolkenGPT: Augmenting Frozen Language Models with Massive Tools via Tool Embeddings","created":"2023-05-19","cited_by_count":240},{"id":"2405.14333","title":"DeepSeek-Prover: Advancing Theorem Proving in LLMs through Large-Scale Synthetic Data","created":"2024-05-23","cited_by_count":234},{"id":"2305.00633","title":"Self-Evaluation Guided Beam Search for Reasoning","created":"2023-05-01","cited_by_count":196},{"id":"2303.05510","title":"Planning with Large Language Models for Code Generation","created":"2023-03-09","cited_by_count":182},{"id":"2502.04180","title":"Multi-agent Architecture Search via Agentic Supernet","created":"2025-02-06","cited_by_count":179},{"id":"2401.04925","title":"The Impact of Reasoning Step Length on Large Language Models","created":"2024-01-10","cited_by_count":153},{"id":"2410.02506","title":"Cut the Crap: An Economical Communication Pipeline for LLM-based Multi-Agent Systems","created":"2024-10-03","cited_by_count":141},{"id":"2502.06703","title":"Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling","created":"2025-02-10","cited_by_count":136},{"id":"2309.05660","title":"Hypothesis Search: Inductive Reasoning with Language Models","created":"2023-09-11","cited_by_count":120},{"id":"2408.11791","title":"Critique-out-Loud Reward Models","created":"2024-08-21","cited_by_count":106},{"id":"2410.02884","title":"LLaMA-Berry: Pairwise Optimization for O1-like Olympiad-Level Mathematical Reasoning","created":"2024-10-03","cited_by_count":91},{"id":"1905.10985","title":"AI-GAs: AI-generating algorithms, an alternate paradigm for producing general artificial intelligence","created":"2019-05-27","cited_by_count":86},{"id":"2412.00154","title":"o1-Coder: an o1 Replication for Coding","created":"2024-11-29","cited_by_count":78},{"id":"2501.11651","title":"T1: Advancing Language Model Reasoning through Reinforcement Learning and Inference Scaling","created":"2025-01-20","cited_by_count":77},{"id":"2406.12753","title":"OlympicArena: Benchmarking Multi-discipline Cognitive Reasoning for Superintelligent AI","created":"2024-06-18","cited_by_count":71},{"id":"2410.01707","title":"Interpretable Contrastive Monte Carlo Tree Search Reasoning","created":"2024-10-02","cited_by_count":64},{"id":"2303.06135","title":"Rewarding Chatbots for Real-World Engagement with Millions of Users","created":"2023-03-10","cited_by_count":59},{"id":"2501.09891","title":"Evolving Deeper LLM Thinking","created":"2025-01-17","cited_by_count":58},{"id":"2412.14135","title":"Scaling of Search and Learning: A Roadmap to Reproduce o1 from Reinforcement Learning Perspective","created":"2024-12-18","cited_by_count":50},{"id":"2402.02769","title":"Learning from Teaching Regularization: Generalizable Correlations Should be Easy to Imitate","created":"2024-02-05","cited_by_count":47},{"id":"2502.01563","title":"Massive Values in Self-Attention Modules are the Key to Contextual Knowledge Understanding","created":"2025-02-03","cited_by_count":47},{"id":"2405.14170","title":"Large Language Models-guided Dynamic Adaptation for Temporal Knowledge Graph Reasoning","created":"2024-05-23","cited_by_count":41},{"id":"2502.20576","title":"OmniRouter: Budget and Performance Controllable Multi-LLM Routing","created":"2025-02-27","cited_by_count":35},{"id":"2405.15124","title":"Scaling Law for Time Series Forecasting","created":"2024-05-24","cited_by_count":33},{"id":"2503.02398","title":"PersonaX: A Recommendation Agent Oriented User Modeling Framework for Long Behavior Sequence","created":"2025-03-04","cited_by_count":33},{"id":"2406.14449","title":"APEER: Automatic Prompt Engineering Enhances Large Language Model Reranking","created":"2024-06-20","cited_by_count":28},{"id":"2502.04506","title":"When One LLM Drools, Multi-LLM Collaboration Rules","created":"2025-02-06","cited_by_count":28},{"id":"2408.06634","title":"Harnessing Earnings Reports for Stock Predictions: A QLoRA-Enhanced LLM Approach","created":"2024-08-13","cited_by_count":24},{"id":"2503.03313","title":"LLM as GNN: Graph Vocabulary Learning for Text-Attributed Graph Foundation Models","created":"2025-03-05","cited_by_count":22},{"id":"2410.02892","title":"The Role of Deductive and Inductive Reasoning in Large Language Models","created":"2024-10-03","cited_by_count":20},{"id":"2503.02103","title":"Superficial Self-Improved Reasoners Benefit from Model Merging","created":"2025-03-03","cited_by_count":16},{"id":"2503.04543","title":"Keeping Yourself is Important in Downstream Tuning Multimodal Large Language Model","created":"2025-03-06","cited_by_count":16},{"id":"2407.10670","title":"Enhancing Retrieval and Managing Retrieval: A Four-Module Synergy for Improved Quality and Efficiency in RAG Systems","created":"2024-07-15","cited_by_count":15},{"id":"2309.04695","title":"Code-Style In-Context Learning for Knowledge-Based Question Answering","created":"2023-09-09","cited_by_count":13},{"id":"2503.16843","title":"LoRASculpt: Sculpting LoRA for Harmonizing General and Specialized Knowledge in Multimodal Large Language Models","created":"2025-03-21","cited_by_count":11},{"id":"2303.15234","title":"Prompt Tuning based Adapter for Vision-Language Model Adaption","created":"2023-03-24","cited_by_count":10},{"id":"2411.02454","title":"Graph-based Confidence Calibration for Large Language Models","created":"2024-11-03","cited_by_count":10},{"id":"2406.17378","title":"A Text is Worth Several Tokens: Text Embedding from LLMs Secretly Aligns Well with The Key Tokens","created":"2024-06-25","cited_by_count":8},{"id":"2404.16407","title":"U2++ MoE: Scaling 4.7x parameters with minimal impact on RTF","created":"2024-04-25","cited_by_count":5},{"id":"2502.00709","title":"RankFlow: A Multi-Role Collaborative Reranking Workflow Utilizing Large Language Models","created":"2025-02-02","cited_by_count":4}],"next_cursor":null}