{"list":"other","total":85,"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":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","created":"2024-02-05","cited_by_count":9379},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"2309.06180","title":"Efficient Memory Management for Large Language Model Serving with PagedAttention","created":"2023-09-12","cited_by_count":5944},{"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":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"2305.20050","title":"Let's Verify Step by Step","created":"2023-05-31","cited_by_count":3789},{"id":"2303.17651","title":"Self-Refine: Iterative Refinement with Self-Feedback","created":"2023-03-30","cited_by_count":3442},{"id":"2305.10601","title":"Tree of Thoughts: Deliberate Problem Solving with Large Language Models","created":"2023-05-17","cited_by_count":3211},{"id":"1502.05477","title":"Trust Region Policy Optimization","created":"2015-02-19","cited_by_count":2580},{"id":"2409.19256","title":"HybridFlow: A Flexible and Efficient RLHF Framework","created":"2024-09-28","cited_by_count":2057},{"id":"2408.03314","title":"Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters","created":"2024-08-06","cited_by_count":1986},{"id":"2308.00352","title":"MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework","created":"2023-08-01","cited_by_count":1808},{"id":"2305.14325","title":"Improving Factuality and Reasoning in Language Models through Multiagent Debate","created":"2023-05-23","cited_by_count":1784},{"id":"2206.14858","title":"Solving Quantitative Reasoning Problems with Language Models","created":"2022-06-29","cited_by_count":1392},{"id":"2501.19393","title":"s1: Simple test-time scaling","created":"2025-01-31","cited_by_count":1341},{"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":"2202.03286","title":"Red Teaming Language Models with Language Models","created":"2022-02-07","cited_by_count":1026},{"id":"2311.03099","title":"Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch","created":"2023-11-06","cited_by_count":694},{"id":"2501.17161","title":"SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training","created":"2025-01-28","cited_by_count":672},{"id":"2308.10848","title":"AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors","created":"2023-08-21","cited_by_count":598},{"id":"2502.01456","title":"Process Reinforcement through Implicit Rewards","created":"2025-02-03","cited_by_count":504},{"id":"2403.13787","title":"RewardBench: Evaluating Reward Models for Language Modeling","created":"2024-03-20","cited_by_count":499},{"id":"2502.03387","title":"LIMO: Less is More for Reasoning","created":"2025-02-05","cited_by_count":498},{"id":"2212.04088","title":"LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language Models","created":"2022-12-08","cited_by_count":462},{"id":"2409.12917","title":"Training Language Models to Self-Correct via Reinforcement Learning","created":"2024-09-19","cited_by_count":426},{"id":"2310.06452","title":"Understanding the Effects of RLHF on LLM Generalisation and Diversity","created":"2023-10-10","cited_by_count":396},{"id":"2503.01307","title":"Cognitive Behaviors that Enable Self-Improving Reasoners, or, Four Habits of Highly Effective STaRs","created":"2025-03-03","cited_by_count":377},{"id":"2404.14618","title":"Hybrid LLM: Cost-Efficient and Quality-Aware Query Routing","created":"2024-04-22","cited_by_count":372},{"id":"2410.12784","title":"JudgeBench: A Benchmark for Evaluating LLM-based Judges","created":"2024-10-16","cited_by_count":318},{"id":"2311.10537","title":"MedAgents: Large Language Models as Collaborators for Zero-shot Medical Reasoning","created":"2023-11-16","cited_by_count":316},{"id":"2309.17179","title":"Alphazero-like Tree-Search can Guide Large Language Model Decoding and Training","created":"2023-09-29","cited_by_count":295},{"id":"2307.06135","title":"SayPlan: Grounding Large Language Models using 3D Scene Graphs for Scalable Robot Task Planning","created":"2023-07-12","cited_by_count":294},{"id":"2501.09686","title":"Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Models","created":"2025-01-16","cited_by_count":293},{"id":"2211.00053","title":"Generating Sequences by Learning to Self-Correct","created":"2022-10-31","cited_by_count":277},{"id":"2502.14768","title":"Logic-RL: Unleashing LLM Reasoning with Rule-Based Reinforcement Learning","created":"2025-02-20","cited_by_count":262},{"id":"2307.05300","title":"Unleashing the Emergent Cognitive Synergy in Large Language Models: A Task-Solving Agent through Multi-Persona Self-Collaboration","created":"2023-07-11","cited_by_count":251},{"id":"2403.12031","title":"RouterBench: A Benchmark for Multi-LLM Routing System","created":"2024-03-18","cited_by_count":238},{"id":"2305.16867","title":"Playing repeated games with Large Language Models","created":"2023-05-26","cited_by_count":217},{"id":"2305.12474","title":"Evaluating the Performance of Large Language Models on GAOKAO Benchmark","created":"2023-05-21","cited_by_count":186},{"id":"2410.12832","title":"Generative Reward Models","created":"2024-10-02","cited_by_count":148},{"id":"2411.14405","title":"Marco-o1: Towards Open Reasoning Models for Open-Ended Solutions","created":"2024-11-21","cited_by_count":144},{"id":"2410.18982","title":"O1 Replication Journey: A Strategic Progress Report -- Part 1","created":"2024-10-08","cited_by_count":143},{"id":"2408.06195","title":"Mutual Reasoning Makes Smaller LLMs Stronger Problem-Solvers","created":"2024-08-12","cited_by_count":138},{"id":"2306.06531","title":"AutoTAMP: Autoregressive Task and Motion Planning with LLMs as Translators and Checkers","created":"2023-06-10","cited_by_count":113},{"id":"2501.04682","title":"Towards System 2 Reasoning in LLMs: Learning How to Think With Meta Chain-of-Thought","created":"2025-01-08","cited_by_count":109},{"id":"2305.17066","title":"Mindstorms in Natural Language-Based Societies of Mind","created":"2023-05-26","cited_by_count":107},{"id":"2410.09671","title":"OpenR: An Open Source Framework for Advanced Reasoning with Large Language Models","created":"2024-10-12","cited_by_count":94},{"id":"2410.02884","title":"LLaMA-Berry: Pairwise Optimization for O1-like Olympiad-Level Mathematical Reasoning","created":"2024-10-03","cited_by_count":91},{"id":"2409.19886","title":"RouterDC: Query-Based Router by Dual Contrastive Learning for Assembling Large Language Models","created":"2024-09-30","cited_by_count":88},{"id":"2502.11133","title":"MasRouter: Learning to Route LLMs for Multi-Agent Systems","created":"2025-02-16","cited_by_count":88},{"id":"2407.13692","title":"Prover-Verifier Games improve legibility of LLM outputs","created":"2024-07-18","cited_by_count":85},{"id":"2405.12205","title":"Metacognitive Capabilities of LLMs: An Exploration in Mathematical Problem Solving","created":"2024-05-20","cited_by_count":84},{"id":"2502.00212","title":"STP: Self-play LLM Theorem Provers with Iterative Conjecturing and Proving","created":"2025-01-31","cited_by_count":79},{"id":"2501.18099","title":"Learning to Plan & Reason for Evaluation with Thinking-LLM-as-a-Judge","created":"2025-01-30","cited_by_count":78},{"id":"2411.15100","title":"XGrammar: Flexible and Efficient Structured Generation Engine for Large Language Models","created":"2024-11-22","cited_by_count":75},{"id":"2502.06772","title":"ReasonFlux: Hierarchical LLM Reasoning via Scaling Thought Templates","created":"2025-02-10","cited_by_count":63},{"id":"2408.12320","title":"TensorOpera Router: A Multi-Model Router for Efficient LLM Inference","created":"2024-08-22","cited_by_count":60},{"id":"2411.16579","title":"Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision","created":"2024-11-25","cited_by_count":60},{"id":"2308.05342","title":"Metacognitive Prompting Improves Understanding in Large Language Models","created":"2023-08-10","cited_by_count":58},{"id":"2410.05695","title":"Unlocking the Capabilities of Thought: A Reasoning Boundary Framework to Quantify and Optimize Chain-of-Thought","created":"2024-10-08","cited_by_count":56},{"id":"2410.03617","title":"What Matters for Model Merging at Scale?","created":"2024-10-04","cited_by_count":55},{"id":"2502.02508","title":"Satori: Reinforcement Learning with Chain-of-Action-Thought Enhances LLM Reasoning via Autoregressive Search","created":"2025-02-04","cited_by_count":53},{"id":"2407.09811","title":"CellAgent: An LLM-driven Multi-Agent Framework for Automated Single-cell Data Analysis","created":"2024-07-13","cited_by_count":39},{"id":"2411.16345","title":"Preference Optimization for Reasoning with Pseudo Feedback","created":"2024-11-25","cited_by_count":39},{"id":"2304.12998","title":"ChatLLM Network: More brains, More intelligence","created":"2023-04-24","cited_by_count":37},{"id":"2402.10614","title":"Can LLMs Speak For Diverse People? Tuning LLMs via Debate to Generate Controllable Controversial Statements","created":"2024-02-16","cited_by_count":34},{"id":"2108.12099","title":"Learning to Give Checkable Answers with Prover-Verifier Games","created":"2021-08-27","cited_by_count":32},{"id":"2406.11698","title":"Meta Reasoning for Large Language Models","created":"2024-06-17","cited_by_count":29},{"id":"2402.04578","title":"S-Agents: Self-organizing Agents in Open-ended Environments","created":"2024-02-07","cited_by_count":22},{"id":"2502.06773","title":"On the Emergence of Thinking in LLMs I: Searching for the Right Intuition","created":"2025-02-10","cited_by_count":22},{"id":"2410.03864","title":"DOTS: Learning to Reason Dynamically in LLMs via Optimal Reasoning Trajectories Search","created":"2024-10-04","cited_by_count":17},{"id":"2405.15821","title":"Reinforcing Language Agents via Policy Optimization with Action Decomposition","created":"2024-05-23","cited_by_count":16},{"id":"2503.01155","title":"Nature-Inspired Population-Based Evolution of Large Language Models","created":"2025-03-03","cited_by_count":15},{"id":"2310.18127","title":"Ask more, know better: Reinforce-Learned Prompt Questions for Decision Making with Large Language Models","created":"2023-10-27","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":"2501.07886","title":"Iterative Label Refinement Matters More than Preference Optimization under Weak Supervision","created":"2025-01-14","cited_by_count":5}],"next_cursor":null}