{"list":"other","total":56,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"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":"2103.03874","title":"Measuring Mathematical Problem Solving With the MATH Dataset","created":"2021-03-05","cited_by_count":5371},{"id":"2305.20050","title":"Let's Verify Step by Step","created":"2023-05-31","cited_by_count":3789},{"id":"2310.06770","title":"SWE-bench: Can Language Models Resolve Real-World GitHub Issues?","created":"2023-10-10","cited_by_count":3373},{"id":"2009.01325","title":"Learning to summarize from human feedback","created":"2020-09-02","cited_by_count":2588},{"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":"2501.19393","title":"s1: Simple test-time scaling","created":"2025-01-31","cited_by_count":1341},{"id":"2011.01060","title":"Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps","created":"2020-11-02","cited_by_count":1282},{"id":"2308.03688","title":"AgentBench: Evaluating LLMs as Agents","created":"2023-08-07","cited_by_count":1267},{"id":"2504.13837","title":"Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?","created":"2025-04-18","cited_by_count":982},{"id":"2405.14734","title":"SimPO: Simple Preference Optimization with a Reference-Free Reward","created":"2024-05-23","cited_by_count":963},{"id":"2306.13649","title":"On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes","created":"2023-06-23","cited_by_count":939},{"id":"2211.14275","title":"Solving math word problems with process- and outcome-based feedback","created":"2022-11-25","cited_by_count":901},{"id":"2101.02235","title":"Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategies","created":"2021-01-06","cited_by_count":743},{"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":"2308.09583","title":"WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct","created":"2023-08-18","cited_by_count":625},{"id":"2406.15877","title":"BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions","created":"2024-06-22","cited_by_count":546},{"id":"2401.08417","title":"Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translation","created":"2024-01-16","cited_by_count":394},{"id":"2206.10498","title":"PlanBench: An Extensible Benchmark for Evaluating Large Language Models on Planning and Reasoning about Change","created":"2022-06-21","cited_by_count":382},{"id":"2402.01306","title":"KTO: Model Alignment as Prospect Theoretic Optimization","created":"2024-02-02","cited_by_count":264},{"id":"2502.18449","title":"SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution","created":"2025-02-25","cited_by_count":263},{"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":"2502.09560","title":"EmbodiedBench: Comprehensive Benchmarking Multi-modal Large Language Models for Vision-Driven Embodied Agents","created":"2025-02-13","cited_by_count":221},{"id":"2305.15066","title":"GPT4Graph: Can Large Language Models Understand Graph Structured Data ? An Empirical Evaluation and Benchmarking","created":"2023-05-24","cited_by_count":210},{"id":"2110.00534","title":"TEACh: Task-driven Embodied Agents that Chat","created":"2021-10-01","cited_by_count":197},{"id":"2404.02078","title":"Advancing LLM Reasoning Generalists with Preference Trees","created":"2024-04-02","cited_by_count":192},{"id":"2402.08170","title":"LLaGA: Large Language and Graph Assistant","created":"2024-02-13","cited_by_count":181},{"id":"2404.03715","title":"Direct Nash Optimization: Teaching Language Models to Self-Improve with General Preferences","created":"2024-04-04","cited_by_count":178},{"id":"2210.07128","title":"Language Models of Code are Few-Shot Commonsense Learners","created":"2022-10-13","cited_by_count":160},{"id":"2504.16828","title":"Process Reward Models That Think","created":"2025-04-23","cited_by_count":118},{"id":"2201.05320","title":"CommonsenseQA 2.0: Exposing the Limits of AI through Gamification","created":"2022-01-14","cited_by_count":109},{"id":"2403.04706","title":"Common 7B Language Models Already Possess Strong Math Capabilities","created":"2024-03-07","cited_by_count":109},{"id":"2502.14382","title":"S*: Test Time Scaling for Code Generation","created":"2025-02-20","cited_by_count":98},{"id":"2406.09136","title":"Chain of Preference Optimization: Improving Chain-of-Thought Reasoning in LLMs","created":"2024-06-13","cited_by_count":96},{"id":"2406.11176","title":"Watch Every Step! LLM Agent Learning via Iterative Step-Level Process Refinement","created":"2024-06-17","cited_by_count":88},{"id":"2502.12118","title":"Scaling Test-Time Compute Without Verification or RL is Suboptimal","created":"2025-02-17","cited_by_count":84},{"id":"2503.00031","title":"Efficient Test-Time Scaling via Self-Calibration","created":"2025-02-25","cited_by_count":75},{"id":"2408.14512","title":"LLMs as Zero-shot Graph Learners: Alignment of GNN Representations with LLM Token Embeddings","created":"2024-08-25","cited_by_count":61},{"id":"2104.07644","title":"ExplaGraphs: An Explanation Graph Generation Task for Structured Commonsense Reasoning","created":"2021-04-15","cited_by_count":58},{"id":"2407.00379","title":"GraphArena: Evaluating and Exploring Large Language Models on Graph Computation","created":"2024-06-29","cited_by_count":49},{"id":"2305.12392","title":"PiVe: Prompting with Iterative Verification Improving Graph-based Generative Capability of LLMs","created":"2023-05-21","cited_by_count":44},{"id":"2405.19119","title":"Can Graph Learning Improve Planning in LLM-based Agents?","created":"2024-05-29","cited_by_count":43},{"id":"2302.04752","title":"Benchmarks for Automated Commonsense Reasoning: A Survey","created":"2023-02-09","cited_by_count":40},{"id":"2402.02805","title":"Graph-enhanced Large Language Models in Asynchronous Plan Reasoning","created":"2024-02-05","cited_by_count":37},{"id":"2405.04950","title":"VisionGraph: Leveraging Large Multimodal Models for Graph Theory Problems in Visual Context","created":"2024-05-08","cited_by_count":31},{"id":"2502.20380","title":"Multi-Turn Code Generation Through Single-Step Rewards","created":"2025-02-27","cited_by_count":28},{"id":"2409.12452","title":"Unlocking Reasoning Potential in Large Langauge Models by Scaling Code-form Planning","created":"2024-09-19","cited_by_count":25},{"id":"2505.12306","title":"Bidirectional LMs are Better Knowledge Memorizers? A Benchmark for Real-world Knowledge Injection","created":"2025-05-18","cited_by_count":7},{"id":"2408.05457","title":"Investigating Instruction Tuning Large Language Models on Graphs","created":"2024-08-10","cited_by_count":5},{"id":"2307.02472","title":"Deductive Additivity for Planning of Natural Language Proofs","created":"2023-07-05","cited_by_count":3}],"next_cursor":null}