{"list":"other","total":100,"rows":[{"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":"2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","created":"2024-02-05","cited_by_count":9379},{"id":"2501.12948","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","created":"2025-01-22","cited_by_count":6330},{"id":"2103.03874","title":"Measuring Mathematical Problem Solving With the MATH Dataset","created":"2021-03-05","cited_by_count":5371},{"id":"2412.15115","title":"Qwen2.5 Technical Report","created":"2024-12-19","cited_by_count":4942},{"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":"2503.14476","title":"DAPO: An Open-Source LLM Reinforcement Learning System at Scale","created":"2025-03-18","cited_by_count":2810},{"id":"2303.18223","title":"A Survey of Large Language Models","created":"2023-03-31","cited_by_count":2576},{"id":"1506.02438","title":"High-Dimensional Continuous Control Using Generalized Advantage Estimation","created":"2015-06-08","cited_by_count":2026},{"id":"2210.09261","title":"Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them","created":"2022-10-17","cited_by_count":1807},{"id":"1606.06565","title":"Concrete Problems in AI Safety","created":"2016-06-21","cited_by_count":1642},{"id":"2306.02858","title":"Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding","created":"2023-06-05","cited_by_count":1471},{"id":"2503.20783","title":"Understanding R1-Zero-Like Training: A Critical Perspective","created":"2025-03-26","cited_by_count":1345},{"id":"2501.19393","title":"s1: Simple test-time scaling","created":"2025-01-31","cited_by_count":1341},{"id":"2412.16720","title":"OpenAI o1 System Card","created":"2024-12-21","cited_by_count":1244},{"id":"2501.12599","title":"Kimi k1.5: Scaling Reinforcement Learning with LLMs","created":"2025-01-22","cited_by_count":1210},{"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":"2312.11805","title":"Gemini: A Family of Highly Capable Multimodal Models","created":"2023-12-19","cited_by_count":872},{"id":"2306.15595","title":"Extending Context Window of Large Language Models via Positional Interpolation","created":"2023-06-27","cited_by_count":740},{"id":"2304.06767","title":"RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignment","created":"2023-04-13","cited_by_count":686},{"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":"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":"2407.10759","title":"Qwen2-Audio Technical Report","created":"2024-07-15","cited_by_count":560},{"id":"2503.18892","title":"SimpleRL-Zoo: Investigating and Taming Zero Reinforcement Learning for Open Base Models in the Wild","created":"2025-03-24","cited_by_count":511},{"id":"2502.01456","title":"Process Reinforcement through Implicit Rewards","created":"2025-02-03","cited_by_count":504},{"id":"2502.03387","title":"LIMO: Less is More for Reasoning","created":"2025-02-05","cited_by_count":498},{"id":"2503.16419","title":"Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models","created":"2025-03-20","cited_by_count":464},{"id":"2503.04697","title":"L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning","created":"2025-03-06","cited_by_count":384},{"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":"2201.03544","title":"The Effects of Reward Misspecification: Mapping and Mitigating Misaligned Models","created":"2022-01-10","cited_by_count":328},{"id":"2502.03373","title":"Demystifying Long Chain-of-Thought Reasoning in LLMs","created":"2025-02-05","cited_by_count":326},{"id":"2501.04519","title":"rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking","created":"2025-01-08","cited_by_count":313},{"id":"2412.16339","title":"Deliberative Alignment: Reasoning Enables Safer Language Models","created":"2024-12-20","cited_by_count":308},{"id":"2504.05118","title":"VAPO: Efficient and Reliable Reinforcement Learning for Advanced Reasoning Tasks","created":"2025-04-07","cited_by_count":285},{"id":"2410.07985","title":"Omni-MATH: A Universal Olympiad Level Mathematic Benchmark For Large Language Models","created":"2024-10-10","cited_by_count":284},{"id":"2504.11456","title":"DeepMath-103K: A Large-Scale, Challenging, Decontaminated, and Verifiable Mathematical Dataset for Advancing Reasoning","created":"2025-04-15","cited_by_count":280},{"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":"2502.14768","title":"Logic-RL: Unleashing LLM Reasoning with Rule-Based Reinforcement Learning","created":"2025-02-20","cited_by_count":262},{"id":"2307.10169","title":"Challenges and Applications of Large Language Models","created":"2023-07-19","cited_by_count":254},{"id":"2502.04463","title":"Training Language Models to Reason Efficiently","created":"2025-02-06","cited_by_count":247},{"id":"2501.03262","title":"REINFORCE++: Stabilizing Critic-Free Policy Optimization with Global Advantage Normalization","created":"2025-01-04","cited_by_count":241},{"id":"2407.04295","title":"Jailbreak Attacks and Defenses Against Large Language Models: A Survey","created":"2024-07-05","cited_by_count":230},{"id":"2401.04398","title":"Chain-of-Table: Evolving Tables in the Reasoning Chain for Table Understanding","created":"2024-01-09","cited_by_count":188},{"id":"2503.12605","title":"Multimodal Chain-of-Thought Reasoning: A Comprehensive Survey","created":"2025-03-16","cited_by_count":182},{"id":"2406.10162","title":"Sycophancy to Subterfuge: Investigating Reward-Tampering in Large Language Models","created":"2024-06-14","cited_by_count":178},{"id":"2309.09400","title":"CulturaX: A Cleaned, Enormous, and Multilingual Dataset for Large Language Models in 167 Languages","created":"2023-09-17","cited_by_count":174},{"id":"2312.14852","title":"TACO: Topics in Algorithmic COde generation dataset","created":"2023-12-22","cited_by_count":160},{"id":"2503.23829","title":"Crossing the Reward Bridge: Expanding RL with Verifiable Rewards Across Diverse Domains","created":"2025-03-31","cited_by_count":156},{"id":"2502.08235","title":"The Danger of Overthinking: Examining the Reasoning-Action Dilemma in Agentic Tasks","created":"2025-02-12","cited_by_count":152},{"id":"2504.02546","title":"GPG: A Simple and Strong Reinforcement Learning Baseline for Model Reasoning","created":"2025-04-03","cited_by_count":150},{"id":"2502.11886","title":"LIMR: Less is More for RL Scaling","created":"2025-02-17","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":"2502.12025","title":"SafeChain: Safety of Language Models with Long Chain-of-Thought Reasoning Capabilities","created":"2025-02-17","cited_by_count":136},{"id":"2503.00555","title":"Safety Tax: Safety Alignment Makes Your Large Reasoning Models Less Reasonable","created":"2025-03-01","cited_by_count":122},{"id":"2503.02951","title":"KodCode: A Diverse, Challenging, and Verifiable Synthetic Dataset for Coding","created":"2025-03-04","cited_by_count":119},{"id":"2502.12143","title":"Small Models Struggle to Learn from Strong Reasoners","created":"2025-02-17","cited_by_count":113},{"id":"2502.17387","title":"Big-Math: A Large-Scale, High-Quality Math Dataset for Reinforcement Learning in Language Models","created":"2025-02-24","cited_by_count":109},{"id":"2501.18492","title":"GuardReasoner: Towards Reasoning-based LLM Safeguards","created":"2025-01-30","cited_by_count":100},{"id":"2402.04049","title":"Systematic Biases in LLM Simulations of Debates","created":"2024-02-06","cited_by_count":99},{"id":"2501.03124","title":"PRMBench: A Fine-grained and Challenging Benchmark for Process-Level Reward Models","created":"2025-01-06","cited_by_count":99},{"id":"2502.12893","title":"H-CoT: Hijacking the Chain-of-Thought Safety Reasoning Mechanism to Jailbreak Large Reasoning Models, Including OpenAI o1/o3, DeepSeek-R1, and Gemini 2.0 Flash Thinking","created":"2025-02-18","cited_by_count":99},{"id":"2503.01491","title":"What's Behind PPO's Collapse in Long-CoT? Value Optimization Holds the Secret","created":"2025-03-03","cited_by_count":98},{"id":"2503.02318","title":"Audio-Reasoner: Improving Reasoning Capability in Large Audio Language Models","created":"2025-03-04","cited_by_count":95},{"id":"2404.14387","title":"A Survey on Self-Evolution of Large Language Models","created":"2024-04-22","cited_by_count":91},{"id":"2502.12659","title":"The Hidden Risks of Large Reasoning Models: A Safety Assessment of R1","created":"2025-02-18","cited_by_count":91},{"id":"2503.15477","title":"What Makes a Reward Model a Good Teacher? An Optimization Perspective","created":"2025-03-19","cited_by_count":73},{"id":"1705.08417","title":"Reinforcement Learning with a Corrupted Reward Channel","created":"2017-05-23","cited_by_count":70},{"id":"2504.14655","title":"LeetCodeDataset: A Temporal Dataset for Robust Evaluation and Efficient Training of Code LLMs","created":"2025-04-20","cited_by_count":70},{"id":"2501.01904","title":"Virgo: A Preliminary Exploration on Reproducing o1-like MLLM","created":"2025-01-03","cited_by_count":68},{"id":"2504.14286","title":"SRPO: A Cross-Domain Implementation of Large-Scale Reinforcement Learning on LLM","created":"2025-04-19","cited_by_count":68},{"id":"2503.11197","title":"Reinforcement Learning Outperforms Supervised Fine-Tuning: A Case Study on Audio Question Answering","created":"2025-03-14","cited_by_count":65},{"id":"2501.07246","title":"Audio-CoT: Exploring Chain-of-Thought Reasoning in Large Audio Language Model","created":"2025-01-13","cited_by_count":62},{"id":"2403.12171","title":"EasyJailbreak: A Unified Framework for Jailbreaking Large Language Models","created":"2024-03-18","cited_by_count":60},{"id":"2501.11284","title":"RedStar: Does Scaling Long-CoT Data Unlock Better Slow-Reasoning Systems?","created":"2025-01-20","cited_by_count":60},{"id":"2502.06781","title":"Exploring the Limit of Outcome Reward for Learning Mathematical Reasoning","created":"2025-02-10","cited_by_count":52},{"id":"2502.15806","title":"A Mousetrap: Fooling Large Reasoning Models for Jailbreak with Chain of Iterative Chaos","created":"2025-02-19","cited_by_count":43},{"id":"2502.12853","title":"S$^2$R: Teaching LLMs to Self-verify and Self-correct via Reinforcement Learning","created":"2025-02-18","cited_by_count":39},{"id":"2502.13383","title":"MM-Verify: Enhancing Multimodal Reasoning with Chain-of-Thought Verification","created":"2025-02-19","cited_by_count":39},{"id":"2503.12854","title":"Enhancing LLM Reasoning with Iterative DPO: A Comprehensive Empirical Investigation","created":"2025-03-17","cited_by_count":37},{"id":"2406.02301","title":"mCoT: Multilingual Instruction Tuning for Reasoning Consistency in Language Models","created":"2024-06-04","cited_by_count":33},{"id":"2412.17451","title":"Diving into Self-Evolving Training for Multimodal Reasoning","created":"2024-12-23","cited_by_count":32},{"id":"2502.13458","title":"ThinkGuard: Deliberative Slow Thinking Leads to Cautious Guardrails","created":"2025-02-19","cited_by_count":31},{"id":"2503.12759","title":"RAG-RL: Advancing Retrieval-Augmented Generation via RL and Curriculum Learning","created":"2025-03-17","cited_by_count":30},{"id":"2502.01633","title":"Adversarial Reasoning at Jailbreaking Time","created":"2025-02-03","cited_by_count":29},{"id":"2502.00883","title":"SimPER: A Minimalist Approach to Preference Alignment without Hyperparameters","created":"2025-02-02","cited_by_count":25},{"id":"2502.02339","title":"AStar: Boosting Multimodal Reasoning with Automated Structured Thinking","created":"2025-02-04","cited_by_count":25},{"id":"2501.18438","title":"o3-mini vs DeepSeek-R1: Which One is Safer?","created":"2025-01-30","cited_by_count":24},{"id":"2410.01428","title":"Can We Further Elicit Reasoning in LLMs? Critic-Guided Planning with Retrieval-Augmentation for Solving Challenging Tasks","created":"2024-10-02","cited_by_count":22},{"id":"2503.12524","title":"EXAONE Deep: Reasoning Enhanced Language Models","created":"2025-03-16","cited_by_count":21},{"id":"2409.19510","title":"Making LLMs Better Many-to-Many Speech-to-Text Translators with Curriculum Learning","created":"2024-09-29","cited_by_count":20},{"id":"2503.17979","title":"Trade-offs in Large Reasoning Models: An Empirical Analysis of Deliberative and Adaptive Reasoning over Foundational Capabilities","created":"2025-03-23","cited_by_count":20},{"id":"2405.16661","title":"RLSF: Fine-tuning LLMs via Symbolic Feedback","created":"2024-05-26","cited_by_count":14},{"id":"2011.08827","title":"Avoiding Tampering Incentives in Deep RL via Decoupled Approval","created":"2020-11-17","cited_by_count":12},{"id":"2410.08081","title":"Packing Analysis: Packing Is More Appropriate for Large Models or Datasets in Supervised Fine-tuning","created":"2024-10-10","cited_by_count":11},{"id":"2502.20238","title":"FINEREASON: Evaluating and Improving LLMs' Deliberate Reasoning through Reflective Puzzle Solving","created":"2025-02-27","cited_by_count":11},{"id":"2503.19612","title":"RL-finetuning LLMs from on- and off-policy data with a single algorithm","created":"2025-03-25","cited_by_count":11},{"id":"2102.01226","title":"Self-Teaching Machines to Read and Comprehend with Large-Scale Multi-Subject Question-Answering Data","created":"2021-02-01","cited_by_count":6},{"id":"2503.01923","title":"Output Length Effect on DeepSeek-R1's Safety in Forced Thinking","created":"2025-03-02","cited_by_count":6},{"id":"2501.04303","title":"Graph-Based Multimodal Contrastive Learning for Chart Question Answering","created":"2025-01-08","cited_by_count":3}],"next_cursor":null}