{"total":377,"rows":[{"id":"2505.14683","title":"Emerging Properties in Unified Multimodal Pretraining","created":"2025-05-20","cited_by_count":897,"area":null},{"id":"2506.01939","title":"Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning","created":"2025-06-02","cited_by_count":559,"area":"lr"},{"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,"area":"lr"},{"id":"2503.09567","title":"Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models","created":"2025-03-12","cited_by_count":384,"area":"lr"},{"id":"2504.20571","title":"Reinforcement Learning for Reasoning in Large Language Models with One Training Example","created":"2025-04-29","cited_by_count":295,"area":"lr"},{"id":"2506.14758","title":"Reasoning with Exploration: An Entropy Perspective","created":"2025-06-17","cited_by_count":281,"area":"lr"},{"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,"area":"lr"},{"id":"2506.10947","title":"Spurious Rewards: Rethinking Training Signals in RLVR","created":"2025-06-12","cited_by_count":209,"area":"lr"},{"id":"2509.02547","title":"The Landscape of Agentic Reinforcement Learning for LLMs: A Survey","created":"2025-09-02","cited_by_count":205,"area":"agents"},{"id":"2505.24864","title":"ProRL: Prolonged Reinforcement Learning Expands Reasoning Boundaries in Large Language Models","created":"2025-05-30","cited_by_count":194,"area":"lr"},{"id":"2504.01296","title":"ThinkPrune: Pruning Long Chain-of-Thought of LLMs via Reinforcement Learning","created":"2025-04-02","cited_by_count":192,"area":"lr"},{"id":"2509.08827","title":"A Survey of Reinforcement Learning for Large Reasoning Models","created":"2025-09-10","cited_by_count":180,"area":"lr"},{"id":"2507.19849","title":"Agentic Reinforced Policy Optimization","created":"2025-07-26","cited_by_count":172,"area":"lr"},{"id":"2505.15134","title":"The Unreasonable Effectiveness of Entropy Minimization in LLM Reasoning","created":"2025-05-21","cited_by_count":166,"area":"lr"},{"id":"2506.01347","title":"The Surprising Effectiveness of Negative Reinforcement in LLM Reasoning","created":"2025-06-02","cited_by_count":162,"area":"lr"},{"id":"2504.07912","title":"Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining","created":"2025-04-10","cited_by_count":129,"area":"lr"},{"id":"2507.16806","title":"Beyond Binary Rewards: Training LMs to Reason About Their Uncertainty","created":"2025-07-22","cited_by_count":117,"area":"lr"},{"id":"2504.01943","title":"OpenCodeReasoning: Advancing Data Distillation for Competitive Coding","created":"2025-04-02","cited_by_count":113,"area":"lr"},{"id":"2506.20512","title":"OctoThinker: Mid-training Incentivizes Reinforcement Learning Scaling","created":"2025-06-25","cited_by_count":113,"area":"lr"},{"id":"2505.14970","title":"Self-Evolving Curriculum for LLM Reasoning","created":"2025-05-20","cited_by_count":112,"area":"lr"},{"id":"2504.07128","title":"DeepSeek-R1 Thoughtology: Let's think about LLM Reasoning","created":"2025-04-02","cited_by_count":92,"area":"lr"},{"id":"2506.06632","title":"Curriculum Reinforcement Learning from Easy to Hard Tasks Improves LLM Reasoning","created":"2025-06-07","cited_by_count":92,"area":"lr"},{"id":"2505.16552","title":"Think Silently, Think Fast: Dynamic Latent Compression of LLM Reasoning Chains","created":"2025-05-22","cited_by_count":85,"area":"lr"},{"id":"2505.23678","title":"Grounded Reinforcement Learning for Visual Reasoning","created":"2025-05-29","cited_by_count":83,"area":"lr"},{"id":"2503.09501","title":"ReMA: Learning to Meta-think for LLMs with Multi-Agent Reinforcement Learning","created":"2025-03-12","cited_by_count":79,"area":"lr"},{"id":"2504.00050","title":"JudgeLRM: Large Reasoning Models as a Judge","created":"2025-03-31","cited_by_count":78,"area":"lr"},{"id":"2512.07783","title":"On the Interplay of Pre-Training, Mid-Training, and RL on Reasoning Language Models","created":"2025-12-08","cited_by_count":69,"area":"lr"},{"id":"2505.00024","title":"Nemotron-Research-Tool-N1: Exploring Tool-Using Language Models with Reinforced Reasoning","created":"2025-04-25","cited_by_count":68,"area":"lr"},{"id":"2505.21444","title":"Can Large Reasoning Models Self-Train?","created":"2025-05-27","cited_by_count":68,"area":"lr"},{"id":"2604.12002","title":"Self-Distillation Zero: Self-Revision Turns Binary Rewards into Dense Supervision","created":"2026-04-13","cited_by_count":68,"area":"distill"},{"id":"2505.14489","title":"Reasoning Models Better Express Their Confidence","created":"2025-05-20","cited_by_count":65,"area":"lr"},{"id":"2507.01679","title":"Blending Supervised and Reinforcement Fine-Tuning with Prefix Sampling","created":"2025-07-02","cited_by_count":60,"area":"lr"},{"id":"2507.08794","title":"One Token to Fool LLM-as-a-Judge","created":"2025-07-11","cited_by_count":60,"area":"alignment"},{"id":"2505.16984","title":"UFT: Unifying Supervised and Reinforcement Fine-Tuning","created":"2025-05-22","cited_by_count":59,"area":"lr"},{"id":"2506.09026","title":"e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs","created":"2025-06-10","cited_by_count":59,"area":"lr"},{"id":"2506.01713","title":"SRPO: Enhancing Multimodal LLM Reasoning via Reflection-Aware Reinforcement Learning","created":"2025-06-02","cited_by_count":57,"area":"lr"},{"id":"2506.17238","title":"Training a Scientific Reasoning Model for Chemistry","created":"2025-06-04","cited_by_count":56,"area":"lr"},{"id":"2601.16443","title":"Endless Terminals: Scaling RL Environments for Terminal Agents","created":"2026-01-23","cited_by_count":54,"area":"synth"},{"id":"2506.08446","title":"A Survey on Large Language Models for Mathematical Reasoning","created":"2025-06-10","cited_by_count":52,"area":"lr"},{"id":"2504.15275","title":"Stop Summation: Min-Form Credit Assignment Is All Process Reward Model Needs for Reasoning","created":"2025-04-21","cited_by_count":50,"area":"lr"},{"id":"2505.19641","title":"SynLogic: Synthesizing Verifiable Reasoning Data at Scale for Learning Logical Reasoning and Beyond","created":"2025-05-26","cited_by_count":50,"area":"lr"},{"id":"2511.07317","title":"RLVE: Scaling Up Reinforcement Learning for Language Models with Adaptive Verifiable Environments","created":"2025-11-10","cited_by_count":50,"area":null},{"id":"2504.10160","title":"MT-R1-Zero: Advancing LLM-based Machine Translation via R1-Zero-like Reinforcement Learning","created":"2025-04-14","cited_by_count":48,"area":"lr"},{"id":"2503.19551","title":"Scaling Laws of Synthetic Data for Language Models","created":"2025-03-25","cited_by_count":46,"area":"synth"},{"id":"2505.05408","title":"Crosslingual Reasoning through Test-Time Scaling","created":"2025-05-08","cited_by_count":46,"area":"lr"},{"id":"2505.15117","title":"An Empirical Study on Reinforcement Learning for Reasoning-Search Interleaved LLM Agents","created":"2025-05-21","cited_by_count":46,"area":"lr"},{"id":"2506.08745","title":"Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning","created":"2025-06-10","cited_by_count":46,"area":"lr"},{"id":"2504.04022","title":"Rethinking Reflection in Pre-Training","created":"2025-04-05","cited_by_count":43,"area":"lr"},{"id":"2508.13755","title":"Depth-Breadth Synergy in RLVR: Unlocking LLM Reasoning Gains with Adaptive Exploration","created":"2025-08-19","cited_by_count":43,"area":"lr"},{"id":"2509.25123","title":"From $f(x)$ and $g(x)$ to $f(g(x))$: LLMs Learn New Skills in RL by Composing Old Ones","created":"2025-09-29","cited_by_count":42,"area":null},{"id":"2601.18779","title":"POPE: Learning to Reason on Hard Problems via Privileged On-Policy Exploration","created":"2026-01-26","cited_by_count":42,"area":"lr"},{"id":"2505.13775","title":"Beyond Semantics: The Unreasonable Effectiveness of Reasonless Intermediate Tokens","created":"2025-05-19","cited_by_count":41,"area":"lr"},{"id":"2506.02208","title":"KDRL: Post-Training Reasoning LLMs via Unified Knowledge Distillation and Reinforcement Learning","created":"2025-06-02","cited_by_count":41,"area":"lr"},{"id":"2604.01193","title":"Embarrassingly Simple Self-Distillation Improves Code Generation","created":"2026-04-01","cited_by_count":40,"area":"distill"},{"id":"2507.15778","title":"Stabilizing Knowledge, Promoting Reasoning: Dual-Token Constraints for RLVR","created":"2025-07-21","cited_by_count":39,"area":"lr"},{"id":"2503.12854","title":"Enhancing LLM Reasoning with Iterative DPO: A Comprehensive Empirical Investigation","created":"2025-03-17","cited_by_count":37,"area":"lr"},{"id":"2504.09762","title":"Position: Stop Anthropomorphizing Intermediate Tokens as Reasoning/Thinking Traces!","created":"2025-04-14","cited_by_count":37,"area":"lr"},{"id":"2505.14183","title":"ThinkSwitcher: When to Think Hard, When to Think Fast","created":"2025-05-20","cited_by_count":37,"area":"lr"},{"id":"2505.23590","title":"Jigsaw-R1: A Study of Rule-based Visual Reinforcement Learning with Jigsaw Puzzles","created":"2025-05-29","cited_by_count":36,"area":"lr"},{"id":"2509.19803","title":"VCRL: Variance-based Curriculum Reinforcement Learning for Large Language Models","created":"2025-09-24","cited_by_count":36,"area":"lr"},{"id":"2602.02710","title":"Maximum Likelihood Reinforcement Learning","created":"2026-02-02","cited_by_count":36,"area":"deeprl"},{"id":"2503.22828","title":"Learning to Reason for Long-Form Story Generation","created":"2025-03-28","cited_by_count":34,"area":"lr"},{"id":"2504.04383","title":"Retro-Search: Exploring Untaken Paths for Deeper and Efficient Reasoning","created":"2025-04-06","cited_by_count":34,"area":"lr"},{"id":"2506.05334","title":"Search Arena: Analyzing Search-Augmented LLMs","created":"2025-06-05","cited_by_count":34,"area":null},{"id":"2506.07976","title":"Thinking vs. Doing: Agents that Reason by Scaling Test-Time Interaction","created":"2025-06-09","cited_by_count":34,"area":"lr"},{"id":"2507.05255","title":"Open Vision Reasoner: Transferring Linguistic Cognitive Behavior for Visual Reasoning","created":"2025-07-07","cited_by_count":34,"area":"lr"},{"id":"2509.24372","title":"Evolution Strategies at Scale: LLM Fine-Tuning Beyond Reinforcement Learning","created":"2025-09-29","cited_by_count":34,"area":null},{"id":"2506.01926","title":"Large language models can learn and generalize steganographic chain-of-thought under process supervision","created":"2025-06-02","cited_by_count":32,"area":"lr"},{"id":"2507.11407","title":"EXAONE 4.0: Unified Large Language Models Integrating Non-reasoning and Reasoning Modes","created":"2025-07-15","cited_by_count":32,"area":"lr"},{"id":"2505.18830","title":"On the Effect of Negative Gradient in Group Relative Deep Reinforcement Optimization","created":"2025-05-24","cited_by_count":31,"area":"lr"},{"id":"2505.00551","title":"100 Days After DeepSeek-R1: A Survey on Replication Studies and More Directions for Reasoning Language Models","created":"2025-05-01","cited_by_count":30,"area":"lr"},{"id":"2506.05744","title":"Topology of Reasoning: Understanding Large Reasoning Models through Reasoning Graph Properties","created":"2025-06-06","cited_by_count":29,"area":"lr"},{"id":"2510.04573","title":"LaDiR: Latent Diffusion Enhances LLMs for Text Reasoning","created":"2025-10-06","cited_by_count":29,"area":"lr"},{"id":"2510.19363","title":"LoongRL: Reinforcement Learning for Advanced Reasoning over Long Contexts","created":"2025-10-22","cited_by_count":29,"area":"lr"},{"id":"2505.15692","title":"TemplateRL: Structured Template-Guided Reinforcement Learning for LLM Reasoning","created":"2025-05-21","cited_by_count":28,"area":"lr"},{"id":"2506.08123","title":"QA-LIGN: Aligning LLMs through Constitutionally Decomposed QA","created":"2025-06-09","cited_by_count":28,"area":"alignment"},{"id":"2504.06122","title":"Leanabell-Prover: Posttraining Scaling in Formal Reasoning","created":"2025-04-08","cited_by_count":27,"area":"lr"},{"id":"2510.07364","title":"Base Models Know How to Reason, Thinking Models Learn When","created":"2025-10-08","cited_by_count":27,"area":"lr"},{"id":"2511.16660","title":"Cognitive Foundations for Reasoning and Their Manifestation in LLMs","created":"2025-11-20","cited_by_count":26,"area":"lr"},{"id":"2509.19284","title":"What Characterizes Effective Reasoning? Revisiting Length, Review, and Structure of CoT","created":"2025-09-23","cited_by_count":25,"area":"lr"},{"id":"2510.01265","title":"RLP: Reinforcement as a Pretraining Objective","created":"2025-09-26","cited_by_count":25,"area":"lr"},{"id":"2510.03222","title":"Low-probability Tokens Sustain Exploration in Reinforcement Learning with Verifiable Reward","created":"2025-10-03","cited_by_count":25,"area":"lr"},{"id":"2510.13554","title":"Attention Illuminates LLM Reasoning: The Preplan-and-Anchor Rhythm Enables Fine-Grained Policy Optimization","created":"2025-10-15","cited_by_count":25,"area":"lr"},{"id":"2504.07052","title":"To Backtrack or Not to Backtrack: When Sequential Search Limits Model Reasoning","created":"2025-04-09","cited_by_count":24,"area":"lr"},{"id":"2505.20686","title":"Accelerating RL for LLM Reasoning with Optimal Advantage Regression","created":"2025-05-27","cited_by_count":24,"area":"lr"},{"id":"2505.13774","title":"Measuring the Faithfulness of Thinking Drafts in Large Reasoning Models","created":"2025-05-19","cited_by_count":23,"area":"lr"},{"id":"2505.24332","title":"DeepDiver: Adaptive Search Intensity Scaling via Open-Web Reinforcement Learning","created":"2025-05-30","cited_by_count":23,"area":"lr"},{"id":"2505.24480","title":"Towards Effective Code-Integrated Reasoning","created":"2025-05-30","cited_by_count":23,"area":null},{"id":"2506.08012","title":"GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior","created":"2025-06-09","cited_by_count":23,"area":"mllm"},{"id":"2509.06863","title":"floq: Training Critics via Flow-Matching for Scaling Compute in Value-Based RL","created":"2025-09-08","cited_by_count":22,"area":"diffusion"},{"id":"2504.10449","title":"M1: Towards Scalable Test-Time Compute with Mamba Reasoning Models","created":"2025-04-14","cited_by_count":21,"area":"lr"},{"id":"2504.11741","title":"Climbing the Ladder of Reasoning: What LLMs Can-and Still Can't-Solve after SFT?","created":"2025-04-16","cited_by_count":21,"area":"lr"},{"id":"2505.22148","title":"What Makes a Good Reasoning Chain? Uncovering Structural Patterns in Long Chain-of-Thought Reasoning","created":"2025-05-28","cited_by_count":21,"area":"lr"},{"id":"2509.26574","title":"Probing the Critical Point (CritPt) of AI Reasoning: a Frontier Physics Research Benchmark","created":"2025-09-30","cited_by_count":21,"area":"lr"},{"id":"2505.17407","title":"Language Matters: How Do Multilingual Input and Reasoning Paths Affect Large Reasoning Models?","created":"2025-05-23","cited_by_count":20,"area":"lr"},{"id":"2506.19807","title":"KnowRL: Exploring Knowledgeable Reinforcement Learning for Factuality","created":"2025-06-24","cited_by_count":20,"area":"lr"},{"id":"2509.03581","title":"Learning When to Plan: Efficiently Allocating Test-Time Compute for LLM Agents","created":"2025-09-03","cited_by_count":20,"area":"lr"},{"id":"2509.26314","title":"Latent Thinking Optimization: Your Latent Reasoning Language Model Secretly Encodes Reward Signals in Its Latent Thoughts","created":"2025-09-30","cited_by_count":19,"area":"lr"},{"id":"2510.01833","title":"Plan Then Action:High-Level Planning Guidance Reinforcement Learning for LLM Reasoning","created":"2025-10-02","cited_by_count":19,"area":"lr"},{"id":"2510.08276","title":"Beyond Turn Limits: Training Deep Search Agents with Dynamic Context Window","created":"2025-10-09","cited_by_count":19,"area":"lr"}],"next_cursor":"100"}