{"total":237,"rows":[{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820,"area":"lr"},{"id":"2501.12948","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","created":"2025-01-22","cited_by_count":6330,"area":"lr"},{"id":"2508.18265","title":"InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency","created":"2025-08-25","cited_by_count":1510,"area":"lr"},{"id":"2501.12599","title":"Kimi k1.5: Scaling Reinforcement Learning with LLMs","created":"2025-01-22","cited_by_count":1210,"area":"lr"},{"id":"2406.12793","title":"ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools","created":"2024-06-18","cited_by_count":1121,"area":"lr"},{"id":"2411.15124","title":"Tulu 3: Pushing Frontiers in Open Language Model Post-Training","created":"2024-11-22","cited_by_count":1053,"area":"lr"},{"id":"2412.19437","title":"DeepSeek-V3 Technical Report","created":"2024-12-27","cited_by_count":811,"area":"lr"},{"id":"2401.02954","title":"DeepSeek LLM: Scaling Open-Source Language Models with Longtermism","created":"2024-01-05","cited_by_count":642,"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":"2508.06471","title":"GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models","created":"2025-08-08","cited_by_count":467,"area":"lr"},{"id":"2406.08464","title":"Magpie: Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing","created":"2024-06-12","cited_by_count":346,"area":"lr"},{"id":"2601.20802","title":"Reinforcement Learning via Self-Distillation","created":"2026-01-28","cited_by_count":332,"area":"lr"},{"id":"2411.10442","title":"Enhancing the Reasoning Ability of Multimodal Large Language Models via Mixed Preference Optimization","created":"2024-11-15","cited_by_count":239,"area":"lr"},{"id":"2507.01352","title":"Skywork-Reward-V2: Scaling Preference Data Curation via Human-AI Synergy","created":"2025-07-02","cited_by_count":214,"area":"lr"},{"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":"2404.02078","title":"Advancing LLM Reasoning Generalists with Preference Trees","created":"2024-04-02","cited_by_count":192,"area":"lr"},{"id":"2509.04259","title":"RL's Razor: Why Online Reinforcement Learning Forgets Less","created":"2025-09-04","cited_by_count":176,"area":"lr"},{"id":"2505.00949","title":"Llama-Nemotron: Efficient Reasoning Models","created":"2025-05-02","cited_by_count":158,"area":"lr"},{"id":"2504.21318","title":"Phi-4-reasoning Technical Report","created":"2025-04-30","cited_by_count":151,"area":"lr"},{"id":"2505.07608","title":"MiMo: Unlocking the Reasoning Potential of Language Model -- From Pretraining to Posttraining","created":"2025-05-12","cited_by_count":121,"area":"lr"},{"id":"2506.03569","title":"MiMo-VL Technical Report","created":"2025-06-04","cited_by_count":115,"area":"lr"},{"id":"2508.12790","title":"Reinforcement Learning with Rubric Anchors","created":"2025-08-18","cited_by_count":113,"area":"lr"},{"id":"2508.14444","title":"NVIDIA Nemotron Nano 2: An Accurate and Efficient Hybrid Mamba-Transformer Reasoning Model","created":"2025-08-20","cited_by_count":108,"area":"lr"},{"id":"2406.09279","title":"Unpacking DPO and PPO: Disentangling Best Practices for Learning from Preference Feedback","created":"2024-06-13","cited_by_count":107,"area":"lr"},{"id":"2507.00432","title":"Does Math Reasoning Improve General LLM Capabilities? Understanding Transferability of LLM Reasoning","created":"2025-07-01","cited_by_count":106,"area":"lr"},{"id":"2512.20848","title":"Nemotron 3 Nano: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning","created":"2025-12-23","cited_by_count":104,"area":"lr"},{"id":"2504.03624","title":"Nemotron-H: A Family of Accurate and Efficient Hybrid Mamba-Transformer Models","created":"2025-04-04","cited_by_count":100,"area":"lr"},{"id":"2502.06453","title":"MATH-Perturb: Benchmarking LLMs' Math Reasoning Abilities against Hard Perturbations","created":"2025-02-10","cited_by_count":89,"area":"lr"},{"id":"2506.14965","title":"Revisiting Reinforcement Learning for LLM Reasoning from A Cross-Domain Perspective","created":"2025-06-17","cited_by_count":76,"area":"lr"},{"id":"2503.24370","title":"Effectively Controlling Reasoning Models through Thinking Intervention","created":"2025-03-31","cited_by_count":65,"area":"lr"},{"id":"2603.08640","title":"PostTrainBench: Can LLM Agents Automate LLM Post-Training?","created":"2026-03-09","cited_by_count":64,"area":"lr"},{"id":"2508.16949","title":"Breaking the Exploration Bottleneck: Rubric-Scaffolded Reinforcement Learning for General LLM Reasoning","created":"2025-08-23","cited_by_count":63,"area":"lr"},{"id":"2408.16737","title":"Smaller, Weaker, Yet Better: Training LLM Reasoners via Compute-Optimal Sampling","created":"2024-08-29","cited_by_count":61,"area":"lr"},{"id":"2501.11284","title":"RedStar: Does Scaling Long-CoT Data Unlock Better Slow-Reasoning Systems?","created":"2025-01-20","cited_by_count":60,"area":"lr"},{"id":"2506.10910","title":"Magistral","created":"2025-06-12","cited_by_count":60,"area":"lr"},{"id":"2509.02208","title":"Baichuan-M2: Scaling Medical Capability with Large Verifier System","created":"2025-09-02","cited_by_count":59,"area":"lr"},{"id":"2510.18855","title":"Every Step Evolves: Scaling Reinforcement Learning for Trillion-Scale Thinking Model","created":"2025-10-21","cited_by_count":55,"area":"lr"},{"id":"2508.20722","title":"rStar2-Agent: Agentic Reasoning Technical Report","created":"2025-08-28","cited_by_count":54,"area":"lr"},{"id":"2505.11423","title":"When Thinking Fails: The Pitfalls of Reasoning for Instruction-Following in LLMs","created":"2025-05-16","cited_by_count":53,"area":"lr"},{"id":"2504.16656","title":"Skywork R1V2: Multimodal Hybrid Reinforcement Learning for Reasoning","created":"2025-04-23","cited_by_count":49,"area":"lr"},{"id":"2512.13607","title":"Nemotron-Cascade: Scaling Cascaded Reinforcement Learning for General-Purpose Reasoning Models","created":"2025-12-15","cited_by_count":48,"area":"lr"},{"id":"2504.15253","title":"Evaluating Judges as Evaluators: The JETTS Benchmark of LLM-as-Judges as Test-Time Scaling Evaluators","created":"2025-04-21","cited_by_count":44,"area":"lr"},{"id":"2410.06458","title":"LLM Self-Correction with DeCRIM: Decompose, Critique, and Refine for Enhanced Following of Instructions with Multiple Constraints","created":"2024-10-09","cited_by_count":35,"area":"lr"},{"id":"2507.21836","title":"AutoTIR: Autonomous Tools Integrated Reasoning via Reinforcement Learning","created":"2025-07-29","cited_by_count":33,"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":"2509.12235","title":"RL Fine-Tuning Heals OOD Forgetting in SFT","created":"2025-09-08","cited_by_count":31,"area":"lr"},{"id":"2505.10475","title":"Parallel Scaling Law for Language Models","created":"2025-05-15","cited_by_count":30,"area":"lr"},{"id":"2502.18878","title":"Learning to Generate Structured Output with Schema Reinforcement Learning","created":"2025-02-26","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":"2505.14810","title":"Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models","created":"2025-05-20","cited_by_count":28,"area":"lr"},{"id":"2412.08972","title":"RuleArena: A Benchmark for Rule-Guided Reasoning with LLMs in Real-World Scenarios","created":"2024-12-12","cited_by_count":27,"area":"lr"},{"id":"2507.03112","title":"RLVER: Reinforcement Learning with Verifiable Emotion Rewards for Empathetic Agents","created":"2025-07-03","cited_by_count":25,"area":"lr"},{"id":"2510.01180","title":"BroRL: Scaling Reinforcement Learning via Broadened Exploration","created":"2025-10-01","cited_by_count":25,"area":"lr"},{"id":"2412.11605","title":"SPaR: Self-Play with Tree-Search Refinement to Improve Instruction-Following in Large Language Models","created":"2024-12-16","cited_by_count":23,"area":"lr"},{"id":"2508.00410","title":"Co-rewarding: Stable Self-supervised RL for Eliciting Reasoning in Large Language Models","created":"2025-08-01","cited_by_count":23,"area":"lr"},{"id":"2410.09335","title":"Rethinking Data Selection at Scale: Random Selection is Almost All You Need","created":"2024-10-12","cited_by_count":22,"area":"lr"},{"id":"2412.00161","title":"STEP: Enhancing Video-LLMs' Compositional Reasoning by Spatio-Temporal Graph-guided Self-Training","created":"2024-11-29","cited_by_count":22,"area":"lr"},{"id":"2504.03790","title":"Sample, Don't Search: Rethinking Test-Time Alignment for Language Models","created":"2025-04-04","cited_by_count":22,"area":"lr"},{"id":"2505.18610","title":"PM-KVQ: Progressive Mixed-precision KV Cache Quantization for Long-CoT LLMs","created":"2025-05-24","cited_by_count":22,"area":"lr"},{"id":"2509.18883","title":"Introducing LongCat-Flash-Thinking: A Technical Report","created":"2025-09-23","cited_by_count":22,"area":"lr"},{"id":"2511.05993","title":"Revisiting Entropy in Reinforcement Learning for Large Reasoning Models","created":"2025-11-08","cited_by_count":21,"area":"lr"},{"id":"2410.04526","title":"FAMMA: A Benchmark for Financial Domain Multilingual Multimodal Question Answering","created":"2024-10-06","cited_by_count":20,"area":"lr"},{"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,"area":"lr"},{"id":"2505.13866","title":"Reasoning Path Compression: Compressing Generation Trajectories for Efficient LLM Reasoning","created":"2025-05-20","cited_by_count":17,"area":"lr"},{"id":"2506.01413","title":"Incentivizing Reasoning for Advanced Instruction-Following of Large Language Models","created":"2025-06-02","cited_by_count":17,"area":"lr"},{"id":"2510.23038","title":"Incentivizing Agentic Reasoning in LLM Judges via Tool-Integrated Reinforcement Learning","created":"2025-10-27","cited_by_count":17,"area":"lr"},{"id":"2508.17784","title":"Proximal Supervised Fine-Tuning","created":"2025-08-25","cited_by_count":16,"area":"lr"},{"id":"2603.13260","title":"Explain in Your Own Words: Improving Reasoning via Token-Selective Dual Knowledge Distillation","created":"2026-02-25","cited_by_count":16,"area":"lr"},{"id":"2507.10616","title":"Scalpel vs. Hammer: GRPO Amplifies Existing Capabilities, SFT Replaces Them","created":"2025-07-13","cited_by_count":15,"area":"lr"},{"id":"2505.17815","title":"Evaluation Faking: Unveiling Observer Effects in Safety Evaluation of Frontier AI Systems","created":"2025-05-23","cited_by_count":14,"area":"lr"},{"id":"2506.23508","title":"Why Reinforcement Fine-Tuning Enables MLLMs Preserve Prior Knowledge Better: A Data Perspective","created":"2025-06-30","cited_by_count":14,"area":"lr"},{"id":"2510.22977","title":"The Reasoning Trap: How Enhancing LLM Reasoning Amplifies Tool Hallucination","created":"2025-10-27","cited_by_count":14,"area":"lr"},{"id":"2604.06628","title":"Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability","created":"2026-04-08","cited_by_count":14,"area":"lr"},{"id":"2504.07081","title":"Self-Steering Language Models","created":"2025-04-09","cited_by_count":13,"area":"lr"},{"id":"2510.15211","title":"ReasonIF: Large Reasoning Models Fail to Follow Instructions During Reasoning","created":"2025-10-17","cited_by_count":13,"area":"lr"},{"id":"2511.03628","title":"LiveTradeBench: Seeking Real-World Alpha with Large Language Models","created":"2025-11-05","cited_by_count":13,"area":"lr"},{"id":"2603.23183","title":"Reasoning over Semantic IDs Enhances Generative Recommendation","created":"2026-03-24","cited_by_count":13,"area":"lr"},{"id":"2607.04037","title":"Reward-Gated On-Policy Distillation","created":"2026-07-04","cited_by_count":13,"area":"lr"},{"id":"2501.11877","title":"From Drafts to Answers: Unlocking LLM Potential via Aggregation Fine-Tuning","created":"2025-01-21","cited_by_count":12,"area":"lr"},{"id":"2505.14009","title":"Activation-Guided Consensus Merging for Large Language Models","created":"2025-05-20","cited_by_count":12,"area":"lr"},{"id":"2509.24393","title":"Towards Safe Reasoning in Large Reasoning Models via Corrective Intervention","created":"2025-09-29","cited_by_count":11,"area":"lr"},{"id":"2602.06717","title":"F-GRPO: Don't Let Your Policy Learn the Obvious and Forget the Rare","created":"2026-02-06","cited_by_count":11,"area":"lr"},{"id":"2602.12566","title":"To Mix or To Merge: Toward Multi-Domain Reinforcement Learning for Large Language Models","created":"2026-02-13","cited_by_count":11,"area":"lr"},{"id":"2501.14693","title":"Rethinking Table Instruction Tuning","created":"2025-01-24","cited_by_count":10,"area":"lr"},{"id":"2601.18091","title":"From LLMs to LRMs: Rethinking Pruning for Reasoning-Centric Models","created":"2026-01-26","cited_by_count":10,"area":"lr"},{"id":"2502.09056","title":"Adapting Language-Specific LLMs to a Reasoning Model in One Day via Model Merging -- An Open Recipe","created":"2025-02-13","cited_by_count":9,"area":"lr"},{"id":"2510.14629","title":"MR.Rec: Synergizing Memory and Reasoning for Personalized Recommendation Assistant with LLMs","created":"2025-10-16","cited_by_count":9,"area":"lr"},{"id":"2602.01395","title":"Rethinking Selective Knowledge Distillation","created":"2026-02-01","cited_by_count":9,"area":"lr"},{"id":"2602.02301","title":"Advancing General-Purpose Reasoning Models with Modular Gradient Surgery","created":"2026-02-02","cited_by_count":9,"area":"lr"},{"id":"2602.22538","title":"RAIN-Merging: A Gradient-Free Method to Enhance Instruction Following in Large Reasoning Models with Preserved Thinking Format","created":"2026-02-26","cited_by_count":9,"area":"lr"},{"id":"2502.18431","title":"TextGames: Learning to Self-Play Text-Based Puzzle Games via Language Model Reasoning","created":"2025-02-25","cited_by_count":8,"area":"lr"},{"id":"2508.18255","title":"Hermes 4 Technical Report","created":"2025-08-25","cited_by_count":8,"area":"lr"},{"id":"2601.15279","title":"MolecularIQ: Characterizing Chemical Reasoning Capabilities Through Symbolic Verification on Molecular Graphs","created":"2026-01-21","cited_by_count":8,"area":"lr"},{"id":"2605.19433","title":"Backtracking When It Strays: Mitigating Dual Exposure Biases in LLM Reasoning Distillation","created":"2026-05-19","cited_by_count":8,"area":"lr"},{"id":"2410.05915","title":"Give me a hint: Can LLMs take a hint to solve math problems?","created":"2024-10-08","cited_by_count":7,"area":"lr"},{"id":"2505.11574","title":"Quantization Meets Reasoning: Exploring and Mitigating Degradation of Low-Bit LLMs in Mathematical Reasoning","created":"2025-05-16","cited_by_count":7,"area":"lr"},{"id":"2505.23816","title":"A Course Correction in Steerability Evaluation: Revealing Miscalibration and Side Effects in LLMs","created":"2025-05-27","cited_by_count":7,"area":"lr"},{"id":"2506.18485","title":"A Simple \"Motivation\" Can Enhance Reinforcement Finetuning of Large Reasoning Models","created":"2025-06-23","cited_by_count":7,"area":"lr"},{"id":"2508.21365","title":"Think in Games: Learning to Reason in Games via Reinforcement Learning with Large Language Models","created":"2025-08-29","cited_by_count":7,"area":"lr"},{"id":"2509.01324","title":"KoBLEX: Open Legal Question Answering with Multi-hop Reasoning","created":"2025-09-01","cited_by_count":7,"area":"lr"}],"next_cursor":"100"}