{"total":73,"rows":[{"id":"2504.11468","title":"SFT or RL? An Early Investigation into Training R1-Like Reasoning Large Vision-Language Models","created":"2025-04-10","cited_by_count":212,"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":"2403.04642","title":"Teaching Large Language Models to Reason with Reinforcement Learning","created":"2024-03-07","cited_by_count":160,"area":"lr"},{"id":"2410.02089","title":"RLEF: Grounding Code LLMs in Execution Feedback with Reinforcement Learning","created":"2024-10-02","cited_by_count":151,"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":"2509.06941","title":"Outcome-based Exploration for LLM Reasoning","created":"2025-09-08","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":"2502.02384","title":"STAIR: Improving Safety Alignment with Introspective Reasoning","created":"2025-02-04","cited_by_count":77,"area":"lr"},{"id":"2501.18101","title":"Diverse Preference Optimization","created":"2025-01-30","cited_by_count":52,"area":"lr"},{"id":"2504.12522","title":"Evaluating the Diversity and Quality of LLM Generated Content","created":"2025-04-16","cited_by_count":51,"area":"lr"},{"id":"2411.04109","title":"Self-Consistency Preference Optimization","created":"2024-11-06","cited_by_count":50,"area":"lr"},{"id":"2601.12538","title":"A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agents","created":"2026-01-18","cited_by_count":50,"area":"lr"},{"id":"2505.23433","title":"Diversity-Aware Policy Optimization for Large Language Model Reasoning","created":"2025-05-29","cited_by_count":41,"area":"lr"},{"id":"2410.04509","title":"ErrorRadar: Benchmarking Complex Mathematical Reasoning of Multimodal Large Language Models Via Error Detection","created":"2024-10-06","cited_by_count":37,"area":"lr"},{"id":"2508.01491","title":"The Homogenizing Effect of Large Language Models on Human Expression and Thought","created":"2025-08-02","cited_by_count":35,"area":"lr"},{"id":"2505.23585","title":"On-Policy RL with Optimal Reward Baseline","created":"2025-05-29","cited_by_count":34,"area":"lr"},{"id":"2404.10346","title":"Self-Explore: Enhancing Mathematical Reasoning in Language Models with Fine-grained Rewards","created":"2024-04-16","cited_by_count":31,"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":"2410.19599","title":"Take Caution in Using LLMs as Human Surrogates: Scylla Ex Machina","created":"2024-10-25","cited_by_count":29,"area":"lr"},{"id":"2407.05013","title":"Progress or Regress? Self-Improvement Reversal in Post-training","created":"2024-07-06","cited_by_count":23,"area":"lr"},{"id":"2604.06268","title":"RAGEN-2: Reasoning Collapse in Agentic RL","created":"2026-04-07","cited_by_count":20,"area":"lr"},{"id":"2504.14363","title":"Improving RL Exploration for LLM Reasoning through Retrospective Replay","created":"2025-04-19","cited_by_count":19,"area":"lr"},{"id":"2601.19921","title":"Demystifying Multi-Agent Debate: The Role of Confidence and Diversity","created":"2026-01-09","cited_by_count":18,"area":"lr"},{"id":"2402.02563","title":"Synergy-of-Thoughts: Eliciting Efficient Reasoning in Hybrid Language Models","created":"2024-02-04","cited_by_count":13,"area":"lr"},{"id":"2504.14379","title":"The Geometry of Self-Verification in a Task-Specific Reasoning Model","created":"2025-04-19","cited_by_count":13,"area":"lr"},{"id":"2508.04117","title":"Unveiling Over-Memorization in Finetuning LLMs for Reasoning Tasks","created":"2025-08-06","cited_by_count":11,"area":"lr"},{"id":"2509.25534","title":"Self-Rewarding Rubric-Based Reinforcement Learning for Open-Ended Reasoning","created":"2025-09-19","cited_by_count":11,"area":"lr"},{"id":"2510.01539","title":"Executable Counterfactuals: Improving LLMs' Causal Reasoning Through Code","created":"2025-10-02","cited_by_count":10,"area":"lr"},{"id":"2510.06870","title":"$\\lambda$-GRPO: Unifying the GRPO Frameworks with Learnable Token Preferences","created":"2025-10-08","cited_by_count":10,"area":"lr"},{"id":"2510.26122","title":"Reasoning Path Divergence: A New Metric and Curation Strategy to Unlock LLM Diverse Thinking","created":"2025-10-30","cited_by_count":10,"area":"lr"},{"id":"2606.15455","title":"Understanding Diversity Collapse in RLVR via the Lens of Overtraining","created":"2026-06-13","cited_by_count":10,"area":"lr"},{"id":"2502.13173","title":"Thinking Preference Optimization","created":"2025-02-17","cited_by_count":8,"area":"lr"},{"id":"2510.04140","title":"Selective Expert Guidance for Effective and Diverse Exploration in Reinforcement Learning of LLMs","created":"2025-10-05","cited_by_count":7,"area":"lr"},{"id":"2511.05385","title":"TeaRAG: A Token-Efficient Agentic Retrieval-Augmented Generation Framework","created":"2025-11-07","cited_by_count":7,"area":"lr"},{"id":"2504.02708","title":"The Hidden Space of Safety: Understanding Preference-Tuned LLMs in Multilingual context","created":"2025-04-03","cited_by_count":6,"area":"lr"},{"id":"2509.12434","title":"Building Coding Agents via Entropy-Enhanced Multi-Turn Preference Optimization","created":"2025-09-15","cited_by_count":6,"area":"lr"},{"id":"2601.09609","title":"DPWriter: Reinforcement Learning with Diverse Planning Branching for Creative Writing","created":"2026-01-14","cited_by_count":6,"area":"lr"},{"id":"2603.24844","title":"Reaching Beyond the Mode: RL for Distributional Reasoning in Language Models","created":"2026-03-25","cited_by_count":6,"area":"lr"},{"id":"2606.28661","title":"When More Sampling Hurts: The Modal Ceiling and Correlation Ceiling of Test-Time Scaling","created":"2026-06-27","cited_by_count":6,"area":"lr"},{"id":"2602.01365","title":"When Domains Interact: Asymmetric and Order-Sensitive Cross-Domain Effects in Reinforcement Learning for Reasoning","created":"2026-02-01","cited_by_count":5,"area":"lr"},{"id":"2602.08498","title":"Characterizing, Evaluating, and Optimizing Complex Reasoning","created":"2026-02-09","cited_by_count":5,"area":"lr"},{"id":"2506.09099","title":"Too Big to Think: Capacity, Memorization, and Generalization in Pre-Trained Transformers","created":"2025-06-10","cited_by_count":4,"area":"lr"},{"id":"2601.06176","title":"TIR-Flow: Active Video Search and Reasoning with Frozen VLMs","created":"2026-01-07","cited_by_count":3,"area":"lr"},{"id":"2601.22629","title":"Time-Annealed Perturbation Sampling: Diverse Generation for Diffusion Language Models","created":"2026-01-30","cited_by_count":3,"area":"lr"},{"id":"2604.02450","title":"Do We Need Frontier Models to Verify Mathematical Proofs?","created":"2026-04-02","cited_by_count":3,"area":"lr"},{"id":"2512.01848","title":"Beyond SFT: Reinforcement Learning for Safer Large Reasoning Models with Better Reasoning Ability","created":"2025-12-01","cited_by_count":2,"area":"lr"},{"id":"2601.04670","title":"Learning Dynamics in RL Post-Training for Language Models","created":"2026-01-08","cited_by_count":2,"area":"lr"},{"id":"2602.11792","title":"Detecting RLVR Training Data via Structural Convergence of Reasoning","created":"2026-02-12","cited_by_count":2,"area":"lr"},{"id":"2605.08862","title":"BubbleSpec: Turning Long-Tail Bubbles into Speculative Rollout Drafts for Synchronous Reinforcement Learning","created":"2026-05-09","cited_by_count":2,"area":"lr"},{"id":"2605.28295","title":"Where Rollouts Begin: Low-Load, High-Leverage First-Token Diversification for RLVR","created":"2026-05-27","cited_by_count":2,"area":"lr"},{"id":"2609.04518","title":"Multi-Harness Reinforcement Learning for Coding Agents: Training Gains and Harness Dependence","created":"2026-09-03","cited_by_count":2,"area":"lr"},{"id":"2410.13216","title":"Anchored Alignment for Self-Explanations Enhancement","created":"2024-10-17","cited_by_count":1,"area":"lr"},{"id":"2502.13207","title":"Thinking Outside the (Gray) Box: A Context-Based Score for Assessing Value and Originality in Neural Text Generation","created":"2025-02-18","cited_by_count":1,"area":"lr"},{"id":"2503.17136","title":"CoKe: Customizable Fine-Grained Story Evaluation via Chain-of-Keyword Rationalization","created":"2025-03-21","cited_by_count":1,"area":"lr"},{"id":"2508.04072","title":"KG-Augmented Executable CoT for Mathematical Coding","created":"2025-08-06","cited_by_count":1,"area":"lr"},{"id":"2509.12936","title":"Rethinking the Evaluation of Alignment Methods: Insights into Diversity, Generalisation, and Safety","created":"2025-09-16","cited_by_count":1,"area":"lr"},{"id":"2510.17921","title":"CLAWS:Creativity detection for LLM-generated solutions using Attention Window of Sections","created":"2025-10-20","cited_by_count":1,"area":"lr"},{"id":"2602.21317","title":"Shared Nature, Unique Nurture: PRISM for Pluralistic Reasoning via In-context Structure Modeling","created":"2026-02-24","cited_by_count":1,"area":"lr"},{"id":"2606.16517","title":"How Post-Training Shapes Biological Reasoning Models","created":"2026-06-15","cited_by_count":1,"area":"lr"},{"id":"2607.03065","title":"Spectral Rewiring for Exploration, Purification, and Model Merging","created":"2026-07-03","cited_by_count":1,"area":"lr"},{"id":"2601.08777","title":"Asymptotic Universal Alignment: A New Alignment Framework via Test-Time Scaling","created":"2026-01-13","cited_by_count":0,"area":"lr"},{"id":"2602.00931","title":"Continuous-Utility Direct Preference Optimization","created":"2026-01-31","cited_by_count":0,"area":"lr"},{"id":"2603.18088","title":"Enhancing Reinforcement Learning Fine-Tuning with an Online Refiner","created":"2026-03-18","cited_by_count":0,"area":"lr"},{"id":"2604.03557","title":"When Do Hallucinations Arise? A Graph Perspective on the Evolution of Path Reuse and Path Compression","created":"2026-04-04","cited_by_count":0,"area":"lr"},{"id":"2604.10827","title":"Know Thy Reasoner: Not All Language Models Explore Alike","created":"2026-04-12","cited_by_count":0,"area":"lr"},{"id":"2605.09853","title":"Exploration-Driven Optimization for Test-Time Large Language Model Reasoning","created":"2026-05-11","cited_by_count":0,"area":"lr"},{"id":"2605.10716","title":"What should post-training optimize? A test-time scaling law perspective","created":"2026-05-11","cited_by_count":0,"area":"lr"},{"id":"2606.26130","title":"Thinking Like a Scientist? A Structural Study of LLM-Generated Research Methods","created":"2026-06-15","cited_by_count":0,"area":"lr"},{"id":"2607.19523","title":"When Reasoning Narrows the Move: Diversity Collapse in LLM Game Play","created":"2026-07-21","cited_by_count":0,"area":"lr"},{"id":"2608.13787","title":"From Passive Delegates to Strategic Negotiators: Reinforcing Social Reasoning in Small Language Models with SocialRL","created":"2026-08-13","cited_by_count":0,"area":"lr"},{"id":"2609.22194","title":"A Pinch of SFT, A Dash of RL: When Reinforcement Learning Helps Long-Horizon Advertising Agents","created":"2026-08-29","cited_by_count":0,"area":"lr"},{"id":"2609.33780","title":"Selecting Diverse SFT Traces Improves Post-RL Generalization","created":"2026-09-27","cited_by_count":0,"area":"lr"},{"id":"2610.11854","title":"GRPODropout: Less is More for Online Reinforcement Learning Rollouts","created":"2026-10-08","cited_by_count":0,"area":"lr"}],"next_cursor":null}