{"total":15,"rows":[{"id":"2501.17161","title":"SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training","created":"2025-01-28","cited_by_count":672,"area":"lr"},{"id":"2504.09037","title":"A Survey of Frontiers in LLM Reasoning: Inference Scaling, Learning to Reason, and Agentic Systems","created":"2025-04-12","cited_by_count":111,"area":"lr"},{"id":"2505.08243","title":"Training Strategies for Efficient Embodied Reasoning","created":"2025-05-13","cited_by_count":55,"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":"2507.00971","title":"Reasoning as an Adaptive Defense for Safety","created":"2025-07-01","cited_by_count":23,"area":"lr"},{"id":"2508.05612","title":"Shuffle-R1: Efficient RL framework for Multimodal Large Language Models via Data-centric Dynamic Shuffle","created":"2025-08-07","cited_by_count":19,"area":"lr"},{"id":"2601.18795","title":"Reuse your FLOPs: Scaling RL on Hard Problems by Conditioning on Very Off-Policy Prefixes","created":"2026-01-26","cited_by_count":16,"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":"2505.18917","title":"Behavior Injection: Preparing Language Models for Reinforcement Learning","created":"2025-05-25","cited_by_count":8,"area":"lr"},{"id":"2501.18482","title":"A Tool for In-depth Analysis of Code Execution Reasoning of Large Language Models","created":"2025-01-30","cited_by_count":7,"area":"lr"},{"id":"2504.01738","title":"Style over Substance: Distilled Language Models Reason Via Stylistic Replication","created":"2025-04-02","cited_by_count":5,"area":"lr"},{"id":"2507.04782","title":"Reason to Rote: Rethinking Memorization in Reasoning","created":"2025-07-07","cited_by_count":5,"area":"lr"},{"id":"2507.14393","title":"Adaptive Multi-Agent Reasoning via Automated Workflow Generation","created":"2025-07-18","cited_by_count":1,"area":"lr"},{"id":"2506.17630","title":"Answer-Centric or Reasoning-Driven? Uncovering the Latent Memory Anchor in LLMs","created":"2025-06-21","cited_by_count":0,"area":"lr"},{"id":"2606.17024","title":"ExpRL: Exploratory RL for LLM Mid-Training","created":"2026-06-15","cited_by_count":0,"area":"lr"}],"next_cursor":null}