{"total":64,"rows":[{"id":"2510.13786","title":"The Art of Scaling Reinforcement Learning Compute for LLMs","created":"2025-10-15","cited_by_count":101,"area":null},{"id":"2506.03136","title":"Co-Evolving LLM Coder and Unit Tester via Reinforcement Learning","created":"2025-06-03","cited_by_count":56,"area":null},{"id":"2508.03682","title":"Self-Questioning Language Models","created":"2025-08-05","cited_by_count":50,"area":null},{"id":"2505.13445","title":"Trust, But Verify: A Self-Verification Approach to Reinforcement Learning with Verifiable Rewards","created":"2025-05-19","cited_by_count":38,"area":null},{"id":"2509.07430","title":"The Choice of Divergence: A Neglected Key to Mitigating Diversity Collapse in Reinforcement Learning with Verifiable Reward","created":"2025-09-09","cited_by_count":37,"area":null},{"id":"2509.04419","title":"Towards a Unified View of Large Language Model Post-Training","created":"2025-09-04","cited_by_count":36,"area":null},{"id":"2509.16679","title":"Reinforcement Learning Meets Large Language Models: A Survey of Advancements and Applications Across the LLM Lifecycle","created":"2025-09-20","cited_by_count":35,"area":null},{"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":"2505.20282","title":"One-shot Entropy Minimization","created":"2025-05-26","cited_by_count":32,"area":null},{"id":"2601.09668","title":"STEP3-VL-10B Technical Report","created":"2026-01-14","cited_by_count":32,"area":null},{"id":"2509.22638","title":"Language Models Can Learn from Verbal Feedback Without Scalar Rewards","created":"2025-09-26","cited_by_count":18,"area":null},{"id":"2510.14807","title":"Beyond the Sampled Token: Preserving Candidate Support in RLVR","created":"2025-10-16","cited_by_count":18,"area":null},{"id":"2505.00662","title":"DeepCritic: Deliberate Critique with Large Language Models","created":"2025-05-01","cited_by_count":17,"area":null},{"id":"2510.06077","title":"When Thinking Drifts: Evidential Grounding for Robust Video Reasoning","created":"2025-10-07","cited_by_count":16,"area":null},{"id":"2602.11164","title":"Automated Optimization Modeling via a Localizable Error-Driven Perspective","created":"2026-01-17","cited_by_count":14,"area":null},{"id":"2511.15248","title":"EntroPIC: Towards Stable Long-Term Training of LLMs via Entropy Stabilization with Proportional-Integral Control","created":"2025-11-19","cited_by_count":13,"area":null},{"id":"2602.21492","title":"GradAlign: Gradient-Aligned Data Selection for LLM Reinforcement Learning","created":"2026-02-25","cited_by_count":12,"area":null},{"id":"2506.23127","title":"Unleashing Embodied Task Planning Ability in LLMs via Reinforcement Learning","created":"2025-06-29","cited_by_count":9,"area":null},{"id":"2510.18554","title":"Extracting alignment data in open models","created":"2025-10-21","cited_by_count":8,"area":null},{"id":"2602.03392","title":"On the Entropy Dynamics in Reinforcement Fine-Tuning of Large Language Models","created":"2026-02-03","cited_by_count":8,"area":null},{"id":"2504.13950","title":"Open-Medical-R1: How to Choose Data for RLVR Training at Medicine Domain","created":"2025-04-16","cited_by_count":7,"area":null},{"id":"2602.03584","title":"$V_0$: A Generalist Value Model for Any Policy at State Zero","created":"2026-02-03","cited_by_count":7,"area":null},{"id":"2602.12036","title":"Composition-RL: Compose Your Verifiable Prompts for Reinforcement Learning of Large Language Models","created":"2026-02-12","cited_by_count":6,"area":null},{"id":"2603.12151","title":"IsoCompute Playbook: Optimally Scaling Sampling Compute for LLM RL","created":"2026-03-12","cited_by_count":6,"area":null},{"id":"2606.14502","title":"From Chatbot to Digital Colleague: The Paradigm Shift Toward Persistent Autonomous AI","created":"2026-06-12","cited_by_count":6,"area":null},{"id":"2510.08549","title":"Entropy Regularizing Activation: Boosting Continuous Control, Large Language Models, and Image Classification with Activation as Entropy Constraints","created":"2025-10-09","cited_by_count":4,"area":null},{"id":"2603.14935","title":"Video-CoE: Reinforcing Video Event Prediction via Chain of Events","created":"2026-03-16","cited_by_count":4,"area":null},{"id":"2608.27409","title":"Consolidating RLVR Capabilities Across Domains: A Deep Dive into Fusion Paradigms","created":"2026-08-27","cited_by_count":4,"area":null},{"id":"2601.13284","title":"Balancing Classification and Calibration Performance in Decision-Making LLMs via Calibration Aware Reinforcement Learning","created":"2026-01-19","cited_by_count":3,"area":null},{"id":"2605.08441","title":"DUET: Optimize Token-Budget Allocation for Reinforcement Learning with Verifiable Rewards","created":"2026-05-08","cited_by_count":3,"area":null},{"id":"2605.08666","title":"The Cancellation Hypothesis in Critic-Free RL: From Outcome Rewards to Token Credits","created":"2026-05-09","cited_by_count":3,"area":null},{"id":"2605.28860","title":"Mechanistic origins of catastrophic forgetting: why RL preserves circuits better than SFT?","created":"2026-05-21","cited_by_count":3,"area":null},{"id":"2606.02437","title":"On the Scaling of PEFT: Towards Million Personal Models of Trillion Parameters","created":"2026-06-01","cited_by_count":3,"area":null},{"id":"2607.16850","title":"Group Entropy-Controlled Policy Optimization","created":"2026-07-18","cited_by_count":3,"area":null},{"id":"2506.03077","title":"StreamBP: Memory-Efficient Exact Backpropagation for Long Sequence Training of LLMs","created":"2025-06-03","cited_by_count":2,"area":null},{"id":"2603.15011","title":"Molecular Identifier Visual Prompt and Verifiable Reinforcement Learning for Chemical Reaction Diagram Parsing","created":"2026-03-16","cited_by_count":2,"area":null},{"id":"2606.05376","title":"SHALA-LLM: Smartly Handling Ambiguous Labels in Aligning LLMs","created":"2026-06-03","cited_by_count":2,"area":null},{"id":"2607.22039","title":"Enough is as good as a feast: A Comprehensive Analysis of How Reinforcement Learning Mitigates Task Conflicts in LLMs","created":"2026-07-24","cited_by_count":2,"area":null},{"id":"2504.13471","title":"From Large to Super-Tiny: End-to-End Optimization for Cost-Efficient LLMs","created":"2025-04-18","cited_by_count":1,"area":null},{"id":"2511.05301","title":"QueStER: Query Specification for Generative keyword-based Retrieval","created":"2025-11-07","cited_by_count":1,"area":null},{"id":"2601.06911","title":"Distributional Clarity: The Hidden Driver of RL-Friendliness in Large Language Models","created":"2026-01-11","cited_by_count":1,"area":null},{"id":"2602.03542","title":"Can Large Language Models Generalize Procedures Across Representations?","created":"2026-02-03","cited_by_count":1,"area":null},{"id":"2603.16843","title":"Internalizing Agency from Reflective Experience","created":"2026-03-17","cited_by_count":1,"area":null},{"id":"2605.00610","title":"Decouple before Integration: Test-time Synthesis of SFT and RLVR Task Vectors","created":"2026-05-01","cited_by_count":1,"area":null},{"id":"2605.02469","title":"Reference-Sampled Boltzmann Projection for KL-Regularized RLVR: Target-Matched Weighted SFT, Finite One-Shot Gaps, and Policy Mirror Descent","created":"2026-05-04","cited_by_count":1,"area":null},{"id":"2605.08568","title":"Different Prompts, Different Ranks: Prompt-aware Dynamic Rank Selection for SVD-based LLM Compression","created":"2026-05-09","cited_by_count":1,"area":null},{"id":"2605.11813","title":"Automated Reformulation of Robust Optimization via Memory-Augmented Large Language Models","created":"2026-05-12","cited_by_count":1,"area":null},{"id":"2605.26971","title":"RLVR Datasets and Where to Find Them: Tracing Data Lineage for Better Training Data","created":"2026-05-26","cited_by_count":1,"area":null},{"id":"2605.31058","title":"Combinatorial Synthesis: Scaling Code RLVR via Atomic Decomposition and Recombination","created":"2026-05-29","cited_by_count":1,"area":null},{"id":"2606.02252","title":"ResMerge: Residual-based Spectral Merging of Large Language Models","created":"2026-06-01","cited_by_count":1,"area":null},{"id":"2606.29526","title":"The Mirage of Optimizing Training Policies: Monotonic Inference Policies as the Real Objective for LLM Reinforcement Learning","created":"2026-06-28","cited_by_count":1,"area":null},{"id":"2608.16739","title":"Le Critique: Privileged Value Functions for LLM Reinforcement Learning","created":"2026-08-17","cited_by_count":1,"area":null},{"id":"2610.05292","title":"Erased, Rerouted, or Rescaled? Post-Training and the Causal Quotient of a Language Model's Belief State","created":"2026-10-04","cited_by_count":1,"area":null},{"id":"2504.05119","title":"Balancing Robustness and Efficiency in Embedded DNNs Through Activation Function Selection","created":"2025-04-07","cited_by_count":0,"area":null},{"id":"2505.24500","title":"TimeHC-RL: Temporal-aware Hierarchical Cognitive Reinforcement Learning for Enhancing LLMs' Social Intelligence","created":"2025-05-30","cited_by_count":0,"area":null},{"id":"2601.23048","title":"From Abstract to Contextual: What LLMs Still Cannot Do in Mathematics","created":"2026-01-30","cited_by_count":0,"area":null},{"id":"2602.11863","title":"In-Context Function Learning in Large Language Models","created":"2026-02-12","cited_by_count":0,"area":null},{"id":"2605.10445","title":"Uni-Synergy: Bridging Understanding and Generation for Personalized Reasoning via Co-operative Reinforcement Learning","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2606.08779","title":"Reformulate LLM Reinforcement Learning for Efficient Training under Black-box Discrepancy","created":"2026-06-07","cited_by_count":0,"area":null},{"id":"2607.05461","title":"AdaStop: Cost-Aware Early Stopping for DNN Test Selection","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2608.00019","title":"Uncertainty-Aware Simulation-Based Inference for Operations Research with Large Language Models","created":"2026-07-01","cited_by_count":0,"area":null},{"id":"2609.01422","title":"From Rollouts to Recipes: Self-Contained Post-Training for LLMs","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2610.05966","title":"HuatuoGPT-3: RL-Only Domain Adaptation from Base Models","created":"2026-10-05","cited_by_count":0,"area":null},{"id":"2610.12161","title":"When KL Regularization Misfires in Group Policy Optimization","created":"2026-10-08","cited_by_count":0,"area":null}],"next_cursor":null}