{"total":21,"rows":[{"id":"2506.12217","title":"From Emergence to Control: Probing and Modulating Self-Reflection in Language Models","created":"2025-06-13","cited_by_count":6,"area":null},{"id":"2511.19356","title":"Rethinking Reward Signals in Video GRPO: When Scores Become Targets","created":"2025-11-24","cited_by_count":6,"area":null},{"id":"2510.08539","title":"On the optimization dynamics of RLVR: Gradient gap and step size thresholds","created":"2025-10-09","cited_by_count":4,"area":null},{"id":"2605.14967","title":"InfoSFT: Learn More and Forget Less with Information-Aware Token Weighting","created":"2026-05-14","cited_by_count":4,"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":"2604.20398","title":"WebGen-R1: Incentivizing Large Language Models to Generate Functional and Aesthetic Websites with Reinforcement Learning","created":"2026-04-22","cited_by_count":2,"area":null},{"id":"2505.21478","title":"Policy Optimized Text-to-Image Pipeline Design","created":"2025-05-27","cited_by_count":1,"area":null},{"id":"2507.12911","title":"LaViPlan : Language-Guided Visual Path Planning with RLVR","created":"2025-07-17","cited_by_count":1,"area":null},{"id":"2609.22547","title":"RLVR is a Kernel, Not a Function: Statistical Inference for pass@$k$ Crossovers","created":"2026-09-18","cited_by_count":1,"area":null},{"id":"2504.02304","title":"Measurement of LLM's Philosophies of Human Nature","created":"2025-04-03","cited_by_count":0,"area":null},{"id":"2511.07803","title":"Judging by the Rules: Compliance-Aligned Framework for Modern Slavery Statement Monitoring","created":"2025-11-11","cited_by_count":0,"area":null},{"id":"2603.15997","title":"Visual Set Program Synthesizer","created":"2026-03-16","cited_by_count":0,"area":null},{"id":"2604.08986","title":"PerMix-RLVR: Preserving Persona Expressivity under Verifiable-Reward Alignment","created":"2026-04-10","cited_by_count":0,"area":null},{"id":"2604.19404","title":"M$^{2}$GRPO: Mamba-based Multi-Agent Group Relative Policy Optimization for Biomimetic Underwater Robots Pursuit","created":"2026-04-21","cited_by_count":0,"area":null},{"id":"2605.31034","title":"Annealed Softmax Greedy in Many-Armed Bayesian Bandits","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2606.12086","title":"IntElicit: Eliciting and Assessing Contextualized Creativity via Dialogue Policy Optimization","created":"2026-06-10","cited_by_count":0,"area":null},{"id":"2606.30789","title":"Predictable GRPO: A Closed-Form Model of Training Dynamics","created":"2026-06-29","cited_by_count":0,"area":null},{"id":"2607.19044","title":"Adopting Reinforcement Learning with Verifiable Rewards for Molecular Generation","created":"2026-07-21","cited_by_count":0,"area":null},{"id":"2609.18496","title":"MiST: Mid-Training LLMs for Cybersecurity","created":"2026-09-16","cited_by_count":0,"area":null},{"id":"2609.27833","title":"From Reasoning Strings to Partial Orders: Verifier-Certified Rule Transport through Quotient Policy Optimization","created":"2026-08-20","cited_by_count":0,"area":null},{"id":"2609.38799","title":"Overlap, Unique and Conflict: Can LLMs Extract What They Can Recognize?","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}