{"total":23,"rows":[{"id":"2605.14220","title":"Diagnosing Training Inference Mismatch in LLM Reinforcement Learning via a Zero-Mismatch Reference","created":"2026-05-14","cited_by_count":7,"area":null},{"id":"2601.12186","title":"Aletheia: What Makes RLVR For Code Verifiers Tick?","created":"2026-01-17","cited_by_count":5,"area":null},{"id":"2603.04918","title":"BandPO: Bridging Trust Regions and Ratio Clipping via Probability-Aware Bounds for LLM Reinforcement Learning","created":"2026-03-05","cited_by_count":3,"area":null},{"id":"2603.06194","title":"MICA: Multi-granularity Intertemporal Credit Assignment for Long-Horizon Emotional Support Dialogue","created":"2026-03-06","cited_by_count":3,"area":null},{"id":"2601.23228","title":"Scaling Multiagent Systems with Process Rewards","created":"2026-01-30","cited_by_count":2,"area":null},{"id":"2607.26253","title":"Early Verdicts, Better Budgets: Sequential Adaptive Rollout Allocation for Compute-Efficient RLVR","created":"2026-07-28","cited_by_count":2,"area":null},{"id":"2608.01321","title":"BiCAA: Bidirectional Credit Assignment for Search-Augmented Agent","created":"2026-08-02","cited_by_count":2,"area":null},{"id":"2609.08368","title":"Miles v0.1: Production-Level Post-Training","created":"2026-09-08","cited_by_count":1,"area":null},{"id":"2609.19164","title":"Advantage Scale Calibration Imbalance in Group-Relative Optimization under Low-Variance Rewards: Diagnosis and Bounded Recovery","created":"2026-08-27","cited_by_count":1,"area":null},{"id":"2603.19152","title":"VEPO: Variable Entropy Policy Optimization for Low-Resource Language Foundation Models","created":"2026-03-19","cited_by_count":0,"area":null},{"id":"2604.27644","title":"ANCORA: Learning to Question via Manifold-Anchored Self-Play for Verifiable Reasoning","created":"2026-04-30","cited_by_count":0,"area":null},{"id":"2605.06981","title":"Bridging Textual Profiles and Latent User Embeddings for Personalization","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2605.11235","title":"Internalizing Curriculum Judgment for LLM Reinforcement Fine-Tuning","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2605.17295","title":"DISA: Offline Importance Sampling for Distribution-Matching LLM-RL","created":"2026-05-17","cited_by_count":0,"area":null},{"id":"2606.00257","title":"ARCA: Adapter-Residual Credit Assignment When Token Signals Degenerate","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2606.13710","title":"Hybrid Open-Ended Tri-Evolution Makes Better Deep Researcher","created":"2026-06-10","cited_by_count":0,"area":null},{"id":"2609.00444","title":"Group Adaptive Clipping Policy Optimization","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.06671","title":"Tracking the Moving Frontier: Long-Short Term Advantage Estimator","created":"2026-09-06","cited_by_count":0,"area":null},{"id":"2609.26355","title":"PACT: From Credit Assignment to Critic Alignment","created":"2026-09-22","cited_by_count":0,"area":null},{"id":"2609.32228","title":"CompassPlay: Rewarding the Proposer for Where It Moves the Solver","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.35433","title":"ReSPO: Reshaped Sequence Policy Optimization for Gradient Starvation in Off-Policy Learning","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.36802","title":"EasyPPO: Stabilizing the Critic Is Key","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.40035","title":"OPTS-TTPO: Enhancing Finite-Sample Policy-Gradient Learning with Tree Search","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}