{"total":19,"rows":[{"id":"2511.17826","title":"Deterministic Inference across Tensor Parallel Sizes That Eliminates Training-Inference Mismatch","created":"2025-11-21","cited_by_count":14,"area":null},{"id":"2602.17616","title":"Stable Asynchrony: Variance-Controlled Off-Policy RL for LLMs","created":"2026-02-19","cited_by_count":11,"area":null},{"id":"2602.01826","title":"Beyond Precision: Training-Inference Mismatch is an Optimization Problem and Simple LR Scheduling Fixes It","created":"2026-02-02","cited_by_count":9,"area":null},{"id":"2604.07853","title":"QaRL: Rollout-Aligned Quantization-Aware RL for Fast and Stable Training under Training--Inference Mismatch","created":"2026-04-09","cited_by_count":7,"area":null},{"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":"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":"2604.21199","title":"ARFBench: Benchmarking Time Series Question Answering Ability for Software Incident Response","created":"2026-04-23","cited_by_count":6,"area":null},{"id":"2604.19790","title":"Hidden Reliability Risks in Large Language Models: Systematic Identification of Precision-Induced Output Disagreements","created":"2026-04-02","cited_by_count":5,"area":null},{"id":"2603.19470","title":"Adaptive Layerwise Perturbation: Unifying Off-Policy Corrections for LLM RL","created":"2026-03-19","cited_by_count":3,"area":null},{"id":"2511.02826","title":"PLUTO-4: Frontier Pathology Foundation Models","created":"2025-11-04","cited_by_count":2,"area":null},{"id":"2602.10609","title":"Online Causal Kalman Filtering for Stable and Effective Policy Optimization","created":"2026-02-11","cited_by_count":1,"area":null},{"id":"2604.28020","title":"Cost-Aware Learning","created":"2026-04-30","cited_by_count":1,"area":null},{"id":"2606.15621","title":"Re-feeding Is Not Replaying: Measuring Replay Noise in Counterfactual Token-Credit Estimation","created":"2026-06-14","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":"2608.11797","title":"Reading the Gate, Not the Interference: Output-Side Interference Measurement Does Not Track Merge Collapse","created":"2026-08-12","cited_by_count":1,"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":"2607.10848","title":"Predictive Divergence Masks for LLM RL","created":"2026-07-12","cited_by_count":0,"area":null},{"id":"2609.09783","title":"BRACE: Anchored Bellman-Residual Correction for Stale Critics in Asynchronous RL","created":"2026-09-09","cited_by_count":0,"area":null},{"id":"2609.26621","title":"Greedy Decoding Is Not Precision-Invariant: Cross-Precision Output Divergence in LLM Inference","created":"2026-09-22","cited_by_count":0,"area":null}],"next_cursor":null}