{"total":9,"rows":[{"id":"2604.16027","title":"Where does output diversity collapse in post-training?","created":"2026-04-17","cited_by_count":11,"area":null},{"id":"2605.22817","title":"Vector Policy Optimization: Training for Diversity Improves Test-Time Search","created":"2026-05-21","cited_by_count":8,"area":null},{"id":"2607.27372","title":"Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation","created":"2026-07-29","cited_by_count":4,"area":null},{"id":"2605.09214","title":"Fast Rates for Offline Contextual Bandits with Forward-KL Regularization under Single-Policy Concentrability","created":"2026-05-09","cited_by_count":3,"area":null},{"id":"2607.12796","title":"The One-Word Census: Answer-Choice Conformity Across 105 Language Models","created":"2026-07-14","cited_by_count":3,"area":null},{"id":"2608.01743","title":"Toward Plasticity-Preserving KL Regularization for Capability Retention in LLM Reinforcement Learning","created":"2026-08-03","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":"2607.20429","title":"More Is Not More: What Matters for Diversity in LLM Opinions?","created":"2026-05-10","cited_by_count":0,"area":null},{"id":"2608.27757","title":"Beyond Search-Imitation: Prior-Directed Exploration for Searchless Chess","created":"2026-08-27","cited_by_count":0,"area":null}],"next_cursor":null}