{"total":14,"rows":[{"id":"2601.04436","title":"Learning to Simulate Human Dialogue","created":"2026-01-07","cited_by_count":9,"area":null},{"id":"2512.23966","title":"Efficient Context Scaling with LongCat ZigZag Attention","created":"2025-12-30","cited_by_count":6,"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":"2604.22779","title":"KARL: Mitigating Hallucinations in LLMs via Knowledge-Boundary-Aware Reinforcement Learning","created":"2026-04-03","cited_by_count":2,"area":null},{"id":"2606.13125","title":"Select and Improve: Understanding the Mechanics of Post-Training for Reasoning","created":"2026-06-11","cited_by_count":2,"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":"2606.04272","title":"RL Excursions during Pre-Training: Re-examining Policy Optimization for LLM training","created":"2026-06-02","cited_by_count":1,"area":null},{"id":"2608.13482","title":"Synthetic Persona Pretraining: Alignment from Token Zero","created":"2026-08-13","cited_by_count":1,"area":null},{"id":"2603.19294","title":"Maximizing Mutual Information Between Prompt and Response Improves LLM Performance With No Additional Data","created":"2026-03-10","cited_by_count":0,"area":null},{"id":"2606.27369","title":"Reinforcement Learning without Ground-Truth Solutions can Improve LLMs","created":"2026-06-25","cited_by_count":0,"area":null},{"id":"2608.13545","title":"LittleLearner: Language Models Under Pedagogically Controlled Knowledge Exposure","created":"2026-08-13","cited_by_count":0,"area":null},{"id":"2608.21325","title":"Move by Move: Measuring and Steering How LLMs Conduct Psychotherapy","created":"2026-08-21","cited_by_count":0,"area":null},{"id":"2609.09081","title":"Everything in Moderation: Per-Domain Coverage Optima and Alignment-Resistant Domain Gaps in Multi-Domain Mid-Training","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2610.04978","title":"What Will Post-Training Fix? Per-Problem Gains Are Shared Across Independent RL Runs, and Existing Checkpoints Predict Them Better Than A Priori Signals","created":"2026-10-04","cited_by_count":0,"area":null}],"next_cursor":null}