{"total":17,"rows":[{"id":"2506.10943","title":"Self-Adapting Language Models","created":"2025-06-12","cited_by_count":84,"area":null},{"id":"2509.16679","title":"Reinforcement Learning Meets Large Language Models: A Survey of Advancements and Applications Across the LLM Lifecycle","created":"2025-09-20","cited_by_count":35,"area":null},{"id":"2509.24372","title":"Evolution Strategies at Scale: LLM Fine-Tuning Beyond Reinforcement Learning","created":"2025-09-29","cited_by_count":34,"area":null},{"id":"2509.10147","title":"Virtual Agent Economies","created":"2025-09-12","cited_by_count":21,"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":"2510.25368","title":"Position: Biology is the Challenge Physics-Informed ML Needs to Evolve","created":"2025-10-29","cited_by_count":4,"area":null},{"id":"2605.04431","title":"Towards Robust LLM Post-Training: Automatic Failure Management for Reinforcement Fine-Tuning","created":"2026-05-06","cited_by_count":3,"area":null},{"id":"2601.15690","title":"From Passive Metric to Active Signal: The Evolving Role of Uncertainty Quantification in Large Language Models","created":"2026-01-22","cited_by_count":2,"area":null},{"id":"2609.03955","title":"Two-Stage Reinforcement Learning for Sound and Adversarial Test Generation in Code LLMs","created":"2026-09-03","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":"2509.10509","title":"The Anti-Ouroboros Effect: Emergent Resilience in Large Language Models from Recursive Selective Feedback","created":"2025-09-02","cited_by_count":0,"area":null},{"id":"2601.03451","title":"Microeconomic Foundations of Multi-Agent Learning","created":"2026-01-06","cited_by_count":0,"area":null},{"id":"2606.26917","title":"GEOALIGN: Geometric Rollout Curation for Robust LLM Reinforcement Learning","created":"2026-06-25","cited_by_count":0,"area":null},{"id":"2608.29280","title":"RAGDiffusion++: From Macro-Retrieval to Micro-Fidelity Alignment for Garment Generation","created":"2026-08-29","cited_by_count":0,"area":null},{"id":"2609.00064","title":"Attention Sensitivity Is Not Enough: Dissociating Attention-Level and Behavioural In-Context Learning under Fine-Tuning","created":"2026-08-30","cited_by_count":0,"area":null},{"id":"2609.20156","title":"QUALS: Corpus Equilibrium for Universal Forecasting via Pattern Quantization and Learnability Synchronization","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2609.23457","title":"RLVR$^{2}$: Reinforcement Learning with Verifiable Rubric-based Ranking","created":"2026-09-20","cited_by_count":0,"area":null}],"next_cursor":null}