{"total":11,"rows":[{"id":"2604.07941","title":"Large Language Model Post-Training: A Unified View of Off-Policy and On-Policy Learning","created":"2026-04-09","cited_by_count":6,"area":null},{"id":"2606.01774","title":"FLARE: Diffusion for Hybrid Language Model","created":"2026-06-01","cited_by_count":6,"area":null},{"id":"2606.14502","title":"From Chatbot to Digital Colleague: The Paradigm Shift Toward Persistent Autonomous AI","created":"2026-06-12","cited_by_count":6,"area":null},{"id":"2608.11152","title":"Scheduling Mixed RL Rollouts Beyond Prefix Locality","created":"2026-08-11","cited_by_count":1,"area":null},{"id":"2609.00092","title":"Safin-1: Safety from Within through Memory-Native State Evolution","created":"2026-08-31","cited_by_count":1,"area":null},{"id":"2609.19553","title":"From Parameters to Behaviors: A Survey of Model Fusion for Large Language Models","created":"2026-09-17","cited_by_count":1,"area":null},{"id":"2607.05198","title":"Noisy-Channel Minimum Bayes Risk Decoding","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2608.20953","title":"Quantization-Aware Healing: A Practical Recipe for Recovering Compressed, 4-Bit LLMs","created":"2026-08-21","cited_by_count":0,"area":null},{"id":"2609.10293","title":"GANDR: Claim Auditing for Verifiable Legal Answer Generation","created":"2026-09-09","cited_by_count":0,"area":null},{"id":"2609.23989","title":"ACLArena: Agent Continue Learning in Multi-stage Post-training","created":"2026-09-21","cited_by_count":0,"area":null},{"id":"2610.15894","title":"Make Every Expansion Count: Learning to Search Efficiently in LLM Code Repair","created":"2026-10-11","cited_by_count":0,"area":null}],"next_cursor":null}