{"total":18,"rows":[{"id":"2606.15007","title":"Nemotron 3 Ultra: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning","created":"2026-06-12","cited_by_count":42,"area":"lr"},{"id":"2601.09088","title":"Distribution-Aligned Sequence Distillation for Superior Long-CoT Reasoning","created":"2026-01-14","cited_by_count":17,"area":"lr"},{"id":"2602.12566","title":"To Mix or To Merge: Toward Multi-Domain Reinforcement Learning for Large Language Models","created":"2026-02-13","cited_by_count":11,"area":"lr"},{"id":"2602.22603","title":"SideQuest: Model-Driven KV Cache Management for Long-Horizon Agentic Reasoning","created":"2026-02-26","cited_by_count":11,"area":"lr"},{"id":"2606.26080","title":"Neglected Free Lunch from Post-training: Progress Advantage for LLM Agents","created":"2026-06-24","cited_by_count":6,"area":"lr"},{"id":"2606.19257","title":"DreamReasoner-8B: Block-Size Curriculum Learning for Diffusion Reasoning Models","created":"2026-06-17","cited_by_count":5,"area":"lr"},{"id":"2605.05365","title":"ZAYA1-8B Technical Report","created":"2026-05-06","cited_by_count":4,"area":"lr"},{"id":"2603.21877","title":"P^2O: Joint Policy and Prompt Optimization","created":"2026-03-23","cited_by_count":3,"area":"lr"},{"id":"2605.07182","title":"Star Elastic: Many-in-One Reasoning LLMs with Efficient Budget Control","created":"2026-05-08","cited_by_count":3,"area":"lr"},{"id":"2605.07654","title":"Reliable Chain-of-Thought via Prefix Consistency","created":"2026-05-08","cited_by_count":3,"area":"lr"},{"id":"2606.16140","title":"VibeThinker-3B: Exploring the Frontier of Verifiable Reasoning in Small Language Models","created":"2026-06-15","cited_by_count":2,"area":"lr"},{"id":"2606.21884","title":"A Verifiable Search Is Not a Learnable Chain-of-Thought","created":"2026-06-20","cited_by_count":1,"area":"lr"},{"id":"2605.30052","title":"REPOT: Recoverable Program-of-Thought via Checkpoint Repair","created":"2026-05-28","cited_by_count":0,"area":"lr"},{"id":"2609.00590","title":"CRAFT: Fine-Tuning Pre-hoc Explainability in AI-native 6G RAN","created":"2026-09-01","cited_by_count":0,"area":"lr"},{"id":"2609.02849","title":"Post-Training Language Models for Gold-Medal Performance in Coding Competitions","created":"2026-09-02","cited_by_count":0,"area":"lr"},{"id":"2609.31947","title":"On-Policy Attention Linearization","created":"2026-09-25","cited_by_count":0,"area":"lr"},{"id":"2610.06366","title":"Correct Verdicts, Flawed Reasoning: Structured Auditing of LLM-based Vulnerability Reasoning","created":"2026-10-05","cited_by_count":0,"area":"lr"},{"id":"2610.16593","title":"Double-Rollout Reinforcement Learning with Sampling-based Reward Estimation","created":"2026-10-12","cited_by_count":0,"area":"lr"}],"next_cursor":null}