{"total":23,"rows":[{"id":"2505.07608","title":"MiMo: Unlocking the Reasoning Potential of Language Model -- From Pretraining to Posttraining","created":"2025-05-12","cited_by_count":121,"area":"lr"},{"id":"2507.06203","title":"A Survey on Latent Reasoning","created":"2025-07-08","cited_by_count":81,"area":"lr"},{"id":"2510.10689","title":"OmniVideoBench: Towards Audio-Visual Understanding Evaluation for Omni MLLMs","created":"2025-10-12","cited_by_count":59,"area":"lr"},{"id":"2505.17667","title":"QwenLong-L1: Towards Long-Context Large Reasoning Models with Reinforcement Learning","created":"2025-05-23","cited_by_count":50,"area":"lr"},{"id":"2509.23863","title":"SPELL: Self-Play Reinforcement Learning for Evolving Long-Context Language Models","created":"2025-09-28","cited_by_count":29,"area":"lr"},{"id":"2505.20096","title":"MA-RAG: Multi-Agent Retrieval-Augmented Generation via Collaborative Chain-of-Thought Reasoning","created":"2025-05-26","cited_by_count":26,"area":"lr"},{"id":"2507.06181","title":"CriticLean: Critic-Guided Reinforcement Learning for Mathematical Formalization","created":"2025-07-08","cited_by_count":16,"area":"lr"},{"id":"2504.13828","title":"Generative AI Act II: Test Time Scaling Drives Cognition Engineering","created":"2025-04-18","cited_by_count":15,"area":"lr"},{"id":"2507.08297","title":"KAT-V1: Kwai-AutoThink Technical Report","created":"2025-07-11","cited_by_count":12,"area":"lr"},{"id":"2510.07312","title":"h1: Bootstrapping LLMs to Reason over Longer Horizons via Reinforcement Learning","created":"2025-10-08","cited_by_count":9,"area":"lr"},{"id":"2602.10560","title":"When to Memorize and When to Stop: Gated Recurrent Memory for Long-Context Reasoning","created":"2026-02-11","cited_by_count":9,"area":"lr"},{"id":"2602.08382","title":"Dynamic Long Context Reasoning over Compressed Memory via End-to-End Reinforcement Learning","created":"2026-02-09","cited_by_count":8,"area":"lr"},{"id":"2603.28610","title":"ResAdapt: Adaptive Resolution for Efficient Multimodal Reasoning","created":"2026-03-30","cited_by_count":8,"area":"lr"},{"id":"2510.07768","title":"ToolLibGen: Scalable Automatic Tool Creation and Aggregation for LLM Reasoning","created":"2025-10-09","cited_by_count":5,"area":"lr"},{"id":"2606.10616","title":"Learning What to Remember: Observability-Safe Memory Retention via Constrained Optimization for Long-Horizon Language Agents","created":"2026-06-09","cited_by_count":4,"area":"lr"},{"id":"2602.08874","title":"Do Reasoning LLMs Refuse What They Infer in Long Contexts?","created":"2026-02-09","cited_by_count":3,"area":"lr"},{"id":"2604.01161","title":"Reasoning Shift: How Context Silently Shortens LLM Reasoning","created":"2026-04-01","cited_by_count":3,"area":"lr"},{"id":"2509.21028","title":"SciTrek: Evaluating and Improving Long-Context Numerical Reasoning over Scientific Articles","created":"2025-09-25","cited_by_count":1,"area":"lr"},{"id":"2605.15016","title":"COTCAgent: Preventive Consultation via Probabilistic Chain-of-Thought Completion","created":"2026-05-14","cited_by_count":0,"area":"lr"},{"id":"2605.20201","title":"Long-Context Reasoning Through Proxy-Based Chain-of-Thought Tuning","created":"2026-04-06","cited_by_count":0,"area":"lr"},{"id":"2608.03048","title":"PI-Mem: Pushing Long-Context Reasoning to 3.6M Tokens with Parallel-Iterative Memory","created":"2026-08-04","cited_by_count":0,"area":"lr"},{"id":"2608.07838","title":"Counterfactual Benchmarking and Training for Factuality Consistency and Order-Robust Grounded Reasoning in LLMs over Heterogeneous Knowledge","created":"2026-08-08","cited_by_count":0,"area":"lr"},{"id":"2609.36935","title":"CoEM: Empowering Long-Context Reasoning with Commit-on-Evidence Memory","created":"2026-09-29","cited_by_count":0,"area":"lr"}],"next_cursor":null}