{"total":15,"rows":[{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065,"area":"lr"},{"id":"2401.02954","title":"DeepSeek LLM: Scaling Open-Source Language Models with Longtermism","created":"2024-01-05","cited_by_count":642,"area":"lr"},{"id":"2504.07491","title":"Kimi-VL Technical Report","created":"2025-04-10","cited_by_count":388,"area":"lr"},{"id":"2505.02881","title":"Rewriting Pre-Training Data Boosts LLM Performance in Math and Code","created":"2025-05-05","cited_by_count":21,"area":"lr"},{"id":"2307.00928","title":"Learning Differentiable Logic Programs for Abstract Visual Reasoning","created":"2023-07-03","cited_by_count":12,"area":"lr"},{"id":"2310.06003","title":"Rethinking Memory and Communication Cost for Efficient Large Language Model Training","created":"2023-10-09","cited_by_count":4,"area":"lr"},{"id":"2606.26997","title":"RolloutPipe: Overlapping Pipelined Rollout and Training in Disaggregated On-Policy LLM Reinforcement Learning","created":"2026-06-25","cited_by_count":4,"area":"lr"},{"id":"2512.11470","title":"Rethinking Expert Trajectory Utilization in LLM Post-training for Mathematical Reasoning","created":"2025-12-12","cited_by_count":2,"area":"lr"},{"id":"2602.11081","title":"SteuerLLM: Local specialized large language model for German tax law analysis","created":"2026-02-11","cited_by_count":1,"area":"lr"},{"id":"2602.00748","title":"HyperOffload: Graph-Driven Hierarchical Memory Management for Large Language Models on SuperNode Architectures","created":"2026-01-31","cited_by_count":0,"area":"lr"},{"id":"2603.10492","title":"Human-AI Co-reasoning for Clinical Diagnosis with Evidence-Integrated Language Agent","created":"2026-03-11","cited_by_count":0,"area":"lr"},{"id":"2606.05158","title":"Streaming Communication in Multi-Agent Reasoning","created":"2026-06-03","cited_by_count":0,"area":"lr"},{"id":"2606.24937","title":"The Hitchhiker's Guide to Agentic AI: From Foundations to Systems","created":"2026-06-22","cited_by_count":0,"area":"lr"},{"id":"2607.12395","title":"Ring-Zero: Scaling Zero RL to a Trillion Parameters for Emergent Reasoning","created":"2026-07-14","cited_by_count":0,"area":"lr"},{"id":"2609.25442","title":"WeightBridge: An Efficient Weight Transfer Library for Reinforcement Learning","created":"2026-09-21","cited_by_count":0,"area":"lr"}],"next_cursor":null}