{"total":35,"rows":[{"id":"2501.12570","title":"O1-Pruner: Length-Harmonizing Fine-Tuning for O1-Like Reasoning Pruning","created":"2025-01-22","cited_by_count":279,"area":"lr"},{"id":"2504.15585","title":"A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment","created":"2025-04-22","cited_by_count":116,"area":"lr"},{"id":"2505.10475","title":"Parallel Scaling Law for Language Models","created":"2025-05-15","cited_by_count":30,"area":"lr"},{"id":"2504.15777","title":"Tina: Tiny Reasoning Models via LoRA","created":"2025-04-22","cited_by_count":25,"area":"lr"},{"id":"2502.00330","title":"From Few to Many: Self-Improving Many-Shot Reasoners Through Iterative Optimization and Generation","created":"2025-02-01","cited_by_count":21,"area":"lr"},{"id":"2503.04543","title":"Keeping Yourself is Important in Downstream Tuning Multimodal Large Language Model","created":"2025-03-06","cited_by_count":16,"area":"lr"},{"id":"2502.11740","title":"Mitigating Visual Knowledge Forgetting in MLLM Instruction-tuning via Modality-decoupled Gradient Descent","created":"2025-02-17","cited_by_count":13,"area":"lr"},{"id":"2508.12495","title":"Mitigating Hallucinations in Large Language Models via Causal Reasoning","created":"2025-08-17","cited_by_count":13,"area":"lr"},{"id":"2509.17336","title":"Mano Technical Report","created":"2025-09-22","cited_by_count":13,"area":"lr"},{"id":"2503.13208","title":"Improving Complex Reasoning with Dynamic Prompt Corruption: A soft prompt Optimization Approach","created":"2025-03-17","cited_by_count":9,"area":"lr"},{"id":"2409.15454","title":"In-Context Learning May Not Elicit Trustworthy Reasoning: A-Not-B Errors in Pretrained Language Models","created":"2024-09-23","cited_by_count":8,"area":"lr"},{"id":"2603.01761","title":"Position: Modular Memory is the Key to Continual Learning Agents","created":"2026-03-02","cited_by_count":8,"area":"lr"},{"id":"2405.15551","title":"Thinking Forward: Memory-Efficient Federated Finetuning of Language Models","created":"2024-05-24","cited_by_count":7,"area":"lr"},{"id":"2411.04535","title":"Meta-Reasoning Improves Tool Use in Large Language Models","created":"2024-11-07","cited_by_count":6,"area":"lr"},{"id":"2503.21735","title":"GateLens: A Reasoning-Enhanced LLM Agent for Automotive Software Release Analytics","created":"2025-03-27","cited_by_count":4,"area":"lr"},{"id":"2504.09100","title":"A Short Survey on Small Reasoning Models: Training, Inference, Applications and Research Directions","created":"2025-04-12","cited_by_count":4,"area":"lr"},{"id":"2601.09361","title":"GeoRA: Geometry-Aware Low-Rank Adaptation for RLVR","created":"2026-01-14","cited_by_count":4,"area":"lr"},{"id":"2407.11009","title":"CharED: Character-wise Ensemble Decoding for Large Language Models","created":"2024-06-25","cited_by_count":3,"area":"lr"},{"id":"2503.13988","title":"Empowering Smaller Models: Tuning LLaMA and Gemma with Chain-of-Thought for Ukrainian Exam Tasks","created":"2025-03-18","cited_by_count":2,"area":"lr"},{"id":"2506.19095","title":"Baba is LLM: Reasoning in a Game with Dynamic Rules","created":"2025-06-23","cited_by_count":2,"area":"lr"},{"id":"2509.08105","title":"MERLIN: Multi-Stage Curriculum Alignment for Multilingual Encoder-LLM Integration in Cross-Lingual Reasoning","created":"2025-09-09","cited_by_count":2,"area":"lr"},{"id":"2510.17130","title":"SEER: Enhancing Chain-of-Thought Code Generation through Self-Exploring Deep Reasoning","created":"2025-10-20","cited_by_count":2,"area":"lr"},{"id":"2605.04451","title":"RemoteZero: Geospatial Reasoning with Zero Labels","created":"2026-05-06","cited_by_count":2,"area":"lr"},{"id":"2412.12163","title":"Towards LLM-based optimization compilers. Can LLMs learn how to apply a single peephole optimization? Reasoning is all LLMs need!","created":"2024-12-11","cited_by_count":1,"area":"lr"},{"id":"2503.09474","title":"Surgical AI Copilot: Energy-Based Fourier Gradient Low-Rank Adaptation for Surgical LLM Agent Reasoning and Planning","created":"2025-03-12","cited_by_count":1,"area":"lr"},{"id":"2505.17153","title":"Amplify Adjacent Token Differences: Enhancing Long Chain-of-Thought Reasoning with Shift-FFN","created":"2025-05-22","cited_by_count":1,"area":"lr"},{"id":"2506.13746","title":"Evaluating Large Language Models for Phishing Detection, Self-Consistency, Faithfulness, and Explainability","created":"2025-06-16","cited_by_count":1,"area":"lr"},{"id":"2510.06005","title":"MASA: Rethinking the Representational Bottleneck in LoRA with Multi-A Shared Adaptation","created":"2025-10-07","cited_by_count":1,"area":"lr"},{"id":"2603.09556","title":"ALARM: Audio-Language Alignment for Reasoning Models","created":"2026-03-10","cited_by_count":1,"area":"lr"},{"id":"2607.14506","title":"Non-vacuous Generalization Bounds for Reinforcement Learning with Verifiable Rewards","created":"2026-07-16","cited_by_count":1,"area":"lr"},{"id":"2601.17489","title":"SpatialMath: Spatial Comprehension-Infused Symbolic Reasoning for Mathematical Problem-Solving","created":"2026-01-24","cited_by_count":0,"area":"lr"},{"id":"2601.21978","title":"Bridging Graph Structure and Knowledge-Guided Editing for Interpretable Temporal Knowledge Graph Reasoning","created":"2026-01-29","cited_by_count":0,"area":"lr"},{"id":"2604.27850","title":"Reasoning over Object Descriptions Improves Coreference Resolution in Task-Based Dialogue Systems","created":"2026-04-30","cited_by_count":0,"area":"lr"},{"id":"2607.18266","title":"Structured Synthetic Reasoning Data for Arithmetic Fine-Tuning of Small Language Models","created":"2026-05-21","cited_by_count":0,"area":"lr"},{"id":"2608.24574","title":"PhysMLLMs: Spatial Priors for Unified Referring Segmentation and Grounded Reasoning of Images and Videos","created":"2026-08-25","cited_by_count":0,"area":"lr"}],"next_cursor":null}