{"total":33,"rows":[{"id":"2503.09567","title":"Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models","created":"2025-03-12","cited_by_count":384,"area":"lr"},{"id":"2505.01441","title":"Agentic Reasoning and Tool Integration for LLMs via Reinforcement Learning","created":"2025-04-28","cited_by_count":110,"area":"lr"},{"id":"2505.15107","title":"StepSearch: Igniting LLMs Search Ability via Step-Wise Proximal Policy Optimization","created":"2025-05-21","cited_by_count":88,"area":"lr"},{"id":"2502.17638","title":"Towards Robust Legal Reasoning: Harnessing Logical LLMs in Law","created":"2025-02-24","cited_by_count":30,"area":"lr"},{"id":"2503.17726","title":"A Survey on Mathematical Reasoning and Optimization with Large Language Models","created":"2025-03-22","cited_by_count":12,"area":"lr"},{"id":"2505.20948","title":"Controllable Logical Hypothesis Generation for Abductive Reasoning in Knowledge Graphs","created":"2025-05-27","cited_by_count":11,"area":"lr"},{"id":"2502.11137","title":"Safety Evaluation of DeepSeek Models in Chinese Contexts","created":"2025-02-16","cited_by_count":9,"area":"lr"},{"id":"2502.12486","title":"EPO: Explicit Policy Optimization for Strategic Reasoning in LLMs via Reinforcement Learning","created":"2025-02-18","cited_by_count":8,"area":"lr"},{"id":"2510.19791","title":"ToolDreamer: Instilling LLM Reasoning Into Tool Retrievers","created":"2025-10-22","cited_by_count":7,"area":"lr"},{"id":"2603.09980","title":"Explainable LLM Unlearning Through Reasoning","created":"2026-02-08","cited_by_count":7,"area":"lr"},{"id":"2511.00640","title":"DTS: Enhancing Large Reasoning Models via Decoding Tree Sketching","created":"2025-11-01","cited_by_count":6,"area":"lr"},{"id":"2503.10095","title":"Cognitive-Mental-LLM: Evaluating Reasoning in Large Language Models for Mental Health Prediction via Online Text","created":"2025-03-13","cited_by_count":5,"area":"lr"},{"id":"2504.05632","title":"Reasoning Towards Fairness: Mitigating Bias in Language Models through Reasoning-Guided Fine-Tuning","created":"2025-04-08","cited_by_count":5,"area":"lr"},{"id":"2508.03159","title":"CoTox: Chain-of-Thought-Based Molecular Toxicity Reasoning and Prediction","created":"2025-08-05","cited_by_count":5,"area":"lr"},{"id":"2503.16529","title":"Safety Evaluation and Enhancement of DeepSeek Models in Chinese Contexts","created":"2025-03-18","cited_by_count":4,"area":"lr"},{"id":"2505.24225","title":"Reasoning Can Hurt the Inductive Abilities of Large Language Models","created":"2025-05-30","cited_by_count":4,"area":"lr"},{"id":"2509.05226","title":"Less is More Tokens: Efficient Math Reasoning via Difficulty-Aware Chain-of-Thought Distillation","created":"2025-09-05","cited_by_count":4,"area":"lr"},{"id":"2509.24269","title":"AdvChain: Adversarial Chain-of-Thought Tuning for Robust Safety Alignment of Large Reasoning Models","created":"2025-09-29","cited_by_count":4,"area":"lr"},{"id":"2605.21851","title":"OPPO: Bayesian Value Recursion for Token-Level Credit Assignment in LLM Reasoning","created":"2026-05-21","cited_by_count":4,"area":"lr"},{"id":"2606.18844","title":"Learning from Your Own Mistakes: Constructing Learnable Micro-Reflective Trajectories for Self-Distillation","created":"2026-06-17","cited_by_count":4,"area":"lr"},{"id":"2504.16414","title":"Evaluating Multi-Hop Reasoning in Large Language Models: A Chemistry-Centric Case Study","created":"2025-04-23","cited_by_count":3,"area":"lr"},{"id":"2511.00389","title":"Rethinking Facial Expression Recognition in the Era of Multimodal Large Language Models: Benchmark, Datasets, and Beyond","created":"2025-11-01","cited_by_count":3,"area":"lr"},{"id":"2510.07790","title":"GCPO: When Contrast Fails, Go Gold","created":"2025-10-09","cited_by_count":2,"area":"lr"},{"id":"2505.16806","title":"Two-way Evidence self-Alignment based Dual-Gated Reasoning Enhancement","created":"2025-05-22","cited_by_count":1,"area":"lr"},{"id":"2604.25419","title":"JURY-RL: Votes Propose, Proofs Dispose for Label-Free RLVR","created":"2026-04-28","cited_by_count":1,"area":"lr"},{"id":"2512.02246","title":"DETAIL Matters: Measuring the Impact of Prompt Specificity on Reasoning in Large Language Models","created":"2025-12-01","cited_by_count":0,"area":"lr"},{"id":"2512.04254","title":"Hey GPT-OSS, Looks Like You Got It -- Now Walk Me Through It! An Assessment of the Reasoning Language Models Chain of Thought Mechanism for Digital Forensics","created":"2025-12-03","cited_by_count":0,"area":"lr"},{"id":"2601.11322","title":"Enhancing Vision Language Models with Logic Reasoning for Situational Awareness","created":"2026-01-16","cited_by_count":0,"area":"lr"},{"id":"2603.27008","title":"RASPRef: Retrieval-Augmented Self-Supervised Prompt Refinement for Large Reasoning Models","created":"2026-03-27","cited_by_count":0,"area":"lr"},{"id":"2604.15725","title":"Reasoning-targeted Jailbreak Attacks on Large Reasoning Models via Semantic Triggers and Psychological Framing","created":"2026-04-17","cited_by_count":0,"area":"lr"},{"id":"2604.21479","title":"Frozen LLMs as Map-Aware Spatio-Temporal Reasoners for Vehicle Trajectory Prediction","created":"2026-04-23","cited_by_count":0,"area":"lr"},{"id":"2605.09853","title":"Exploration-Driven Optimization for Test-Time Large Language Model Reasoning","created":"2026-05-11","cited_by_count":0,"area":"lr"},{"id":"2608.26836","title":"SymbolLKG: Towards Verifiable Logical Reasoning via Logical Knowledge Graph and Symbolic Solvers","created":"2026-08-27","cited_by_count":0,"area":"lr"}],"next_cursor":null}