{"total":97,"rows":[{"id":"2508.06471","title":"GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models","created":"2025-08-08","cited_by_count":467,"area":"lr"},{"id":"2506.13585","title":"MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention","created":"2025-06-16","cited_by_count":263,"area":"lr"},{"id":"2507.02592","title":"WebSailor: Navigating Super-human Reasoning for Web Agent","created":"2025-07-03","cited_by_count":229,"area":"lr"},{"id":"2507.16806","title":"Beyond Binary Rewards: Training LMs to Reason About Their Uncertainty","created":"2025-07-22","cited_by_count":117,"area":"lr"},{"id":"2505.11896","title":"AdaCoT: Pareto-Optimal Adaptive Chain-of-Thought Triggering via Reinforcement Learning","created":"2025-05-17","cited_by_count":87,"area":"lr"},{"id":"2502.02384","title":"STAIR: Improving Safety Alignment with Introspective Reasoning","created":"2025-02-04","cited_by_count":77,"area":"lr"},{"id":"2506.01062","title":"SealQA: Raising the Bar for Reasoning in Search-Augmented Language Models","created":"2025-06-01","cited_by_count":75,"area":"lr"},{"id":"2505.23646","title":"Are Reasoning Models More Prone to Hallucination?","created":"2025-05-29","cited_by_count":64,"area":"lr"},{"id":"2501.18841","title":"Trading Inference-Time Compute for Adversarial Robustness","created":"2025-01-31","cited_by_count":61,"area":"lr"},{"id":"2505.16834","title":"SimpleDeepSearcher: Deep Information Seeking via Web-Powered Reasoning Trajectory Synthesis","created":"2025-05-22","cited_by_count":55,"area":"lr"},{"id":"2503.20201","title":"Open Deep Search: Democratizing Search with Open-source Reasoning Agents","created":"2025-03-26","cited_by_count":49,"area":"lr"},{"id":"2505.15117","title":"An Empirical Study on Reinforcement Learning for Reasoning-Search Interleaved LLM Agents","created":"2025-05-21","cited_by_count":46,"area":"lr"},{"id":"2506.18183","title":"Reasoning about Uncertainty: Do Reasoning Models Know When They Don't Know?","created":"2025-06-22","cited_by_count":38,"area":"lr"},{"id":"2511.02805","title":"MemSearcher: Training LLMs to Reason, Search and Manage Memory via End-to-End Reinforcement Learning","created":"2025-11-04","cited_by_count":27,"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":"2509.03871","title":"A Comprehensive Survey on Trustworthiness in Reasoning with Large Language Models","created":"2025-09-04","cited_by_count":25,"area":"lr"},{"id":"2502.12272","title":"Learning to Reason at the Frontier of Learnability","created":"2025-02-17","cited_by_count":23,"area":"lr"},{"id":"2505.24332","title":"DeepDiver: Adaptive Search Intensity Scaling via Open-Web Reinforcement Learning","created":"2025-05-30","cited_by_count":23,"area":"lr"},{"id":"2508.11133","title":"MoNaCo: More Natural and Complex Questions for Reasoning Across Dozens of Documents","created":"2025-08-15","cited_by_count":21,"area":"lr"},{"id":"2512.25070","title":"Scaling Open-Ended Reasoning to Predict the Future","created":"2025-12-31","cited_by_count":21,"area":"lr"},{"id":"2507.09662","title":"Towards Concise and Adaptive Thinking in Large Reasoning Models: A Survey","created":"2025-07-13","cited_by_count":18,"area":"lr"},{"id":"2502.13962","title":"Is That Your Final Answer? Test-Time Scaling Improves Selective Question Answering","created":"2025-02-19","cited_by_count":17,"area":"lr"},{"id":"2502.20432","title":"LLM Strategic Reasoning: Agentic Study through Behavioral Game Theory","created":"2025-02-27","cited_by_count":17,"area":"lr"},{"id":"2505.20013","title":"WebCoT: Enhancing Web Agent Reasoning by Reconstructing Chain-of-Thought in Reflection, Branching, and Rollback","created":"2025-05-26","cited_by_count":17,"area":"lr"},{"id":"2603.09906","title":"Thinking to Recall: How Reasoning Unlocks Parametric Knowledge in LLMs","created":"2026-03-10","cited_by_count":16,"area":"lr"},{"id":"2508.10874","title":"SSRL: Self-Search Reinforcement Learning","created":"2025-08-14","cited_by_count":14,"area":"lr"},{"id":"2509.06733","title":"Reinforcement Learning Foundations for Deep Research Systems: A Survey","created":"2025-09-08","cited_by_count":14,"area":"lr"},{"id":"2504.06564","title":"Thinking Out Loud: Do Reasoning Models Know When They're Right?","created":"2025-04-09","cited_by_count":12,"area":"lr"},{"id":"2507.14683","title":"MiroMind-M1: An Open-Source Advancement in Mathematical Reasoning via Context-Aware Multi-Stage Policy Optimization","created":"2025-07-19","cited_by_count":12,"area":"lr"},{"id":"2509.06861","title":"Test-Time Scaling in Reasoning Models Is Not Effective for Knowledge-Intensive Tasks Yet","created":"2025-09-08","cited_by_count":11,"area":"lr"},{"id":"2509.24393","title":"Towards Safe Reasoning in Large Reasoning Models via Corrective Intervention","created":"2025-09-29","cited_by_count":11,"area":"lr"},{"id":"2505.23845","title":"Read Your Own Mind: Reasoning Helps Surface Self-Confidence Signals in LLMs","created":"2025-05-28","cited_by_count":10,"area":"lr"},{"id":"2506.19467","title":"Can Reasoning Help Large Language Models Capture Human Annotator Disagreement?","created":"2025-06-24","cited_by_count":10,"area":"lr"},{"id":"2509.24967","title":"SecInfer: Preventing Prompt Injection via Inference-time Scaling","created":"2025-09-29","cited_by_count":10,"area":"lr"},{"id":"2510.07880","title":"Do LLMs Really Need 10+ Thoughts for \"Find the Time 1000 Days Later\"? Towards Structural Understanding of LLM Overthinking","created":"2025-10-09","cited_by_count":10,"area":"lr"},{"id":"2604.17112","title":"Complementing Self-Consistency with Cross-Model Disagreement for Uncertainty Quantification","created":"2026-04-18","cited_by_count":10,"area":"lr"},{"id":"2508.03058","title":"VRPO: Rethinking Value Modeling for Robust RL under Noisy Supervision in LLM Post-Training","created":"2025-08-05","cited_by_count":9,"area":"lr"},{"id":"2508.15842","title":"Lexical Hints of Accuracy in LLM Reasoning Chains","created":"2025-08-19","cited_by_count":9,"area":"lr"},{"id":"2505.13529","title":"BARREL: Boundary-Aware Reasoning for Factual and Reliable LRMs","created":"2025-05-18","cited_by_count":8,"area":"lr"},{"id":"2508.18255","title":"Hermes 4 Technical Report","created":"2025-08-25","cited_by_count":8,"area":"lr"},{"id":"2509.08814","title":"Merge-of-Thought Distillation","created":"2025-09-10","cited_by_count":7,"area":"lr"},{"id":"2510.00177","title":"PrefDisco: Benchmarking Proactive Personalized Reasoning","created":"2025-09-30","cited_by_count":7,"area":"lr"},{"id":"2510.18798","title":"WebSeer: Training Deeper Search Agents through Reinforcement Learning with Self-Reflection","created":"2025-10-21","cited_by_count":7,"area":"lr"},{"id":"2511.01365","title":"The Ouroboros of Benchmarking: Reasoning Evaluation in an Era of Saturation","created":"2025-11-03","cited_by_count":7,"area":"lr"},{"id":"2511.05784","title":"DRAGON: Guard LLM Unlearning in Context via Negative Detection and Reasoning","created":"2025-11-08","cited_by_count":7,"area":"lr"},{"id":"2601.23163","title":"Probing the Trajectories of Reasoning Traces in Large Language Models","created":"2026-01-30","cited_by_count":7,"area":"lr"},{"id":"2604.04503","title":"Memory Intelligence Agent","created":"2026-04-06","cited_by_count":7,"area":"lr"},{"id":"2504.02670","title":"Affordable AI Assistants with Knowledge Graph of Thoughts","created":"2025-04-03","cited_by_count":6,"area":"lr"},{"id":"2505.16088","title":"Date Fragments: A Hidden Bottleneck of Tokenization for Temporal Reasoning","created":"2025-05-22","cited_by_count":6,"area":"lr"},{"id":"2509.24285","title":"SCI-Verifier: Scientific Verifier with Thinking","created":"2025-09-29","cited_by_count":6,"area":"lr"},{"id":"2606.15079","title":"Ling and Ring 2.6 Technical Report: Efficient and Instant Agentic Intelligence at Trillion-Parameter Scale","created":"2026-06-13","cited_by_count":6,"area":"lr"},{"id":"2508.06361","title":"Beyond Prompt-Induced Lies: Investigating LLM Deception on Benign Prompts","created":"2025-08-08","cited_by_count":5,"area":"lr"},{"id":"2510.09275","title":"Inflated Excellence or True Performance? Rethinking Medical Diagnostic Benchmarks with Dynamic Evaluation","created":"2025-10-10","cited_by_count":5,"area":"lr"},{"id":"2602.22193","title":"Improving Parametric Knowledge Access in Reasoning Language Models","created":"2026-02-25","cited_by_count":5,"area":"lr"},{"id":"2608.31075","title":"Scaling Large Reasoning Models beyond Human Supervision: A Path toward Superintelligence","created":"2026-08-31","cited_by_count":5,"area":"lr"},{"id":"2504.02725","title":"SAFER: Advancing Safety Alignment via Efficient Ex-Ante Reasoning","created":"2025-04-03","cited_by_count":4,"area":"lr"},{"id":"2505.13498","title":"IRLBench: A Multi-modal, Culturally Grounded, Parallel Irish-English Benchmark for Open-Ended LLM Reasoning Evaluation","created":"2025-05-16","cited_by_count":4,"area":"lr"},{"id":"2507.09751","title":"Sound and Complete Neurosymbolic Reasoning with LLM-Grounded Interpretations","created":"2025-07-13","cited_by_count":4,"area":"lr"},{"id":"2510.14773","title":"Finding Answers in Thought Matters: Revisiting Evaluation on Large Language Models with Reasoning","created":"2025-10-16","cited_by_count":4,"area":"lr"},{"id":"2510.24794","title":"MR-Align: Meta-Reasoning Informed Factuality Alignment for Large Reasoning Models","created":"2025-10-27","cited_by_count":4,"area":"lr"},{"id":"2601.22323","title":"Models Under SCOPE: Scalable and Controllable Routing via Pre-hoc Reasoning","created":"2026-01-29","cited_by_count":4,"area":"lr"},{"id":"2604.16909","title":"PRISM: Probing Reasoning, Instruction, and Source Memory in LLM Hallucinations","created":"2026-04-18","cited_by_count":4,"area":"lr"},{"id":"2605.07153","title":"Beyond Reasoning: Reinforcement Learning Unlocks Parametric Knowledge in LLMs","created":"2026-05-08","cited_by_count":4,"area":"lr"},{"id":"2605.29648","title":"Beyond Math and Code: Lightweight Corpus-Grounded Process Rewards for Factual Question Answering","created":"2026-05-28","cited_by_count":4,"area":"lr"},{"id":"2503.06218","title":"SCoRE: Benchmarking Long-Chain Reasoning in Commonsense Scenarios","created":"2025-03-08","cited_by_count":3,"area":"lr"},{"id":"2511.01409","title":"LiveSearchBench: An Automatically Constructed Benchmark for Retrieval and Reasoning over Dynamic Knowledge","created":"2025-11-03","cited_by_count":3,"area":"lr"},{"id":"2604.05404","title":"Beyond Accuracy: Unveiling Inefficiency Patterns in Tool-Integrated Reasoning","created":"2026-04-07","cited_by_count":3,"area":"lr"},{"id":"2607.05861","title":"Mitigating Factual Hallucination in Large Reasoning Models via Mixed-Mode Advantage Regularization","created":"2026-07-07","cited_by_count":3,"area":"lr"},{"id":"2511.07397","title":"Thinking While Speaking: Inference-Time Knowledge Transfer for Responsive and Intelligent Conversational Voice Agents","created":"2025-11-10","cited_by_count":2,"area":"lr"},{"id":"2602.19517","title":"Classroom Final Exam: An Instructor-Tested Reasoning Benchmark","created":"2026-02-23","cited_by_count":2,"area":"lr"},{"id":"2603.19539","title":"FDARxBench: Benchmarking Regulatory and Clinical Reasoning on FDA Generic Drug Assessment","created":"2026-03-20","cited_by_count":2,"area":"lr"},{"id":"2505.11140","title":"Follow the Path: Reasoning over Knowledge Graph Paths to Improve Large Language Model Factuality","created":"2025-05-16","cited_by_count":1,"area":"lr"},{"id":"2507.18857","title":"PrismRAG: Boosting RAG Factuality with Distractor Resilience and Strategized Reasoning","created":"2025-07-25","cited_by_count":1,"area":"lr"},{"id":"2509.17177","title":"FlagEval Findings Report: A Preliminary Evaluation of Large Reasoning Models on Automatically Verifiable Textual and Visual Questions","created":"2025-09-21","cited_by_count":1,"area":"lr"},{"id":"2510.18368","title":"KoSimpleQA: A Korean Factuality Benchmark with an Analysis of Reasoning LLMs","created":"2025-10-21","cited_by_count":1,"area":"lr"},{"id":"2601.08282","title":"D$^2$Plan: Dual-Agent Dynamic Global Planning for Complex Retrieval-Augmented Reasoning","created":"2026-01-13","cited_by_count":1,"area":"lr"},{"id":"2602.19063","title":"Direction-aware 3D Large Multimodal Models","created":"2026-02-22","cited_by_count":1,"area":"lr"},{"id":"2606.18947","title":"Decoupling Search from Reasoning: A Vendor-Agnostic Grounding Architecture for LLM Agents","created":"2026-06-17","cited_by_count":1,"area":"lr"},{"id":"2606.24281","title":"CALIBER: Calibrating Confidence Before and After Reasoning in Language Models","created":"2026-06-23","cited_by_count":1,"area":"lr"},{"id":"2607.00447","title":"Understanding Why Language Models Hallucinate: Testing Reasoning Against Priors","created":"2026-07-01","cited_by_count":1,"area":"lr"},{"id":"2607.19367","title":"Rethinking Uncertainty Evaluation in Large Language Models","created":"2026-06-11","cited_by_count":1,"area":"lr"},{"id":"2509.22876","title":"HEART: Emotionally-Driven Test-Time Scaling of Language Models","created":"2025-09-26","cited_by_count":0,"area":"lr"},{"id":"2509.23730","title":"EAPO: Enhancing Policy Optimization with On-Demand Expert Assistance","created":"2025-09-28","cited_by_count":0,"area":"lr"},{"id":"2512.08944","title":"Enhancing Reliability across Short and Long-Form QA via Reinforcement Learning","created":"2025-11-19","cited_by_count":0,"area":"lr"},{"id":"2603.26846","title":"Stable Reasoning, Unstable Responses: Mitigating LLM Deception via Stability Asymmetry","created":"2026-03-27","cited_by_count":0,"area":"lr"},{"id":"2604.01430","title":"Improving Latent Generalization Using Test-time Compute","created":"2026-04-01","cited_by_count":0,"area":"lr"},{"id":"2605.09544","title":"TIDE-Bench: Task-Aware and Diagnostic Evaluation of Tool-Integrated Reasoning","created":"2026-05-10","cited_by_count":0,"area":"lr"},{"id":"2605.15102","title":"Improving Multi-turn Dialogue Consistency with Self-Recall Thinking","created":"2026-05-14","cited_by_count":0,"area":"lr"},{"id":"2607.02262","title":"CheckRLM: Effective Knowledge-Thought Coherence Checking in Retrieval-Augmented Reasoning","created":"2026-07-02","cited_by_count":0,"area":"lr"},{"id":"2609.01532","title":"Knowledge Distillation During Mid-Training Favors Reasoning over Factual Recall","created":"2026-09-01","cited_by_count":0,"area":"lr"},{"id":"2609.17686","title":"The Missing \"I Don't Know\": Why Three Reasoning-Reliability Findings Converge on Calibrated Abstention","created":"2026-09-15","cited_by_count":0,"area":"lr"},{"id":"2609.33290","title":"Calibration, Not Answer Selection: Distilling Internal Confidence in Reasoning Models","created":"2026-09-27","cited_by_count":0,"area":"lr"},{"id":"2609.34454","title":"When Words Fall Short: Iterative Synergy Between Verbalized Reasoning and Hidden Features for LLM Confidence Estimation","created":"2026-09-28","cited_by_count":0,"area":"lr"},{"id":"2609.37169","title":"Trajectory Soup: Pushing the Compute-Scaling Frontier of LLM Mid-training via Diverse Trajectories","created":"2026-09-29","cited_by_count":0,"area":"lr"},{"id":"2610.02695","title":"Test-time Calibration Learning for Large Language Model Reasoning","created":"2026-10-02","cited_by_count":0,"area":"lr"},{"id":"2610.11352","title":"RL-ARC: Calibrating Large Reasoning Models via Reasoning-guided Uncertainty","created":"2026-10-08","cited_by_count":0,"area":"lr"},{"id":"2610.20012","title":"ChemArgus: Automated Scientific Diagnostics for Lab-Grade Multimodal Chemistry Reasoning: A Frontier Benchmark","created":"2026-10-14","cited_by_count":0,"area":"lr"}],"next_cursor":null}