{"total":111,"rows":[{"id":"2505.10468","title":"AI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and Challenges","created":"2025-05-15","cited_by_count":169,"area":"agents"},{"id":"2505.08638","title":"TRAIL: Trace Reasoning and Agentic Issue Localization","created":"2025-05-13","cited_by_count":104,"area":"lr"},{"id":"2506.07527","title":"Learning What Reinforcement Learning Can't: Interleaved Online Fine-Tuning for Hardest Questions","created":"2025-06-09","cited_by_count":97,"area":"lr"},{"id":"2509.01055","title":"VerlTool: Towards Holistic Agentic Reinforcement Learning with Tool Use","created":"2025-09-01","cited_by_count":96,"area":"lr"},{"id":"2505.17813","title":"Don't Overthink it. Preferring Shorter Thinking Chains for Improved LLM Reasoning","created":"2025-05-23","cited_by_count":85,"area":"lr"},{"id":"2504.17704","title":"Safety in Large Reasoning Models: A Survey","created":"2025-04-24","cited_by_count":64,"area":"lr"},{"id":"2601.03515","title":"Mem-Gallery: Benchmarking Multimodal Long-Term Conversational Memory for MLLM Agents","created":"2026-01-07","cited_by_count":54,"area":"mllm"},{"id":"2506.01300","title":"ReAgent-V: A Reward-Driven Multi-Agent Framework for Video Understanding","created":"2025-06-02","cited_by_count":50,"area":"agents"},{"id":"2601.12538","title":"A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agents","created":"2026-01-18","cited_by_count":50,"area":"lr"},{"id":"2504.15253","title":"Evaluating Judges as Evaluators: The JETTS Benchmark of LLM-as-Judges as Test-Time Scaling Evaluators","created":"2025-04-21","cited_by_count":44,"area":"lr"},{"id":"2505.19443","title":"Vibe Coding vs. Agentic Coding: Fundamentals and Practical Implications of Agentic AI","created":"2025-05-26","cited_by_count":42,"area":"agents"},{"id":"2509.16679","title":"Reinforcement Learning Meets Large Language Models: A Survey of Advancements and Applications Across the LLM Lifecycle","created":"2025-09-20","cited_by_count":35,"area":null},{"id":"2510.25760","title":"Multimodal Spatial Reasoning in the Large Model Era: A Survey and Benchmarks","created":"2025-10-29","cited_by_count":33,"area":"lr"},{"id":"2505.13949","title":"FlashThink: An Early Exit Method For Efficient Reasoning","created":"2025-05-20","cited_by_count":28,"area":"lr"},{"id":"2508.17692","title":"LLM-based Agentic Reasoning Frameworks: A Survey from Methods to Scenarios","created":"2025-08-25","cited_by_count":26,"area":"lr"},{"id":"2510.10991","title":"A Survey on Agentic Multimodal Large Language Models","created":"2025-10-13","cited_by_count":23,"area":"mllm"},{"id":"2602.19672","title":"SkillOrchestra: Learning to Route Agents via Skill Transfer","created":"2026-02-23","cited_by_count":23,"area":null},{"id":"2510.13744","title":"Hard2Verify: A Step-Level Verification Benchmark for Open-Ended Frontier Math","created":"2025-10-15","cited_by_count":22,"area":"lr"},{"id":"2509.11575","title":"A Survey of Reasoning and Agentic Systems in Time Series with Large Language Models","created":"2025-09-15","cited_by_count":21,"area":"lr"},{"id":"2509.17995","title":"Variation in Verification: Understanding Verification Dynamics in Large Language Models","created":"2025-09-22","cited_by_count":19,"area":null},{"id":"2510.01833","title":"Plan Then Action:High-Level Planning Guidance Reinforcement Learning for LLM Reasoning","created":"2025-10-02","cited_by_count":19,"area":"lr"},{"id":"2506.04832","title":"Joint Evaluation of Answer and Reasoning Consistency for Hallucination Detection in Large Reasoning Models","created":"2025-06-05","cited_by_count":14,"area":"lr"},{"id":"2506.15170","title":"From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem","created":"2025-06-18","cited_by_count":12,"area":"agents"},{"id":"2508.02344","title":"Traffic-R1: Reinforced LLMs Bring Human-Like Reasoning to Traffic Signal Control Systems","created":"2025-08-04","cited_by_count":12,"area":"lr"},{"id":"2508.05282","title":"Not All Errors Are Created Equal: ASCoT Addresses Late-Stage Fragility in Efficient LLM Reasoning","created":"2025-08-07","cited_by_count":11,"area":"lr"},{"id":"2509.16742","title":"Sycophancy Mitigation Through Reinforcement Learning with Uncertainty-Aware Adaptive Reasoning Trajectories","created":"2025-09-20","cited_by_count":11,"area":"lr"},{"id":"2505.13346","title":"J4R: Learning to Judge with Equivalent Initial State Group Relative Policy Optimization","created":"2025-05-19","cited_by_count":9,"area":"lr"},{"id":"2506.19846","title":"HiMA-Ecom: Enabling Joint Training of Hierarchical Multi-Agent E-commerce Assistants","created":"2025-06-24","cited_by_count":9,"area":"agents"},{"id":"2508.15842","title":"Lexical Hints of Accuracy in LLM Reasoning Chains","created":"2025-08-19","cited_by_count":9,"area":"lr"},{"id":"2510.10248","title":"Reasoning-Enhanced Large Language Models for Molecular Property Prediction","created":"2025-10-11","cited_by_count":9,"area":"lr"},{"id":"2510.24645","title":"FunReason-MT Technical Report: Advanced Data Synthesis Solution for Real-world Multi-Turn Tool-use","created":"2025-10-28","cited_by_count":9,"area":"lr"},{"id":"2511.06727","title":"S-DAG: A Subject-Based Directed Acyclic Graph for Multi-Agent Heterogeneous Reasoning","created":"2025-11-10","cited_by_count":9,"area":"lr"},{"id":"2606.13003","title":"The Illusion of Multi-Agent Advantage","created":"2026-06-11","cited_by_count":9,"area":null},{"id":"2505.23715","title":"Don't Take the Premise for Granted: Evaluating the Premise Critique Ability of Large Language Models","created":"2025-05-29","cited_by_count":8,"area":"lr"},{"id":"2512.07436","title":"LocalSearchBench: Benchmarking Agentic Search in Real-World Local Life Services","created":"2025-12-08","cited_by_count":8,"area":"lr"},{"id":"2505.17315","title":"Longer Context, Deeper Thinking: Uncovering the Role of Long-Context Ability in Reasoning","created":"2025-05-22","cited_by_count":7,"area":"lr"},{"id":"2506.04723","title":"Beyond Accuracy: Dissecting Mathematical Reasoning for LLMs Under Reinforcement Learning","created":"2025-06-05","cited_by_count":7,"area":"lr"},{"id":"2510.08710","title":"Thinking Longer, Not Always Smarter: Evaluating LLM Capabilities in Hierarchical Legal Reasoning","created":"2025-10-09","cited_by_count":7,"area":"lr"},{"id":"2511.10621","title":"SSR: Socratic Self-Refine for Large Language Model Reasoning","created":"2025-11-13","cited_by_count":7,"area":"lr"},{"id":"2602.01381","title":"On the Power of (Approximate) Reward Models for Inference-Time Scaling","created":"2026-02-01","cited_by_count":7,"area":"lr"},{"id":"2606.23104","title":"ReNIO: Reweighting Negative Trajectory Importance for LLM On-Policy Distillation","created":"2026-06-22","cited_by_count":7,"area":"lr"},{"id":"2608.12307","title":"AI4AI at Test-Time: Strong-to-Weak Capability Transfer via Harnesses","created":"2026-08-12","cited_by_count":7,"area":"distill"},{"id":"2508.16383","title":"GLARE: Agentic Reasoning for Legal Judgment Prediction","created":"2025-08-22","cited_by_count":6,"area":"lr"},{"id":"2603.07432","title":"Generalization in Online Reinforcement Learning for Mobile Agents","created":"2026-03-08","cited_by_count":6,"area":"lr"},{"id":"2510.17793","title":"Foundational Automatic Evaluators: Scaling Multi-Task Generative Evaluator Training for Reasoning-Centric Domains","created":"2025-10-20","cited_by_count":5,"area":null},{"id":"2510.19661","title":"AgentSense: LLMs Empower Generalizable and Explainable Web-Based Participatory Urban Sensing","created":"2025-10-22","cited_by_count":5,"area":null},{"id":"2601.19001","title":"FROST: Filtering Reasoning Outliers with Attention for Efficient Reasoning","created":"2026-01-26","cited_by_count":5,"area":null},{"id":"2603.02119","title":"Pencil Puzzle Bench: A Benchmark for Multi-Step Verifiable Reasoning","created":"2026-03-02","cited_by_count":5,"area":"lr"},{"id":"2605.28120","title":"LegalGraphRAG: Multi-Agent Graph Retrieval-Augmented Generation for Reliable Legal Reasoning","created":"2026-05-27","cited_by_count":5,"area":"lr"},{"id":"2505.09901","title":"Comparing Exploration-Exploitation Strategies of LLMs and Humans: Insights from Standard Multi-armed Bandit Experiments","created":"2025-05-15","cited_by_count":4,"area":null},{"id":"2510.14703","title":"ToolPRM: Fine-Grained Inference Scaling of Structured Outputs for Function Calling","created":"2025-10-16","cited_by_count":4,"area":"agents"},{"id":"2510.22860","title":"Far from the Shallow: Brain-Predictive Reasoning Embedding through Residual Disentanglement","created":"2025-10-26","cited_by_count":4,"area":"lr"},{"id":"2512.01925","title":"Rectifying LLM Thought from Lens of Optimization","created":"2025-12-01","cited_by_count":4,"area":"lr"},{"id":"2602.01523","title":"A Relative-Budget Theory for Reinforcement Learning with Verifiable Rewards in Large Language Model Reasoning","created":"2026-02-02","cited_by_count":4,"area":"lr"},{"id":"2603.08743","title":"Zipage: Maintain High Request Concurrency for LLM Reasoning through Compressed PagedAttention","created":"2026-03-01","cited_by_count":4,"area":"lr"},{"id":"2603.23607","title":"Reasoning models do not yet follow their reasoning in autonomous driving: The KITScenes LongTail Dataset","created":"2026-03-24","cited_by_count":4,"area":"lr"},{"id":"2609.04280","title":"EvoHarnessBench: Can Your Agents Keep Pace with an Evolving Harness?","created":"2026-09-03","cited_by_count":4,"area":"agents"},{"id":"2505.19764","title":"Multi-View Encoders for Performance Prediction in LLM-Based Agentic Workflows","created":"2025-05-26","cited_by_count":3,"area":"agents"},{"id":"2506.07820","title":"Guideline Forest: Retrieval-Augmented Reasoning with Branching Experience-Induced Guidelines","created":"2025-06-09","cited_by_count":3,"area":"lr"},{"id":"2506.22376","title":"OptScale: Probabilistic Optimality for Inference-time Scaling","created":"2025-06-27","cited_by_count":3,"area":"lr"},{"id":"2509.13332","title":"Explicit Reasoning Makes Better Judges: A Systematic Study on Accuracy, Efficiency, and Robustness","created":"2025-09-09","cited_by_count":3,"area":"lr"},{"id":"2509.24922","title":"MASLegalBench: Benchmarking Multi-Agent Systems in Deductive Legal Reasoning","created":"2025-09-29","cited_by_count":3,"area":"lr"},{"id":"2510.07896","title":"ACE: Attribution-Controlled Knowledge Editing for Multi-hop Factual Recall","created":"2025-10-09","cited_by_count":3,"area":null},{"id":"2510.27251","title":"FinPos: A Position-Aware Trading Agent System for Real Financial Markets","created":"2025-10-31","cited_by_count":3,"area":"agents"},{"id":"2512.00163","title":"Measuring What LLMs Think They Do: SHAP Faithfulness and Deployability on Financial Tabular Classification","created":"2025-11-28","cited_by_count":3,"area":"lr"},{"id":"2603.13985","title":"Supervised Fine-Tuning versus Reinforcement Learning: A Study of Post-Training Methods for Large Language Models","created":"2026-03-14","cited_by_count":3,"area":null},{"id":"2603.20260","title":"ProMAS: Proactive Error Forecasting for Multi-Agent Systems Using Markov Transition Dynamics","created":"2026-03-12","cited_by_count":3,"area":"agents"},{"id":"2604.07851","title":"ReRec: Reasoning-Augmented LLM-based Recommendation Assistant via Reinforcement Fine-tuning","created":"2026-04-09","cited_by_count":3,"area":"lr"},{"id":"2604.16778","title":"Federation over Text: Insight Sharing for Multi-Agent Reasoning","created":"2026-04-18","cited_by_count":3,"area":"lr"},{"id":"2605.28069","title":"ZipRL: Adaptive Multi-Turn Context Compression with Hindsight Response Replay","created":"2026-05-27","cited_by_count":3,"area":"inference"},{"id":"2505.21191","title":"Unveiling Instruction-Specific Neurons & Experts: An Analytical Framework for LLM's Instruction-Following Capabilities","created":"2025-05-27","cited_by_count":2,"area":"moe"},{"id":"2506.05370","title":"Contextual Memory Intelligence -- A Foundational Paradigm for Human-AI Collaboration and Reflective Generative AI Systems","created":"2025-05-28","cited_by_count":2,"area":null},{"id":"2507.08584","title":"To Trade or Not to Trade: An Agentic Approach to Estimating Market Risk Improves Trading Decisions","created":"2025-07-11","cited_by_count":2,"area":"agents"},{"id":"2510.03231","title":"Reward Models are Metrics in a Trench Coat","created":"2025-10-03","cited_by_count":2,"area":"alignment"},{"id":"2510.17491","title":"Empowering Real-World: A Survey on the Technology, Practice, and Evaluation of LLM-driven Industry Agents","created":"2025-10-20","cited_by_count":2,"area":"lr"},{"id":"2603.17305","title":"Contrastive Reasoning Alignment: Reinforcement Learning from Hidden Representations","created":"2026-03-18","cited_by_count":2,"area":"lr"},{"id":"2606.13598","title":"Reward Modeling for Multi-Agent Orchestration","created":"2026-06-11","cited_by_count":2,"area":"lr"},{"id":"2511.13095","title":"BeDiscovER: The Benchmark of Discourse Understanding in the Era of Reasoning Language Models","created":"2025-11-17","cited_by_count":1,"area":"lr"},{"id":"2603.18469","title":"GAIN: A Benchmark for Goal-Aligned Decision-Making of Large Language Models under Imperfect Norms","created":"2026-03-19","cited_by_count":1,"area":null},{"id":"2603.22528","title":"GraphRAG for Engineering Diagrams: ChatP&ID Enables LLM Interaction with P&IDs","created":"2026-03-23","cited_by_count":1,"area":"rag"},{"id":"2604.15972","title":"Weak-Link Optimization for Multi-Agent Reasoning and Collaboration","created":"2026-04-17","cited_by_count":1,"area":"lr"},{"id":"2605.26178","title":"ATOM: Instantiating Budget-Controllable Multi-Agent Collaboration via Nucleus-Electron Hierarchy","created":"2026-05-25","cited_by_count":1,"area":"agents"},{"id":"2606.09484","title":"Detecting Differences Is Not Understanding Structure: Large Language Models Fail at Graph Isomorphism","created":"2026-06-08","cited_by_count":1,"area":null},{"id":"2609.10177","title":"Beyond Surface Imitation: Contrastive Modeling for Reasoning Path Alignment in Multimodal In-Context Learning","created":"2026-09-09","cited_by_count":1,"area":"lr"},{"id":"2609.15054","title":"BusMA: A Bus Communication Substrate for Multi-Agent Systems","created":"2026-09-14","cited_by_count":1,"area":"agents"},{"id":"2510.05746","title":"ARM: Discovering Agentic Reasoning Modules for Generalizable Multi-Agent Systems","created":"2025-10-07","cited_by_count":0,"area":"lr"},{"id":"2510.07173","title":"NurseLLM: The First Specialized Language Model for Nursing","created":"2025-10-08","cited_by_count":0,"area":null},{"id":"2510.11652","title":"ACADREASON: Exploring the Limits of Reasoning Models with Academic Research Problems","created":"2025-10-13","cited_by_count":0,"area":"lr"},{"id":"2510.18095","title":"SMaRT: Select, Mix, and ReinvenT -- A Strategy Fusion Framework for LLM-Driven Reasoning and Planning","created":"2025-10-20","cited_by_count":0,"area":"lr"},{"id":"2512.08169","title":"Information-Dense Reasoning for Efficient and Auditable Security Alert Triage","created":"2025-12-09","cited_by_count":0,"area":"lr"},{"id":"2512.18020","title":"Specification and Detection of LLM Code Smells","created":"2025-12-19","cited_by_count":0,"area":null},{"id":"2602.08586","title":"DIANOIA: Diagnostic Decomposition and Joint Optimization for Multi-Agent Reasoning","created":"2026-02-09","cited_by_count":0,"area":"lr"},{"id":"2604.06501","title":"Transformer See, Transformer Do: Copying as an Intermediate Step in Learning Analogical Reasoning","created":"2026-04-07","cited_by_count":0,"area":"lr"},{"id":"2604.08563","title":"Temperature-Dependent Performance of Prompting Strategies in Extended Reasoning Large Language Models","created":"2026-03-18","cited_by_count":0,"area":"lr"},{"id":"2604.09553","title":"SRBench: A Comprehensive Benchmark for Sequential Recommendation with Large Language Models","created":"2026-01-31","cited_by_count":0,"area":null},{"id":"2604.11912","title":"How Transformers Learn to Plan via Multi-Token Prediction","created":"2026-04-13","cited_by_count":0,"area":null},{"id":"2605.08516","title":"OracleTSC: Oracle-Informed Reward Hurdle and Uncertainty Regularization for Traffic Signal Control","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2605.13848","title":"GraphBit: A Graph-based Agentic Framework for Non-Linear Agent Orchestration","created":"2026-03-08","cited_by_count":0,"area":"agents"},{"id":"2605.15012","title":"Boosting Reinforcement Learning with Verifiable Rewards via Randomly Selected Few-Shot Guidance","created":"2026-05-14","cited_by_count":0,"area":"lr"},{"id":"2605.22976","title":"LLM Code Smells: A Taxonomy and Detection Approach","created":"2026-05-21","cited_by_count":0,"area":null}],"next_cursor":"100"}