{"total":164,"rows":[{"id":"2504.13837","title":"Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?","created":"2025-04-18","cited_by_count":982,"area":"lr"},{"id":"2507.02259","title":"MemAgent: Reshaping Long-Context LLM with Multi-Conv RL-based Memory Agent","created":"2025-07-03","cited_by_count":246,"area":"lr"},{"id":"2510.14276","title":"Qwen3Guard Technical Report","created":"2025-10-16","cited_by_count":155,"area":"safety"},{"id":"2505.18079","title":"Deep Video Discovery: Agentic Search with Tool Use for Long-form Video Understanding","created":"2025-05-23","cited_by_count":98,"area":"agents"},{"id":"2505.23416","title":"KVzip: Query-Agnostic KV Cache Compression with Context Reconstruction","created":"2025-05-29","cited_by_count":95,"area":"inference"},{"id":"2602.22769","title":"AMA-Bench: Evaluating Long-Horizon Memory for Agentic Applications","created":"2026-02-26","cited_by_count":53,"area":"agents"},{"id":"2502.02770","title":"Twilight: Adaptive Attention Sparsity with Hierarchical Top-$p$ Pruning","created":"2025-02-04","cited_by_count":49,"area":null},{"id":"2505.12448","title":"SSR: Enhancing Depth Perception in Vision-Language Models via Rationale-Guided Spatial Reasoning","created":"2025-05-18","cited_by_count":46,"area":"lr"},{"id":"2509.23040","title":"Look Back to Reason Forward: Revisitable Memory for Long-Context LLM Agents","created":"2025-09-27","cited_by_count":38,"area":"lr"},{"id":"2509.24372","title":"Evolution Strategies at Scale: LLM Fine-Tuning Beyond Reinforcement Learning","created":"2025-09-29","cited_by_count":34,"area":null},{"id":"2509.24765","title":"Semantic-Aware Logical Reasoning via a Semiotic Framework","created":"2025-09-29","cited_by_count":32,"area":"lr"},{"id":"2604.17535","title":"OPSDL: On-Policy Self-Distillation for Long-Context Language Models","created":"2026-04-19","cited_by_count":30,"area":"distill"},{"id":"2601.02902","title":"Logical Phase Transitions: Understanding Collapse in LLM Logical Reasoning","created":"2026-01-06","cited_by_count":25,"area":"lr"},{"id":"2505.23380","title":"UniRL: Self-Improving Unified Multimodal Models via Supervised and Reinforcement Learning","created":"2025-05-29","cited_by_count":24,"area":"mllm"},{"id":"2510.06826","title":"Mid-Training of Large Language Models: A Survey","created":"2025-10-08","cited_by_count":21,"area":null},{"id":"2504.08719","title":"SWAN-GPT: An Efficient and Scalable Approach for Long-Context Language Modeling","created":"2025-04-11","cited_by_count":19,"area":null},{"id":"2601.07408","title":"Outcome-Grounded Advantage Reshaping for Fine-Grained Credit Assignment in Mathematical Reasoning","created":"2026-01-12","cited_by_count":19,"area":"lr"},{"id":"2503.22048","title":"ThinkEdit: Interpretable Weight Editing to Mitigate Overly Short Thinking in Reasoning Models","created":"2025-03-27","cited_by_count":17,"area":"lr"},{"id":"2510.10129","title":"CacheClip: Accelerating RAG with Effective KV Cache Reuse","created":"2025-10-11","cited_by_count":16,"area":"rag"},{"id":"2601.17668","title":"Fast KVzip: Efficient and Accurate LLM Inference with Gated KV Eviction","created":"2026-01-25","cited_by_count":16,"area":"inference"},{"id":"2503.19693","title":"AdaptiVocab: Enhancing LLM Efficiency in Focused Domains through Lightweight Vocabulary Adaptation","created":"2025-03-25","cited_by_count":15,"area":null},{"id":"2601.21468","title":"MemOCR: Layout-Aware Visual Memory for Efficient Long-Horizon Reasoning","created":"2026-01-29","cited_by_count":15,"area":"agents"},{"id":"2502.14317","title":"ParallelComp: Parallel Long-Context Compressor for Length Extrapolation","created":"2025-02-20","cited_by_count":14,"area":"inference"},{"id":"2504.06214","title":"From 128K to 4M: Efficient Training of Ultra-Long Context Large Language Models","created":"2025-04-08","cited_by_count":14,"area":"lr"},{"id":"2505.24164","title":"Mixed-R1: Unified Reward Perspective For Reasoning Capability in Multimodal Large Language Models","created":"2025-05-30","cited_by_count":13,"area":"lr"},{"id":"2601.03023","title":"MedDialogRubrics: A Comprehensive Benchmark and Evaluation Framework for Multi-turn Medical Consultations in Large Language Models","created":"2026-01-06","cited_by_count":12,"area":null},{"id":"2509.18849","title":"MAPO: Mixed Advantage Policy Optimization","created":"2025-09-23","cited_by_count":11,"area":"lr"},{"id":"2510.16476","title":"NP-Engine: Empowering Optimization Reasoning in Large Language Models with Verifiable Synthetic NP Problems","created":"2025-10-18","cited_by_count":11,"area":"lr"},{"id":"2506.04108","title":"Rectified Sparse Attention","created":"2025-06-04","cited_by_count":10,"area":"inference"},{"id":"2509.24789","title":"Fidel-TS: A High-Fidelity Multimodal Benchmark for Time Series Forecasting","created":"2025-09-29","cited_by_count":10,"area":null},{"id":"2601.04151","title":"Apollo: Unified Multi-Task Audio-Video Joint Generation","created":"2026-01-07","cited_by_count":10,"area":null},{"id":"2602.01053","title":"LRAgent: Efficient KV Cache Sharing for Multi-LoRA LLM Agents","created":"2026-02-01","cited_by_count":10,"area":"agents"},{"id":"2604.04356","title":"REAM: Merging Improves Pruning of Experts in LLMs","created":"2026-04-06","cited_by_count":10,"area":"moe"},{"id":"2505.24842","title":"Cascading Adversarial Bias from Injection to Distillation in Language Models","created":"2025-05-30","cited_by_count":9,"area":null},{"id":"2508.04852","title":"VER-Bench: Evaluating MLLMs on Reasoning with Fine-Grained Visual Evidence","created":"2025-08-06","cited_by_count":9,"area":"lr"},{"id":"2509.24745","title":"ProxyAttn: Guided Sparse Attention via Representative Heads","created":"2025-09-29","cited_by_count":9,"area":null},{"id":"2601.20730","title":"AgentLongBench: A Controllable Long Benchmark For Long-Contexts Agents via Environment Rollouts","created":"2026-01-28","cited_by_count":9,"area":"agents"},{"id":"2602.08005","title":"ResidualKV: Residual-Based KV Cache Compression for Efficient Long-Context Inference","created":"2026-02-08","cited_by_count":9,"area":"inference"},{"id":"2603.06199","title":"FlashPrefill: Instantaneous Pattern Discovery and Thresholding for Ultra-Fast Long-Context Prefilling","created":"2026-03-06","cited_by_count":9,"area":null},{"id":"2604.08362","title":"Towards Real-world Human Behavior Simulation: Benchmarking Large Language Models on Long-horizon, Cross-scenario, Heterogeneous Behavior Traces","created":"2026-04-09","cited_by_count":9,"area":null},{"id":"2504.01698","title":"Do Theory of Mind Benchmarks Need Explicit Human-like Reasoning in Language Models?","created":"2025-04-02","cited_by_count":8,"area":"lr"},{"id":"2505.07313","title":"Towards Multi-Agent Reasoning Systems for Collaborative Expertise Delegation: An Exploratory Design Study","created":"2025-05-12","cited_by_count":8,"area":"lr"},{"id":"2505.12833","title":"Reasoning BO: Enhancing Bayesian Optimization with Long-Context Reasoning Power of LLMs","created":"2025-05-19","cited_by_count":8,"area":"lr"},{"id":"2505.16368","title":"SATURN: SAT-based Reinforcement Learning to Unleash LLMs Reasoning","created":"2025-05-22","cited_by_count":8,"area":"lr"},{"id":"2506.11144","title":"AlignHuman: Improving Motion and Fidelity via Timestep-Segment Preference Optimization for Audio-Driven Human Animation","created":"2025-06-11","cited_by_count":8,"area":"diffusion"},{"id":"2510.16720","title":"Beyond Pipelines: A Survey of the Paradigm Shift toward Model-Native Agentic AI","created":"2025-10-19","cited_by_count":8,"area":"agents"},{"id":"2510.22548","title":"LooGLE v2: Are LLMs Ready for Real World Long Dependency Challenges?","created":"2025-10-26","cited_by_count":8,"area":null},{"id":"2602.08382","title":"Dynamic Long Context Reasoning over Compressed Memory via End-to-End Reinforcement Learning","created":"2026-02-09","cited_by_count":8,"area":"lr"},{"id":"2604.00499","title":"Scheduling LLM Inference with Uncertainty-Aware Output Length Predictions","created":"2026-04-01","cited_by_count":8,"area":null},{"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":"2506.04427","title":"Plugging Schema Graph into Multi-Table QA: A Human-Guided Framework for Reducing LLM Reliance","created":"2025-06-04","cited_by_count":7,"area":null},{"id":"2510.08744","title":"Graph Diffusion Transformers are In-Context Molecular Designers","created":"2025-10-09","cited_by_count":7,"area":"diffusion"},{"id":"2601.14952","title":"CorpusQA: A 10 Million Token Benchmark for Corpus-Level Analysis and Reasoning","created":"2026-01-21","cited_by_count":7,"area":"lr"},{"id":"2601.18204","title":"MemWeaver: Weaving Hybrid Memories for Traceable Long-Horizon Agentic Reasoning","created":"2026-01-26","cited_by_count":7,"area":"lr"},{"id":"2604.09855","title":"Instructing LLMs to Negotiate using Reinforcement Learning with Verifiable Rewards","created":"2026-04-10","cited_by_count":7,"area":null},{"id":"2508.12459","title":"LoraxBench: A Multitask, Multilingual Benchmark Suite for 20 Indonesian Languages","created":"2025-08-17","cited_by_count":6,"area":null},{"id":"2508.15813","title":"SCOPE: A Generative Approach for LLM Prompt Compression","created":"2025-08-16","cited_by_count":6,"area":"inference"},{"id":"2510.08697","title":"BigCodeArena: Unveiling More Reliable Human Preferences in Code Generation via Execution","created":"2025-10-09","cited_by_count":6,"area":"alignment"},{"id":"2510.13494","title":"LiteraryQA: Towards Effective Evaluation of Long-document Narrative QA","created":"2025-10-15","cited_by_count":6,"area":null},{"id":"2510.18053","title":"Adaptive Divergence Regularized Policy Optimization for Fine-tuning Generative Models","created":"2025-10-20","cited_by_count":6,"area":"alignment"},{"id":"2512.22256","title":"Agentic Software Issue Resolution with Large Language Models: A Survey","created":"2025-12-24","cited_by_count":6,"area":"agents"},{"id":"2605.06353","title":"SEQUOR: A Multi-Turn Benchmark for Realistic Constraint Following","created":"2026-05-07","cited_by_count":6,"area":null},{"id":"2506.08373","title":"Draft-based Approximate Inference for LLMs","created":"2025-06-10","cited_by_count":5,"area":"inference"},{"id":"2506.15710","title":"RAST: Reasoning Activation in LLMs via Small-model Transfer","created":"2025-05-30","cited_by_count":5,"area":"lr"},{"id":"2511.00868","title":"FlexiCache: Leveraging Temporal Stability of Attention Heads for Efficient KV Cache Management","created":"2025-11-02","cited_by_count":5,"area":"inference"},{"id":"2602.04541","title":"LycheeDecode: Accelerating Long-Context LLM Inference via Hybrid-Head Sparse Decoding","created":"2026-02-04","cited_by_count":5,"area":"inference"},{"id":"2602.05191","title":"Double-P: Hierarchical Top-P Sparse Attention for Long-Context LLMs","created":"2026-02-05","cited_by_count":5,"area":"inference"},{"id":"2603.09827","title":"MA-EgoQA: Question Answering over Egocentric Videos from Multiple Embodied Agents","created":"2026-03-10","cited_by_count":5,"area":null},{"id":"2501.16029","title":"FDLLM: A Dedicated Detector for Black-Box LLMs Fingerprinting","created":"2025-01-27","cited_by_count":4,"area":null},{"id":"2505.22945","title":"OWL: Probing Cross-Lingual Recall of Memorized Texts via World Literature","created":"2025-05-28","cited_by_count":4,"area":null},{"id":"2506.13324","title":"Towards Pervasive Distributed Agentic Generative AI -- A State of The Art","created":"2025-06-16","cited_by_count":4,"area":"agents"},{"id":"2507.06415","title":"PERK: Long-Context Reasoning as Test-Time Learning","created":"2025-07-08","cited_by_count":4,"area":"lr"},{"id":"2509.23291","title":"Scaling Policy Compliance Assessment in Language Models with Policy Reasoning Traces","created":"2025-09-27","cited_by_count":4,"area":"lr"},{"id":"2510.07414","title":"Haystack Engineering: Context Engineering for Heterogeneous and Agentic Long-Context Evaluation","created":"2025-10-08","cited_by_count":4,"area":"agents"},{"id":"2511.00066","title":"Sharpness-Guided Group Relative Policy Optimization via Probability Shaping","created":"2025-10-29","cited_by_count":4,"area":"lr"},{"id":"2601.20687","title":"Positive-Unlabeled Reinforcement Learning Distillation for On-Premise Small Models","created":"2026-01-28","cited_by_count":4,"area":"alignment"},{"id":"2602.12056","title":"LawThinker: A Deep Research Legal Agent in Dynamic Environments","created":"2026-02-12","cited_by_count":4,"area":"lr"},{"id":"2603.00028","title":"EPPCMinerBen: A Novel Benchmark for Evaluating Large Language Models on Electronic Patient-Provider Communication via the Patient Portal","created":"2026-02-04","cited_by_count":4,"area":null},{"id":"2603.27630","title":"RTLSeek: Boosting the LLM-Based RTL Generation with Multi-Stage Diversity-Oriented Reinforcement Learning","created":"2026-03-29","cited_by_count":4,"area":null},{"id":"2607.05863","title":"Strategic Bargaining in Multi-Buyer Markets: Reinforcement Learning from Verifiable Rewards for LLM Negotiations","created":"2026-07-07","cited_by_count":4,"area":null},{"id":"2607.17715","title":"C$^2$KV: Compressed and Composable KV Cache Reuse for Efficient LLM Inference","created":"2026-07-20","cited_by_count":4,"area":"rag"},{"id":"2504.18587","title":"An Expectation-Maximization Perspective on Reinforcement Learning for LLM Reasoning","created":"2025-04-24","cited_by_count":3,"area":"lr"},{"id":"2505.24179","title":"SALE : Low-bit Estimation for Efficient Sparse Attention in Long-context LLM Prefilling","created":"2025-05-30","cited_by_count":3,"area":null},{"id":"2508.10967","title":"Retro-Expert: Collaborative Reasoning for Interpretable Retrosynthesis","created":"2025-08-14","cited_by_count":3,"area":"lr"},{"id":"2510.09369","title":"Token-Level Policy Optimization: Linking Group-Level Rewards to Token-Level Aggregation via Markov Likelihood","created":"2025-10-10","cited_by_count":3,"area":"lr"},{"id":"2603.17484","title":"Learning When to Attend: Conditional Memory Access for Long-Context LLMs","created":"2026-03-18","cited_by_count":3,"area":null},{"id":"2605.09778","title":"Nectar: Neural Estimation of Cached-Token Attention via Regression","created":"2026-05-10","cited_by_count":3,"area":null},{"id":"2608.15962","title":"SEER: Long-Context Reasoning via Selective Visual-Text Compression","created":"2026-08-16","cited_by_count":3,"area":"lr"},{"id":"2502.11330","title":"System Message Generation for User Preferences using Open-Source Models","created":"2025-02-17","cited_by_count":2,"area":null},{"id":"2503.02993","title":"Zero-Shot Multi-Label Classification of Bangla Documents: Large Decoders Vs. Classic Encoders","created":"2025-03-04","cited_by_count":2,"area":null},{"id":"2504.02865","title":"The Illusionist's Prompt: Exposing the Factual Vulnerabilities of Large Language Models with Linguistic Nuances","created":"2025-04-01","cited_by_count":2,"area":null},{"id":"2507.10281","title":"Toward Real-World Table Agents: Capabilities, Workflows, and Design Principles for LLM-based Table Intelligence","created":"2025-07-14","cited_by_count":2,"area":"agents"},{"id":"2508.11326","title":"MoE-TTS: Enhancing Out-of-Domain Text Understanding for Description-based TTS via Mixture-of-Experts","created":"2025-08-15","cited_by_count":2,"area":"moe"},{"id":"2512.03067","title":"Quantifying the Potential to Escape Filter Bubbles: A Behavior-Aware Measure via Contrastive Simulation","created":"2025-11-27","cited_by_count":2,"area":null},{"id":"2512.05277","title":"From Segments to Scenes: Temporal Understanding for Agentic Autonomous Driving via Vision-Language Models","created":"2025-12-04","cited_by_count":2,"area":"mllm"},{"id":"2601.20309","title":"SuperInfer: SLO-Aware Rotary Scheduling and Memory Management for LLM Inference on Superchips","created":"2026-01-28","cited_by_count":2,"area":"inference"},{"id":"2602.03515","title":"Mitigating Staleness in Asynchronous Pipeline Parallelism via Basis Rotation","created":"2026-02-03","cited_by_count":2,"area":null},{"id":"2603.29186","title":"SLVMEval: Synthetic Meta Evaluation Benchmark for Text-to-Long Video Generation","created":"2026-03-31","cited_by_count":2,"area":null},{"id":"2604.27723","title":"Optimized Deferral for Imbalanced Settings","created":"2026-04-30","cited_by_count":2,"area":null},{"id":"2605.03058","title":"Neuron-Anchored Rule Extraction for Large Language Models via Contrastive Hierarchical Ablation","created":"2026-05-04","cited_by_count":2,"area":"safety"}],"next_cursor":"100"}