{"total":138,"rows":[{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132,"area":"lr"},{"id":"2508.18265","title":"InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency","created":"2025-08-25","cited_by_count":1510,"area":"lr"},{"id":"2508.10925","title":"gpt-oss-120b & gpt-oss-20b Model Card","created":"2025-08-08","cited_by_count":1386,"area":"lr"},{"id":"2406.12793","title":"ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools","created":"2024-06-18","cited_by_count":1121,"area":"lr"},{"id":"2401.02954","title":"DeepSeek LLM: Scaling Open-Source Language Models with Longtermism","created":"2024-01-05","cited_by_count":642,"area":"lr"},{"id":"2502.05171","title":"Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach","created":"2025-02-07","cited_by_count":415,"area":"lr"},{"id":"2504.07491","title":"Kimi-VL Technical Report","created":"2025-04-10","cited_by_count":388,"area":"lr"},{"id":"2308.11462","title":"LegalBench: A Collaboratively Built Benchmark for Measuring Legal Reasoning in Large Language Models","created":"2023-08-20","cited_by_count":336,"area":"lr"},{"id":"2501.00663","title":"Titans: Learning to Memorize at Test Time","created":"2024-12-31","cited_by_count":328,"area":"lr"},{"id":"2402.01306","title":"KTO: Model Alignment as Prospect Theoretic Optimization","created":"2024-02-02","cited_by_count":264,"area":"lr"},{"id":"2312.01552","title":"The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context Learning","created":"2023-12-04","cited_by_count":257,"area":"lr"},{"id":"2310.03731","title":"MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical Reasoning","created":"2023-10-05","cited_by_count":156,"area":"lr"},{"id":"2404.03683","title":"Stream of Search (SoS): Learning to Search in Language","created":"2024-04-01","cited_by_count":145,"area":"lr"},{"id":"2412.19442","title":"A Survey on Large Language Model Acceleration based on KV Cache Management","created":"2024-12-27","cited_by_count":131,"area":"lr"},{"id":"2402.05602","title":"AttnLRP: Attention-Aware Layer-Wise Relevance Propagation for Transformers","created":"2024-02-08","cited_by_count":120,"area":"lr"},{"id":"2310.05845","title":"GraphLLM: Boosting Graph Reasoning Ability of Large Language Model","created":"2023-10-09","cited_by_count":107,"area":"lr"},{"id":"2402.11163","title":"KG-Agent: An Efficient Autonomous Agent Framework for Complex Reasoning over Knowledge Graph","created":"2024-02-17","cited_by_count":93,"area":"lr"},{"id":"2311.09724","title":"OVM, Outcome-supervised Value Models for Planning in Mathematical Reasoning","created":"2023-11-16","cited_by_count":85,"area":"lr"},{"id":"2402.02244","title":"Beyond the Limits: A Survey of Techniques to Extend the Context Length in Large Language Models","created":"2024-02-03","cited_by_count":76,"area":"lr"},{"id":"2411.14794","title":"VideoEspresso: A Large-Scale Chain-of-Thought Dataset for Fine-Grained Video Reasoning via Core Frame Selection","created":"2024-11-22","cited_by_count":65,"area":"lr"},{"id":"2401.06915","title":"DocFinQA: A Long-Context Financial Reasoning Dataset","created":"2024-01-12","cited_by_count":60,"area":"lr"},{"id":"2402.08785","title":"InstructGraph: Boosting Large Language Models via Graph-centric Instruction Tuning and Preference Alignment","created":"2024-02-13","cited_by_count":56,"area":"lr"},{"id":"2306.00024","title":"Self-Verification Improves Few-Shot Clinical Information Extraction","created":"2023-05-30","cited_by_count":52,"area":"lr"},{"id":"2606.13392","title":"MiniMax Sparse Attention","created":"2026-06-11","cited_by_count":44,"area":"lr"},{"id":"2505.22654","title":"VScan: Rethinking Visual Token Reduction for Efficient Large Vision-Language Models","created":"2025-05-28","cited_by_count":41,"area":"lr"},{"id":"2509.21009","title":"RollPacker: Mitigating Long-Tail Rollouts for Fast, Synchronous RL Post-Training","created":"2025-09-25","cited_by_count":35,"area":"lr"},{"id":"2401.15269","title":"Improving Medical Reasoning through Retrieval and Self-Reflection with Retrieval-Augmented Large Language Models","created":"2024-01-27","cited_by_count":34,"area":"lr"},{"id":"2502.12970","title":"Reasoning-to-Defend: Safety-Aware Reasoning Can Defend Large Language Models from Jailbreaking","created":"2025-02-18","cited_by_count":34,"area":"lr"},{"id":"2310.07712","title":"Found in the Middle: Permutation Self-Consistency Improves Listwise Ranking in Large Language Models","created":"2023-10-11","cited_by_count":31,"area":"lr"},{"id":"2505.10475","title":"Parallel Scaling Law for Language Models","created":"2025-05-15","cited_by_count":30,"area":"lr"},{"id":"2504.09772","title":"Two Heads are Better Than One: Test-time Scaling of Multi-agent Collaborative Reasoning","created":"2025-04-14","cited_by_count":29,"area":"lr"},{"id":"2310.10845","title":"CoTFormer: A Chain-of-Thought Driven Architecture with Budget-Adaptive Computation Cost at Inference","created":"2023-10-16","cited_by_count":27,"area":"lr"},{"id":"2403.02054","title":"Large Language Model-Based Evolutionary Optimizer: Reasoning with elitism","created":"2024-03-04","cited_by_count":27,"area":"lr"},{"id":"2505.13438","title":"Optimizing Anytime Reasoning via Budget Relative Policy Optimization","created":"2025-05-19","cited_by_count":27,"area":"lr"},{"id":"2502.01567","title":"Latent Thought Models with Variational Bayes Inference-Time Computation","created":"2025-02-03","cited_by_count":25,"area":"lr"},{"id":"2510.13554","title":"Attention Illuminates LLM Reasoning: The Preplan-and-Anchor Rhythm Enables Fine-Grained Policy Optimization","created":"2025-10-15","cited_by_count":25,"area":"lr"},{"id":"2510.05069","title":"SwiReasoning: Switch-Thinking in Latent and Explicit for Pareto-Superior Reasoning LLMs","created":"2025-10-06","cited_by_count":22,"area":"lr"},{"id":"2602.06176","title":"Large Language Model Reasoning Failures","created":"2026-02-05","cited_by_count":21,"area":"lr"},{"id":"2506.21710","title":"FOCUS: Internal MLLM Representations for Efficient Fine-Grained Visual Question Answering","created":"2025-06-26","cited_by_count":20,"area":"lr"},{"id":"2311.03250","title":"Instructed Language Models with Retrievers Are Powerful Entity Linkers","created":"2023-11-06","cited_by_count":18,"area":"lr"},{"id":"2503.13551","title":"Towards Hierarchical Multi-Step Reward Models for Enhanced Reasoning in Large Language Models","created":"2025-03-16","cited_by_count":18,"area":"lr"},{"id":"2312.01279","title":"TextGenSHAP: Scalable Post-hoc Explanations in Text Generation with Long Documents","created":"2023-12-03","cited_by_count":17,"area":"lr"},{"id":"2507.08806","title":"Think Clearly: Improving Reasoning via Redundant Token Pruning","created":"2025-06-17","cited_by_count":17,"area":"lr"},{"id":"2510.00054","title":"HiDe: Rethinking The Zoom-IN method in High Resolution MLLMs via Hierarchical Decoupling","created":"2025-09-28","cited_by_count":17,"area":"lr"},{"id":"2512.24617","title":"Dynamic Large Concept Models: Latent Reasoning in an Adaptive Semantic Space","created":"2025-12-31","cited_by_count":17,"area":"lr"},{"id":"2502.01941","title":"Semantic Integrity Matters: Benchmarking and Preserving High-Density Reasoning in KV Cache Compression","created":"2025-02-04","cited_by_count":16,"area":"lr"},{"id":"2506.15969","title":"LazyEviction: Lagged KV Eviction with Attention Pattern Observation for Efficient Long Reasoning","created":"2025-06-19","cited_by_count":16,"area":"lr"},{"id":"2511.08577","title":"Think-at-Hard: Dynamic Looped Transformers for Improved Reasoning","created":"2025-11-11","cited_by_count":16,"area":"lr"},{"id":"2310.05030","title":"Counter Turing Test CT^2: AI-Generated Text Detection is Not as Easy as You May Think -- Introducing AI Detectability Index","created":"2023-10-08","cited_by_count":14,"area":"lr"},{"id":"2409.01893","title":"What are the Essential Factors in Crafting Effective Long Context Multi-Hop Instruction Datasets? Insights and Best Practices","created":"2024-09-03","cited_by_count":14,"area":"lr"},{"id":"2504.15077","title":"Think2SQL: Reinforce LLM Reasoning Capabilities for Text2SQL","created":"2025-04-21","cited_by_count":14,"area":"lr"},{"id":"2510.24051","title":"Pie: A Programmable Serving System for Emerging LLM Applications","created":"2025-10-28","cited_by_count":14,"area":"lr"},{"id":"2511.22645","title":"GeoZero: Incentivizing Reasoning from Scratch on Geospatial Scenes","created":"2025-11-27","cited_by_count":14,"area":"lr"},{"id":"2607.05378","title":"CompactionRL: Reinforcement Learning with Context Compaction for Long-Horizon Agents","created":"2026-07-06","cited_by_count":14,"area":"lr"},{"id":"2402.16631","title":"GenAINet: Enabling Wireless Collective Intelligence via Knowledge Transfer and Reasoning","created":"2024-02-26","cited_by_count":13,"area":"lr"},{"id":"2405.05955","title":"Smurfs: Multi-Agent System using Context-Efficient DFSDT for Tool Planning","created":"2024-05-09","cited_by_count":13,"area":"lr"},{"id":"2510.07356","title":"ConCuR: Conciseness Makes State-of-the-Art Kernel Generation","created":"2025-10-08","cited_by_count":13,"area":"lr"},{"id":"2403.03458","title":"Slot Abstractors: Toward Scalable Abstract Visual Reasoning","created":"2024-03-06","cited_by_count":11,"area":"lr"},{"id":"2511.05722","title":"OckBench: Measuring the Efficiency of LLM Reasoning","created":"2025-11-07","cited_by_count":11,"area":"lr"},{"id":"2512.22939","title":"ColaVLA: Leveraging Cognitive Latent Reasoning for Hierarchical Parallel Trajectory Planning in Autonomous Driving","created":"2025-12-28","cited_by_count":11,"area":"lr"},{"id":"2506.22950","title":"Infinite Sampling: Efficient and Stable Grouped RL Training for Large Language Models","created":"2025-06-28","cited_by_count":10,"area":"lr"},{"id":"2603.01914","title":"AdaPonderLM: Gated Pondering Language Models with Token-Wise Adaptive Depth","created":"2026-03-02","cited_by_count":10,"area":"lr"},{"id":"2312.09542","title":"Marathon: A Race Through the Realm of Long Context with Large Language Models","created":"2023-12-15","cited_by_count":9,"area":"lr"},{"id":"2506.06600","title":"RARL: Improving Medical VLM Reasoning and Generalization with Reinforcement Learning and LoRA under Data and Hardware Constraints","created":"2025-06-07","cited_by_count":9,"area":"lr"},{"id":"2603.22847","title":"Rethinking Token-Level Policy Optimization for Multimodal Chain-of-Thought","created":"2026-03-24","cited_by_count":9,"area":"lr"},{"id":"2603.11896","title":"Think While Watching: Online Streaming Segment-Level Memory for Multi-Turn Video Reasoning in Multimodal Large Language Models","created":"2026-03-12","cited_by_count":8,"area":"lr"},{"id":"2410.13699","title":"Unconstrained Model Merging for Enhanced LLM Reasoning","created":"2024-10-17","cited_by_count":7,"area":"lr"},{"id":"2412.02906","title":"Does Few-Shot Learning Help LLM Performance in Code Synthesis?","created":"2024-12-03","cited_by_count":6,"area":"lr"},{"id":"2506.19235","title":"RecLLM-R1: A Two-Stage Training Paradigm with Reinforcement Learning and Chain-of-Thought v1","created":"2025-06-24","cited_by_count":6,"area":"lr"},{"id":"2603.14337","title":"On the Nature of Attention Sink that Shapes Decoding Strategy in Omni-LLMs","created":"2026-03-15","cited_by_count":6,"area":"lr"},{"id":"2603.20586","title":"MKA: Memory-Keyed Attention for Efficient Long-Context Reasoning","created":"2026-03-21","cited_by_count":6,"area":"lr"},{"id":"2305.14864","title":"Just CHOP: Embarrassingly Simple LLM Compression","created":"2023-05-24","cited_by_count":5,"area":"lr"},{"id":"2506.01969","title":"FlashMLA-ETAP: Efficient Transpose Attention Pipeline for Accelerating MLA Inference on NVIDIA H20 GPUs","created":"2025-05-13","cited_by_count":5,"area":"lr"},{"id":"2506.16123","title":"FinCoT: Grounding Chain-of-Thought in Expert Financial Reasoning","created":"2025-06-19","cited_by_count":5,"area":"lr"},{"id":"2510.21978","title":"Beyond Reasoning Gains: Mitigating General-Capability Forgetting in Large Reasoning Models","created":"2025-10-24","cited_by_count":5,"area":"lr"},{"id":"2603.06274","title":"Stem: Rethinking Causal Information Flow in Sparse Attention","created":"2026-03-06","cited_by_count":5,"area":"lr"},{"id":"2501.00712","title":"Rethinking Addressing in Language Models via Contexualized Equivariant Positional Encoding","created":"2025-01-01","cited_by_count":4,"area":"lr"},{"id":"2512.16144","title":"INTELLECT-3: Technical Report","created":"2025-12-18","cited_by_count":4,"area":"lr"},{"id":"2606.11576","title":"AVIS: Adaptive Test-Time Scaling for Vision-Language Models","created":"2026-06-10","cited_by_count":4,"area":"lr"},{"id":"2505.23667","title":"Formula-R1: Incentivizing LLM Reasoning over Complex Tables with Numerical Computation via Formula-Driven Reinforcement Learning","created":"2025-05-29","cited_by_count":3,"area":"lr"},{"id":"2601.18832","title":"The Geometric Reasoner: Manifold-Informed Latent Foresight Search for Long-Context Reasoning","created":"2026-01-25","cited_by_count":3,"area":"lr"},{"id":"2602.20934","title":"Architecting AgentOS: From Token-Level Context to Emergent System-Level Intelligence","created":"2026-02-24","cited_by_count":3,"area":"lr"},{"id":"2603.21465","title":"DRTriton: Large-Scale Synthetic Data Driven Reinforcement Learning for Triton Kernel Generation","created":"2026-03-23","cited_by_count":3,"area":"lr"},{"id":"2604.27201","title":"Path-Lock Expert: Separating Reasoning Mode in Hybrid Thinking via Architecture-Level Separation","created":"2026-04-29","cited_by_count":3,"area":"lr"},{"id":"2605.05227","title":"Rethinking Data Curation in LLM Training: Online Reweighting Offers Better Generalization than Offline Methods","created":"2026-04-19","cited_by_count":3,"area":"lr"},{"id":"2410.03662","title":"System 2 Reasoning Capabilities Are Nigh","created":"2024-10-04","cited_by_count":2,"area":"lr"},{"id":"2502.21309","title":"Reasoning is Periodicity? Improving Large Language Models Through Effective Periodicity Modeling","created":"2025-02-28","cited_by_count":2,"area":"lr"},{"id":"2505.04075","title":"Rethinking LLM Advancement: Compute-Dependent and Independent Paths to Progress","created":"2025-05-07","cited_by_count":2,"area":"lr"},{"id":"2508.18736","title":"Rethinking Caching for LLM Serving Systems: Beyond Traditional Heuristics","created":"2025-08-26","cited_by_count":2,"area":"lr"},{"id":"2509.22144","title":"From Long to Lean: Performance-aware and Adaptive Chain-of-Thought Compression via Multi-round Refinement","created":"2025-09-26","cited_by_count":2,"area":"lr"},{"id":"2511.00521","title":"Reasoning Planning for Language Models","created":"2025-11-01","cited_by_count":2,"area":"lr"},{"id":"2511.10301","title":"Rethinking Visual Information Processing in Multimodal LLMs","created":"2025-11-13","cited_by_count":2,"area":"lr"},{"id":"2511.11313","title":"DocSLM: A Small Vision-Language Model for Long Multimodal Document Understanding","created":"2025-11-14","cited_by_count":2,"area":"lr"},{"id":"2601.18197","title":"GAIA: A Data Flywheel System for Training GUI Test-Time Scaling Critic Models","created":"2026-01-26","cited_by_count":2,"area":"lr"},{"id":"2602.15843","title":"The Perplexity Paradox: Why Code Compresses Better Than Math in LLM Prompts","created":"2026-01-21","cited_by_count":2,"area":"lr"},{"id":"2603.27375","title":"Bridging Visual Representation and Reinforcement Learning from Verifiable Rewards in Large Vision-Language Models","created":"2026-03-28","cited_by_count":2,"area":"lr"},{"id":"2604.18002","title":"Neural Garbage Collection: Learning to Forget while Learning to Reason","created":"2026-04-20","cited_by_count":2,"area":"lr"},{"id":"2604.19060","title":"Reinforcement Learning Improves LLM Accuracy and Reasoning in Disease Classification from Radiology Reports","created":"2026-04-21","cited_by_count":2,"area":"lr"},{"id":"2605.05802","title":"Selective Rollout: Mid-Trajectory Termination for Multi-Sample Agent RL","created":"2026-05-07","cited_by_count":2,"area":"lr"},{"id":"2605.15422","title":"DualKV: Shared-Prompt Flash Attention for Efficient RL Training with Large Rollouts and Long Contexts","created":"2026-05-14","cited_by_count":2,"area":"lr"}],"next_cursor":"100"}