{"total":58,"rows":[{"id":"2511.11793","title":"MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling","created":"2025-11-14","cited_by_count":81,"area":"lr"},{"id":"2509.26490","title":"VitaBench: Benchmarking LLM Agents with Versatile Interactive Tasks in Real-world Applications","created":"2025-09-30","cited_by_count":53,"area":"agents"},{"id":"2601.16725","title":"LongCat-Flash-Thinking-2601 Technical Report","created":"2026-01-23","cited_by_count":34,"area":"lr"},{"id":"2511.00279","title":"LongCat-Flash-Omni Technical Report","created":"2025-10-31","cited_by_count":26,"area":"moe"},{"id":"2602.11348","title":"AgentNoiseBench: Benchmarking Robustness of Tool-Using LLM Agents Under Noisy Condition","created":"2026-02-11","cited_by_count":23,"area":"agents"},{"id":"2509.18883","title":"Introducing LongCat-Flash-Thinking: A Technical Report","created":"2025-09-23","cited_by_count":22,"area":"lr"},{"id":"2511.18903","title":"How Learning Rate Decay Wastes Your Best Data in Curriculum-Based LLM Pretraining","created":"2025-11-24","cited_by_count":14,"area":null},{"id":"2604.26256","title":"DORA: A Scalable Asynchronous Reinforcement Learning System for Language Model Training","created":"2026-04-29","cited_by_count":14,"area":null},{"id":"2509.18362","title":"FastMTP: Accelerating LLM Inference with Enhanced Multi-Token Prediction","created":"2025-09-16","cited_by_count":13,"area":"inference"},{"id":"2601.10355","title":"Unlocking Implicit Experience: Synthesizing Tool-Use Trajectories from Text","created":"2026-01-15","cited_by_count":13,"area":null},{"id":"2509.18847","title":"Failure Makes the Agent Stronger: Enhancing Accuracy through Structured Reflection for Reliable Tool Interactions","created":"2025-09-23","cited_by_count":12,"area":"agents"},{"id":"2512.13095","title":"ADHint: Adaptive Hints with Difficulty Priors for Reinforcement Learning","created":"2025-12-15","cited_by_count":12,"area":"lr"},{"id":"2605.27141","title":"VitaBench 2.0: Evaluating Personalized and Proactive Agents in Long-Term User Interactions","created":"2026-05-26","cited_by_count":12,"area":"agents"},{"id":"2602.11287","title":"HiFloat4 Format for Language Model Inference","created":"2026-02-11","cited_by_count":11,"area":null},{"id":"2604.10098","title":"Attention Sink in Transformers: A Survey on Utilization, Interpretation, and Mitigation","created":"2026-04-11","cited_by_count":11,"area":null},{"id":"2509.23678","title":"Towards a Comprehensive Scaling Law of Mixture-of-Experts","created":"2025-09-28","cited_by_count":10,"area":"moe"},{"id":"2510.13291","title":"Higher Satisfaction, Lower Cost: A Technical Report on How LLMs Revolutionize Meituan's Intelligent Interaction Systems","created":"2025-10-15","cited_by_count":7,"area":null},{"id":"2512.18425","title":"MoE Pathfinder: Trajectory-driven Expert Pruning","created":"2025-12-20","cited_by_count":7,"area":"moe"},{"id":"2601.01204","title":"XStreamVGGT: Extremely Memory-Efficient Streaming Vision Geometry Grounded Transformer with KV Cache Compression","created":"2026-01-03","cited_by_count":7,"area":"inference"},{"id":"2602.03584","title":"$V_0$: A Generalist Value Model for Any Policy at State Zero","created":"2026-02-03","cited_by_count":7,"area":null},{"id":"2602.14208","title":"Fast Catch-Up, Late Switching: Optimal Batch Size Scheduling via Functional Scaling Laws","created":"2026-02-15","cited_by_count":6,"area":null},{"id":"2604.11778","title":"General365: Benchmarking General Reasoning in Large Language Models Across Diverse and Challenging Tasks","created":"2026-04-13","cited_by_count":6,"area":"lr"},{"id":"2605.27209","title":"Learning to Act under Noise: Enhancing Agent Robustness via Noisy Environments","created":"2026-05-26","cited_by_count":6,"area":"agents"},{"id":"2606.14502","title":"From Chatbot to Digital Colleague: The Paradigm Shift Toward Persistent Autonomous AI","created":"2026-06-12","cited_by_count":6,"area":null},{"id":"2602.22273","title":"FIRE: A Comprehensive Benchmark for Financial Intelligence and Reasoning Evaluation","created":"2026-02-25","cited_by_count":5,"area":"lr"},{"id":"2605.19660","title":"OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond","created":"2026-05-19","cited_by_count":5,"area":"inference"},{"id":"2602.10718","title":"SnapMLA: Efficient Long-Context MLA Decoding via Hardware-Aware FP8 Quantized Pipelining","created":"2026-02-11","cited_by_count":4,"area":null},{"id":"2605.18643","title":"Post-Trained MoE Can Skip Half Experts via Self-Distillation","created":"2026-05-18","cited_by_count":4,"area":"moe"},{"id":"2606.12384","title":"APPO: Agentic Procedural Policy Optimization","created":"2026-06-10","cited_by_count":4,"area":"agents"},{"id":"2603.28569","title":"CirrusBench: Evaluating LLM-based Agents Beyond Correctness in Real-World Cloud Service Environments","created":"2026-03-30","cited_by_count":3,"area":"agents"},{"id":"2607.14952","title":"LongStraw: Long-Context RL Beyond 2M Tokens under a Fixed GPU Budget","created":"2026-07-16","cited_by_count":3,"area":null},{"id":"2601.22580","title":"SpanNorm: Reconciling Training Stability and Performance in Deep Transformers","created":"2026-01-30","cited_by_count":2,"area":"moe"},{"id":"2603.02188","title":"Multi-Head Low-Rank Attention","created":"2026-03-02","cited_by_count":2,"area":"inference"},{"id":"2606.31564","title":"ACE: Pluggable Adaptive Context Elasticizer across Agents","created":"2026-06-30","cited_by_count":2,"area":"agents"},{"id":"2608.01662","title":"LongCat Sparse Attention: Taming the Lightning via Streaming-aware Hierarchical Cross-Layer Indexing","created":"2026-08-03","cited_by_count":2,"area":null},{"id":"2608.12149","title":"Massive Activations in Hybrid Linear Attention Large Language Models: Pre-Attention Spikes and Inter-Spike Plateaus","created":"2026-08-12","cited_by_count":2,"area":null},{"id":"2511.02854","title":"SELF-REDRAFT: Eliciting Intrinsic Exploration-Exploitation Balance in Test-Time Scaling for Code Generation","created":"2025-10-31","cited_by_count":1,"area":"lr"},{"id":"2512.13705","title":"Scaling and Transferability of Annealing Strategies in Large Language Model Training","created":"2025-12-05","cited_by_count":1,"area":"moe"},{"id":"2601.20255","title":"HE-SNR: Uncovering Latent Logic via Entropy for Guiding Mid-Training on SWE-bench","created":"2026-01-28","cited_by_count":1,"area":null},{"id":"2602.13185","title":"FlexAM: Flexible Appearance-Motion Decomposition for Versatile Video Generation Control","created":"2026-02-13","cited_by_count":1,"area":null},{"id":"2602.22697","title":"Reinforcing Real-world Service Agents: Balancing Utility and Cost in Task-oriented Dialogue","created":"2026-02-26","cited_by_count":1,"area":"agents"},{"id":"2605.23893","title":"Complete-muE: Optimal Hyperparameter Transfer and Scaling for MoE Models","created":"2026-05-22","cited_by_count":1,"area":"moe"},{"id":"2509.21081","title":"TyphoonMLA: A Mixed Naive-Absorb MLA Kernel For Shared Prefix","created":"2025-09-25","cited_by_count":0,"area":null},{"id":"2511.18314","title":"AnyExperts: On-Demand Expert Allocation for Multimodal Language Models with Mixture of Expert","created":"2025-11-23","cited_by_count":0,"area":"mllm"},{"id":"2512.22455","title":"AFA-LoRA: Enabling Non-Linear Adaptations in LoRA with Activation Function Annealing","created":"2025-12-27","cited_by_count":0,"area":null},{"id":"2602.08344","title":"OPE: Overcoming Information Saturation in Parallel Thinking via Outline-Guided Path Exploration","created":"2026-02-09","cited_by_count":0,"area":"lr"},{"id":"2602.21780","title":"XStreamVGGT: Extremely Memory-Efficient Streaming Vision Geometry Grounded Transformer with KV Cache Compression","created":"2026-02-25","cited_by_count":0,"area":"inference"},{"id":"2603.13364","title":"FineRMoE: Dimension Expansion for Finer-Grained Expert with Its Upcycling Approach","created":"2026-03-09","cited_by_count":0,"area":"moe"},{"id":"2603.18074","title":"Adapting Technical-Service LLM Agents with Latent Logic Augmentation, Robust Noise Reduction, and Hybrid Reward Modeling","created":"2026-03-18","cited_by_count":0,"area":"agents"},{"id":"2605.21603","title":"DynaFlow: Transparent and Flexible Intra-Device Parallelism via Programmable Operator Scheduling","created":"2026-05-20","cited_by_count":0,"area":null},{"id":"2606.04048","title":"Unlocking Feature Learning in Gated Delta Networks at Scale","created":"2026-06-02","cited_by_count":0,"area":null},{"id":"2606.07689","title":"Struct-Searcher: Agentic Structural Thinking Advances Multimodal Deep Information Seeking","created":"2026-06-05","cited_by_count":0,"area":"lr"},{"id":"2607.10387","title":"GigaChat Audio: Time-aware Large Audio Language Model","created":"2026-07-11","cited_by_count":0,"area":null},{"id":"2607.22662","title":"CuraWeb: Joint Optimization of Quality, Redundancy, and Diversity for Web-Scale Pretraining Data","created":"2026-06-29","cited_by_count":0,"area":null},{"id":"2608.08650","title":"The Evolution of Mixture-of-Experts Architectures in Large Language Models: Routing, Topology, Load Balancing, and Expert Parallelism","created":"2026-08-09","cited_by_count":0,"area":"moe"},{"id":"2609.36760","title":"QuantMLA: Function-Aligned Dual-Path Quantization for Low-Bit MLA KV Caching","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.39661","title":"The Evolution of Attention in Large Language Models: Mechanisms, Trade-offs, and Emerging Trends","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.11575","title":"Smoothing the Top-k Exposure Boundary for Sparse Mixture-of-Experts","created":"2026-10-08","cited_by_count":0,"area":"moe"}],"next_cursor":null}