LongCat · 22 records

dateidtitleauthorsvenue↑
2026-11-092611.12426dNaViT: Discrete Codes are General-Purpose Visual RepresentationsXiaotong Li et al.arXiv35
2026-11-082611.13004G-STAR: Group-Scaled Token Capacity for Deeply Compressed Autoregressive GenerationXu Huang et al.arXiv45
2026-10-282610.38425IntReal: A Real-World Dataset and Benchmark for Multimodal Interleaved GenerationShaohan Yu et al.arXiv14
2026-10-272610.37662Can Discrete Tokens Serve as Semantically Lossless Representations of Visual Signals?Jialv Zou et al.arXiv29
2026-10-202610.19686Interlock: From Local Correctness to Task Completion in Long-Horizon AgentsLinji Hao et al.arXiv24
2026-10-162610.21656Data World: Scaling Data Environments from ScratchZhanli Li et al.arXiv39
2026-10-162610.20731WorldCast: Exploring Intelligent Visual Generation in World State PredictionWenhao Yan et al.arXiv38
2026-10-142610.14118ClawLoop: Self-Improving Agents via Harness-Native Training LoopHansi Yang et al.arXiv33
2026-10-122609.36760QuantMLA: Function-Aligned Dual-Path Quantization for Low-Bit MLA KV CachingZunhai Su et al.arXiv10
2026-10-062609.32423PluginRSI: Recursive Improvement of Agent Harnesses with Reusable PluginsYaorui Shi et al.arXiv7
2026-10-022609.39687Better Supervision Is Nearby: Neighborhood On-Policy Self-DistillationXincheng Wei et al.arXiv14
2026-09-302609.36071LongCat-DeepResearch Technical ReportMeituan LongCat Team et al.arXiv52
2026-09-022609.00768DiagEvo: Diagnosis-Guided Self-Evolution via Hierarchical Error MemoryXincheng Wei et al.arXiv23
2026-08-242608.08676UniSpace: Unified Visual Representation and Scalable Multimodal ModelingJinbo Yan et al.arXiv12
2026-08-172608.13417Beyond Final Scores: A Systematic Evaluation of Agents for Long-Horizon AI Research and DevelopmentYiwei Li et al.arXiv59
2026-08-032607.29209SAF-OPD: Stable Advantage Fusion for On-Policy DistillationYifan Ding et al.arXiv26
2026-07-302607.25308CAST: Game Solvers as Turn-Level Teachers for LLM AgentsYu Wang et al.arXiv41
2026-05-282605.28534GUI-CIDER: Mid-training GUI Agents via Causal Internalization and Density-aware Exemplar ReselectionZheng Wu et al.arXiv7
2026-05-272605.27141VitaBench 2.0: Evaluating Personalized and Proactive Agents in Long-Term User InteractionsYuxin Chen et al.arXiv17
2026-05-272605.27209Learning to Act under Noise: Enhancing Agent Robustness via Noisy EnvironmentsYuxin Chen et al.arXiv12
2026-05-262605.25874WBench: A Comprehensive Multi-turn Benchmark for Interactive Video World Model EvaluationKaining Ying et al.arXiv70
2026-05-062605.02396HeavySkill: Heavy Thinking as the Inner Skill in Agentic HarnessJianing Wang et al.arXiv23