alibaba · 19 records

dateidtitleauthorsvenue↑
2026-11-042611.04035Recursa: Toward Recursively Self-Improving Foundation Model SystemsErkang Zhu et al.arXiv15
2026-10-222610.30932UserArena: Benchmarking Interactive User Simulation for Long-Horizon Shopping AgentsJujia Zhao et al.arXiv63
2026-10-212610.25844SWIFT: Self-guided Weak-to-strong dIFfusion models via Target extrapolationYanjin He et al.arXiv34
2026-10-162610.20603CommerceGen-Studio: An End-to-End Framework for Commercial-Grade Main-Image GenerationXiaoli Xu et al.arXiv40
2026-10-142610.18356Urbex: Agentic Spatial Grounding for City-Scale 3D ScenesYu Wang et al.arXiv130
2026-10-132610.13166Scaling Agentic Data for Long-Horizon Terminal IntelligenceShun Zou et al.arXiv140
2026-10-122610.12978Learning Representations to Guide Pixel Diffusion TransformersZihao Pan et al.arXiv23
2026-10-022610.01415Beyond Memory: Harnessing Long-Horizon Agents with Explicit Belief StatesYu Luo et al.arXiv63
2026-09-242609.24308HappyWorld-BenchZhiqi Bai et al.arXiv55
2026-09-222609.23377One to More, More to One: Category-Aware Iterative Expert Training for Software Engineering AgentsJie Zhao et al.arXiv47
2026-08-262608.09408DREAM Technical ReportBin Zhang et al.arXiv5
2026-08-252608.23311Beyond the Stability-Exploration Dilemma: Environmental Regularization for LLM Policy OptimizationXianlei Zhou et al.arXiv17
2026-08-192608.18076From Corpora to Co-Evolving Capabilities: Capability-Centric Data Design for Generalist Image GenerationXingjian Wang et al.arXiv13
2026-08-172608.14546CPI-Bench: A Comprehensive,Practical and Intelligent Benchmark for Real-World Image EditingQinye Zhou et al.arXiv15
2026-08-142608.13489DreamX-Phi 1.0: Action-Conditioned Video World Model for Robotic ManipulationDreamX Team et al.arXiv54
2026-08-112608.08621Business Arena: Benchmarking LLM Agents in a Realistic MarketplaceYijun Pan et al.arXiv18
2026-08-052607.28956MerchantBench: Benchmarking LLM Agents for Long-Term Coherence in E-Commerce OperationsQiming Shi et al.arXiv85
2026-08-042608.01964LongHorizon-Harness: Advancing Long-Horizon Agents for Real-World TasksZiyu Ma et al.arXiv139
2026-06-102606.10646How Does Reasoning Flow? Tracing Attention-Induced Information Flow for Targeted RL in LLMsZhichen Dong et al.arXiv8