Submitted by Yu Luo 82 Beyond Memory: Harnessing Long-Horizon Agents with Explicit Belief States alibaba 24 3
Submitted by Williams JIANG 50 One to More, More to One: Category-Aware Iterative Expert Training for Software Engineering Agents alibaba 41 4
Submitted by he 17 Beyond the Stability-Exploration Dilemma: Environmental Regularization for LLM Policy Optimization alibaba 11 2
Submitted by Xingjian Wang 14 From Corpora to Co-Evolving Capabilities: Capability-Centric Data Design for Generalist Image Generation alibaba 2
Submitted by TaobaoTmall-AlgorithmProducts 16 CPI-Bench: A Comprehensive,Practical and Intelligent Benchmark for Real-World Image Editing alibaba 7 2
Submitted by xiaochonglinghu 101 DreamX-Phi 1.0: Action-Conditioned Video World Model for Robotic Manipulation alibaba 68 3
Submitted by Xiaoying Xing 21 Business Arena: Benchmarking LLM Agents in a Realistic Marketplace alibaba 91 5
Submitted by Wang Yong 187 LongHorizon-Harness: Advancing Long-Horizon Agents for Real-World Tasks alibaba 1.65k 3
Submitted by Qiming Shi 114 MerchantBench: Benchmarking LLM Agents for Long-Term Coherence in E-Commerce Operations alibaba 171 5
Submitted by Yang Li (SJTU & SII) 9 How Does Reasoning Flow? Tracing Attention-Induced Information Flow for Targeted RL in LLMs alibaba 2
Yu Luo 
