4 papers
Trace-to-Architecture: Capability Bottleneck Diagnosis for Harness Revision
Wenfeng Wang, Jianrui Shi, Mingang Guo +5
Improving an LLM agent requires knowing what to change when it fails. Similar failures can require different fixes, and resolving one problem can expose another. We introduce Trace…
UNIQUE: A Unified Retrieval and Ranking System for Large-Scale Feed Recommendation
Zhuang Liu, Yongkang Fu, Zuodong Yang +6
Industrial mobile feed systems rely on a retrieval-ranking pipeline to serve large-scale, heterogeneous, and fast-changing content under strict latency constraints. However, existi…
MuSeR: Scalable Long-sequence Recommendation with Multi-interest Modeling
Yongkang Fu, Beining Bao, Yu Jiang +10
Ultra-long user behavior sequences carry rich signals of stable and diverse preferences, yet industrial recommender systems typically truncate histories to a few hundred actions un…
FPCO-Dialog: A Multi-Turn False-Premise Benchmark for Correction and Cooperation in Vision-Language Models
Jiayuan Ma, Yuqi Lu, Weiyang Guo +5
Vision-language models (VLMs) are increasingly deployed in multi-turn settings where users may describe visual content with incorrect assumptions. Yet existing evaluations rarely i…