Skip to main content

# SEEK

2 related articles

Subscribe to updates

arXiv Oct 2, 2026
HIDE benchmark and SEEK memory framework: 62.9% average success across 15 hidden-state tasks, 11.7 points above the strongest baseline
The authors introduce HIDE, an RLBench-based benchmark of 15 manipulation-memory tasks spanning repetition counting, historical-state recall, and execution-progress tracking under partial observability, together with SEEK, a framework combining windowed context memory, persistent anchor memory, and stage-counter memory to retain historical evidence and track execution state; evaluations show substantial limitations in existing policies on HIDE, while SEEK reaches 62.9% average success in simulation, 11.7 percentage points above the strongest baseline SAM2Act+, and 89% average success on four real-robot tasks.
The authors introduce HIDE, an RLBench-based benchmark of 15 manipulation-memory tasks spanning repetition counting, historical-state recall, and execution-progress tracking under partial observability, together with SEEK, a framework combining windowed context memory, persistent anchor memory, and stage-counter memory to retain historical evidence and track execution state; evaluations show substantial limitations in existing policies on HIDE, while SEEK reaches 62.9% average success in simulation, 11.7 percentage points above the strongest baseline SAM2Act+, and 89% average success on four real-robot tasks.
Zhejiang University Nanjing University Shanghai Jiao Tong University Shanghai Artificial Intelligence Laboratory
Yansong Shi（First author）
HIDE SEEK Manipulation Memory under Partial Observability Robotic Manipulation
arXiv Sep 27, 2026
SEEK externalizes search evaluation criteria into a routable skill bank, improving listwise quality evaluation and attribution diagnosis in Kuaishou short-video search
The work proposes SEEK (Skill-routed Evaluation with Evolvable Knowledge), which externalizes specific search evaluation criteria into a skill bank, dynamically routes relevant skills for each query-result list pair, and employs a task-adapted listwise evaluator to produce page-level judgments and failure mode attribution; a two-stage training pipeline teaches the evaluator to align evaluation criteria with human preferences, while a replay-gated skill bank allows recurring evaluation knowledge gaps to be incorporated without model retraining; experiments on industrial short-video search show that SEEK improves listwise quality evaluation accuracy and achieves significant progress in attribution diagnosis, and SEEK has been deployed at Kuaishou, a platform with over 400 million daily activ
The work proposes SEEK (Skill-routed Evaluation with Evolvable Knowledge), which externalizes specific search evaluation criteria into a skill bank, dynamically routes relevant skills for each query-result list pair, and employs a task-adapted listwise evaluator to produce page-level judgments and failure mode attribution; a two-stage training pipeline teaches the evaluator to align evaluation criteria with human preferences, while a replay-gated skill bank allows recurring evaluation knowledge gaps to be incorporated without model retraining; experiments on industrial short-video search show that SEEK improves listwise quality evaluation accuracy and achieves significant progress in attribution diagnosis, and SEEK has been deployed at Kuaishou, a platform with over 400 million daily activ
Kuaishou (China)Peking University
Zhongxin Huang（First author）
SEEK Search quality evaluation Listwise evaluator

You’re all caught up