16 papers
Argus: A General-Purpose Agentic Reasoning Runtime for Long-Horizon Tasks
Boxiu Li, Zimo Wen, Yijia Fan +24
Long-horizon reasoning requires an agentic runtime that can persist when evidence supports its current approach and pivot when measurements reveal failure, hidden constraints, or a…
TEngineDB-V: An OLAP-Native Vector Search System for Large- Workloads at Tencent
Xufei Wu, Pengcheng Zhang, Yitong Song +11
Vector search systems are essential infrastructure for modern data-driven applications. Large- analytical vector search, which retrieves -- results for analytics (…
OmniOpt: Taxonomy, Geometry, and Benchmarking of Modern Optimizers
Siyuan Li, Jiabao Pan, Yumou Liu +9
Optimizer selection for large-scale model training has become a system-level design decision constrained jointly by compute, memory, tuning budget, and task diversity, yet the land…
CLIP: Lightweight Cosine-Law-Based Inverted-List Pruning for IVF-Based Vector Search
Yitong Song, Shuhang Lu, Xuanhe Zhou +2
Vector search has become a core component of modern multimodal retrieval systems. Among existing methods, inverted file (IVF)-based methods are widely adopted due to their scalabil…
Are We Ready For An Agent-Native Memory System?
Wei Zhou, Xuanhe Zhou, Shaokun Han +5
Memory for large language model (LLM) agents has rapidly evolved from simple retrieval-augmented mechanisms into a data management system that supports persistent information stora…
X+Slides: Benchmarking Audience-Conditioned Slide Generation
Haodong Chen, Xuanhe Zhou, Wei Zhou +6
Automatically generating slide decks from source documents is an important application of large language models (LLMs). Existing benchmarks primarily assess slide completeness and…