3 papers
cs.AI2026
Evidence Blindness in Direct Corpus Interaction: Persistent Navigation with AtlasNav
Hongyu Guo, Zhiyu Zheng, Zhao Cao
Large language model agents are moving beyond conventional retrieval-augmented generation toward direct interaction with external corpora. Direct Corpus Interaction (DCI) keeps the…
cs.AI2026
MemoBrain: Executive Memory as an Agentic Brain for Reasoning
Hongjin Qian, Zhao Cao, Zheng Liu
Complex reasoning in tool-augmented agent frameworks is inherently long-horizon, causing reasoning traces and transient tool artifacts to accumulate and strain the bounded working…
cs.CV2025
MomentSeeker: A Task-Oriented Benchmark For Long-Video Moment Retrieval
Huaying Yuan, Jian Ni, Zheng Liu +7
Accurately locating key moments within long videos is crucial for solving long video understanding (LVU) tasks. However, existing benchmarks are either severely limited in terms of…