3 papers
cs.LG2026
EvoHarness-RL: Learning Self-Evolving Runtime Harness for Long-Horizon LLM Agents
Xuying Ning, Dongqi Fu, Tianxin Wei +13
Long-horizon LLM agents increasingly rely on external execution support to maintain state, track progress, invoke tools, verify outcomes, and reuse experience across interactions.…
cs.CL2026
Agentic Recommender System with Hierarchical Belief-State Memory
Xiang Shen, Yuhang Zhou, Yifan Wu +8
Memory-augmented LLM agents have advanced personalized recommendation, yet existing approaches universally adopt flat memory representations that conflate ephemeral signals with st…
cs.IR2025
Embedding-based Retrieval in Multimodal Content Moderation
Hanzhong Liang, Jinghao Shi, Xiang Shen +6
Video understanding plays a fundamental role for content moderation on short video platforms, enabling the detection of inappropriate content. While classification remains the domi…