3 papers
cs.CV2026
Weaving Visual Narratives: Agentic Image Bundle Composition Beyond Atomic Visual Matching
Rong Shan, Tianyi Xu, Congmin Zheng +9
Image retrieval has traditionally been formulated as a point-wise matching problem, where each candidate image is scored in isolation. However, this atomic paradigm fails to captur…
cs.CL2026
OThink-SRR1: Search, Refine and Reasoning with Reinforced Learning for Large Language Models
Haijian Liang, Zenghao Niu, Junjie Wu +3
Retrieval-Augmented Generation (RAG) expands the knowledge of Large Language Models (LLMs), yet current static retrieval methods struggle with complex, multi-hop problems. While re…
cs.AI2025
Proof-of-Use: Mitigating Tool-Call Hacking in Deep Research Agents
SHengjie Ma, Chenlong Deng, Jiaxin Mao +5
While reinforcement learning (RL) enhances their ability to plan and reason across retrieval steps, we identify a critical failure mode in this setting: Tool-Call Hacking. Unlike e…