1
Context-Aware RL for Agentic and Multimodal LLMs
通过上下文感知强化学习，让大模型在长上下文中精准定位关键证据，提升推理与多模态能力。
arXiv:2606.17053v1 Announce Type: cross Abstract: Large language models (LLMs) often fail when answering requires identifying a small but decisive pie…