1
CRANE: Knowledge Editing for Reasoning MLLMs
推理多模态大模型的知识编辑面临新挑战:传统方法看似完美实则暗藏隐患。
arXiv:2606.09033v1 Announce Type: cross Abstract: The emergence of reasoning multimodal large language models (MLLMs), which generate explicit chain-o…
推理多模态大模型的知识编辑面临新挑战:传统方法看似完美实则暗藏隐患。
arXiv:2606.09033v1 Announce Type: cross Abstract: The emergence of reasoning multimodal large language models (MLLMs), which generate explicit chain-o…
提出CRANE方法,通过零空间编辑向代码代理注入约束推理,巧妙平衡指令模型的简洁纪律与思考模型的规划韧性,为智能体模型对齐提供新思路。
arXiv:2605.14084v1 Announce Type: cross Abstract: Code agents must both reason over long-horizon repository state and obey strict tool-use protocols. …