arXiv · cs.AI · Lang Mo, Xingxuan Zhang, Qi Wang, Mingchao Hao, Hao Yuan, Chunjing Gan, Wang Lu, Peng Cui · 12 小时前模型评分50
DPDM：用共享条件预测器统一智能体决策
Decoupled Predictive Decision Making: A Shared Conditional Predictor for Agents
导读
研究者提出解耦预测决策架构（DPDM，Decoupled Predictive Decision Making），把智能体的多种决策统一为条件预测，由语言模型编码当前与历史记录，再由一个冻结的 LimiX-2 预测器输出任务目标，无需更新任何神经参数。
分类置信度
中 · 待人工复核
- 只有单一媒体来源，需要人工复核。
来源级别：媒体与个人
事件类型：研究发布
证据摘录
- “We introduce Decoupled Predictive Decision Making (DPDM), an architecture that formulates heterogeneous agent decisions as conditional prediction with a shared pretrained learner.”
- “Pretraining supplies reusable inference capability; deployment evidence instantiates problem-specific predictions without updating either model's neural parameters.”
- “A single frozen LimiX-2 predictor serves all five task categories.”
- “With Qwen3.5-27B as the semantic encoder, DPDM raises mean accuracy across 50 benchmarks from 78.80% with few-shot prompting to 84.92% under their respective evaluated history budgets, and reaches 82.33% with identical histories and queries.”
来源：arXiv · cs.AI · arxiv.org