PatternBloom 让 Agentic RAG 学会可复用的推理图模式
PatternBloom: Empowering Agentic RAG with Externalized RL-Distilled Graph Patterns
搞 RAG 智能体的值得看看：它不再只检索文本，而是把 RL 训练出的推理骨架存成图谱记忆给 agent 复用。7B 模型跑赢了 27 个基线 15 个点，代码也开源了，想做深度推理检索的团队可以直接抄作业。
PatternBloom 是一个新的 agentic RAG 框架，把检索单位从“读什么内容”转向“怎么推理”。方法分两阶段：第一段 RL 用冻结 oracle 的信息增益（Information-Density Reward，即尺寸归一化的互信息代理指标）给 agent 构建的证据图打分；高奖励轨迹被蒸馏成类型抽象的推理骨架库 Graph Pattern Memory（GPM）。
第二段 RL 引入 Pattern-Augmented Reward（PAR）把策略与 GPM 耦合，使过程性推理变成可外置、可复用的结构先验，而不是每次查询都重新推导。作者实验显示 7B 模型的 PatternBloom 在 27 个基线方法上平均超出 +15.0 Avg-OOD EM，且增益随推理深度增加而扩大，因为过程性知识被蒸馏后可跨查询复用。代码已在 GitHub 开源，对做 RAG 和智能体 RL 训练的团队有直接参考价值。
PatternBloom: Empowering Agentic RAG with Externalized RL-Distilled Graph Patterns
Reinforcement-learning-trained agents for retrieval-augmented generation retrieve content (passages, knowledge-graph fragments, or hyperedges) and supervise training with outcome rewards on the final answer. Across these paradigms the reasoning route through retrieved content never leaves the language model's hidden state, conflating declarative knowledge with the procedural knowledge that recurs across queries of the same logical type; content-only methods consequently plateau as reasoning depth grows. We introduce PatternBloom, an agentic RAG framework that shifts the unit of retrieval from content (what to read) to logic (how to reason). A first RL stage scores the agent's constructed evidence graph by a frozen oracle's information gain through the Information-Density Reward (IDR), a size-normalized mutual-information surrogate. High-reward trajectories are distilled into a Graph Pattern Memory (GPM) of type-abstracted reasoning skeletons, and a second RL stage uses the Pattern-Augmented Reward (PAR) to couple policy to memory, turning procedural reasoning into a learnable, externalized structural prior. A 7B PatternBloom outperforms $27$ baselines by $+15.0$ Avg-OOD EM, with the gain compounding with reasoning depth precisely because procedural knowledge, once distilled, is reused rather than re-derived at every query. We release our code at https://github.com/EllenYiGe/PatternBloom.
This report is categorized under AITOP's "Models" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows and US-China foundation model benchmarks and commercialization comparison. Key entities and technical topics under continuous tracking include PatternBloom, Agentic RAG, 强化学习, RAG.
Source attribution: curated from arXiv cs.AI (@Yi Ge, Heng Huang).
