[论文] From Events to Reasoning: Hierarchical Rule Composition over Explic...

论文概要

研究领域: ML 作者: Cheng Lyu, Xueqi Wang 发布时间: 2026-10-19 arXiv: 2610.22403

中文摘要

推理系统给出的不仅是结论，还必须欠一份 justification（正当化说明）：每个操作须在可得事实上可采纳，中间结果的依赖须保留到路径终点，前提变化时路径须可修正。ERS（事件推理系统）把推理状态建成显式事件图：语义特征提名候选对象与规则绑定，由声明的规则和任务条件决定哪些可执行——违反时段、单位或证据约束的候选无法进入被接受的推理路径。底层规则提供可复用的局部变换，可递归组合的高层控制规则依据当前目标、信息缺口和预算组织子目标与合法路径；有限规则库由此重组成从未作为完整解存储的路径。形式化方面涵盖可采纳转移、任务相关控制、组合表达力、保依赖修正，以及可达解与预算控制下可求解之间的鸿沟。在结构化事件图上，ERS 构建最长 12 步的依赖链；前瞻增至 16 时把无关已执行领域操作从 32 个降到 0；24 个负例中无一产生无依据的目标输出；规则冻结后通过 12/12 项聚焦检查（9 个含未见输入/路径组合的接受推导、3 个有理由的拒绝）与 6/6 事实变更案例；在 14 个联合求解的开发任务上，动态子目标配置比单级全局控制节省 51.6% 的推理墙钟时间。

原文摘要

What a reasoning system emits is a conclusion; what it owes is a justification. Producing one requires every operation to be admissible on the facts actually available, the dependencies of intermediate results to survive to the end of the path, and the path to be revised when a premise changes. We present the Event Reasoning System (ERS), in which the reasoning state is an explicit event graph. Semantic features nominate candidate objects and rule bindings, and declared rule and task conditions decide which may execute, so candidates that violate the represented period, unit, or evidence constraints cannot enter an accepted reasoning path. Low-level rules provide reusable local transformations, and recursively composable high-level control rules organize subgoals and legal paths under the current goal, information gaps, and budget; a finite library is thereby rebound into paths never stored as complete solutions. We formalize admissible transitions, task-dependent control, compositional expressivity, dependency-preserving revision, and the gap between reachable solutions and those a budgeted controller finds. On structured-event graphs, ERS builds dependency chains of up to twelve steps, cuts irrelevant executed domain operations from 32 to 0 as lookahead grows to 16, and produces no unsupported target output across 24 negative cases; with rules frozen, it passes 12/12 focused checks comprising nine accepted derivations involving unseen input/path combinations and three justified refusals, as well as 6/6 fact-change cases. On fourteen jointly solved development tasks, the recorded dynamic subgoal configuration uses 51.6% less inference wall-clock time than single-level global control under their respective frozen settings.

---

*自动采集于 2026-10-19*

#论文 #arXiv #ML #小凯