ScholarPulse 日报 2026-09-09

2026-09-09 学术简报：2 篇。A-JIT通过嵌入AI代理实现软件的动态演化，使应用程序能实时适应用户需求并持续进化，开启自适应、自演进软件的新范式。

今日速览

序号	标题	来源	日期	主题	推荐等级
1	A-JIT: Agentic Just-In-Time Software Construction	arXiv	2026-09-09	AI-Agent	高
2	Can AI Agents Deliver Verifiable Network-Wide Outcomes Across Authority Boundaries?	arXiv	2026-09-09	RAG	高

重点论文与技术动态

1. A-JIT: Agentic Just-In-Time Software Construction

来源：arXiv
日期：2026-09-09
作者/机构：Mark Marron, Earl T. Barr
主题标签：AI-Agent, arXiv
推荐等级：高
分类：cs.SE, cs.AI

一句话结论

A-JIT通过嵌入AI代理实现软件的动态演化，使应用程序能实时适应用户需求并持续进化，开启自适应、自演进软件的新范式。

核心内容

A-JIT将应用程序定义为集成组装，包含代码、运行时支架和嵌入式AI代理，该代理持续观察系统使用和实时执行跟踪。
类似传统JIT编译器优化执行路径，A-JIT动态专业化软件逻辑、工作流和工具界面以匹配终端用户特定需求。
通过集成合成到应用生命周期，A-JIT支持动态构建缺失实现、生成新功能并连续适应用户行为，促进trace-driven human-AI co-construction。

方法与数据

摘要未明确。

价值判断

值得关注：开启自适应、自演进软件的新设计空间，通过trace-driven human-AI co-construction实现软件持续进化。
可复用点：嵌入式AI代理的实时观察与动态调整机制可复用于其他需自适应能力的软件系统。
局限/待核查：摘要未明确局限性。

摘要

Traditional software delivery assumes a static paradigm: code is constructed prior to execution and deployed as a fixed artifact. We present Agentic Just-In-Time Software Construction (A-JIT), a paradigm that replaces static binaries with dynamic, software systems that can perpetually evolve to meet changing demands. In A-JIT, an application is an integrated assembly comprising code, a runtime harness, and an embedded AI agent that continuously observes system usage and live execution traces. Much like a traditional JIT compiler specializes machine code to runtime execution paths, A-JIT specializes software logic, workflows, and tool interfaces to meet the specific needs of the end-user. By integrating synthesis directly into the ambient application lifecycle, A-JIT enables applications to dynamically construct missing implementations, generate new capabilities on the fly, and continuously adapt to end-user behavior. We demonstrate how this model supports trace-driven human-AI co-construction and opens a new design space for adaptive, self-evolving software.

2. Can AI Agents Deliver Verifiable Network-Wide Outcomes Across Authority Boundaries?

来源：arXiv
日期：2026-09-09
作者/机构：Tianzhu Zhang, Chih-Kai Huang, Meikang Qiu
主题标签：RAG, arXiv
推荐等级：高
分类：cs.NI, cs.AI, eess.SY

一句话结论

EvidenceNet通过运行时保证层有效验证了跨域网络操作的全局结果，解决证据碎片化问题。

核心内容

网络自动化中，AI代理因权限范围分割导致证据碎片化，无法确认远程设备响应或路由变更是否达成意图。
EvidenceNet的broker收集后配置观察，admission gate检查证据来源、时效性及规则符合性，verifier agent评估内容。
实验显示，后配置状态检查能识别配置记录无法建立的成功结果，且在证据来源错误、被替换或过时时拒绝完成。

方法与数据

实验基于真实路由网络进行验证。
摘要未明确具体数据集和方法细节。

价值判断

值得关注：解决跨域网络自动化中全局结果验证的核心难题，提升系统可靠性。
可复用点：运行时保证层架构可推广至其他分布式AI协调场景。
局限/待核查：摘要未提局限，但实验仅限路由网络，需扩展验证至更广网络类型。

摘要

AI agents are increasingly involved in network automation, where they can initiate configuration changes through mediated operational interfaces and assess the resulting state. Nonetheless, operational networks usually span many devices and administrative domains. Realizing an operator's intent requires coordinating agents with distinct authority scopes that define the resources they can access, the operations they can invoke, and the network state they can observe. This division limits the blast radius of an erroneous action but fragments the evidence needed to assess the network-wide outcome. Successful execution of a configuration action proposed by one agent does not establish that remote devices responded as intended or that routing changes reached the required devices. A valid observation may also become stale after a subsequent change. Before the coordinated operation can be declared complete, a trusted assurance layer must collect current observations from the required scopes and determine whether they collectively support the operator's intended network-wide outcome. To address the completion admission problem, we present EvidenceNet, a runtime assurance layer for deciding whether coordinated agent operations have achieved an operator's network intent. Its broker collects the post-change observations required by a completion contract, and its admission gate checks that the evidence comes from the required scopes, remains current, and satisfies the task rules. A verifier agent provides an additional assessment of the observation content. Experiments on live routing networks show that post-change state checks recognize successful outcomes that configuration-action records alone cannot establish. Controlled interventions further show that EvidenceNet rejects completion when otherwise satisfactory observations have the wrong source, have been substituted, or are stale.