发表机构
Algorithm Reconnaissance Division; Mankind Research Labs; North-West University; University of Pretoria（算法侦察部; 人类研究实验室; 西北大学; 比勒陀利亚大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对智能体编码的令牌浪费问题，提出Blast Radius内存管理层，结合NECROPHORESIS与RDM实现可逆上下文驱逐，在7个OpenAI模型上降低令牌消耗17%-26%，提升编码可持续性。
AI 中文摘要
智能体编码面临可负担性下降与令牌浪费日益严重的问题。我们提出Blast Radius，一种预测性内存管理层，用于估计输入提示通过耦合上下文与代码通道的覆盖范围。NECROPHORESIS通过逐字归档失效上下文实现可驱逐，而重复失效实体（Recurring Dead Matter，RDM）可识别并归档重复出现的文本。我们在Polish上下文空间上构建可逆转上下文驱逐机制，为保留、重复与驱逐提供可测量基础，同时将上下文熵与复活概率关联。在7个OpenAI模型上，Blast Radius将令牌消耗降低17%-26%，在所有测试策略中实现最低溢出率，且保持字节级可逆。在450个归档实体中，378个为重复失效实体，无被召回实体。Blast Radius在HCRC下方运行，确定需归档的记录及输入提示在代码库中的覆盖范围。本研究为Algosophy的更广泛目标作出贡献：使大语言模型与智能体编码更具可复用性与可持续性。
英文摘要
Agentic coding faces growing problems of affordability and wasted tokens. We introduce Blast Radius, a predictive memory management layer that estimates an incoming prompt's reach through coupled context and code channels. NECROPHORESIS enables reversible eviction by archiving dead context verbatim, while Recurring Dead Matter (RDM) identifies and buries repeatedly occurring transcripts. We formulate reversible context eviction over a Polish context space, providing a measurable foundation for retention, recurrence, and eviction while connecting context entropy to resurrection probability. Across seven OpenAI models, Blast Radius reduced token consumption by 17-26%, achieved the lowest overflow rate among tested policies, and remained byte exact reversible. Of 450 buried bodies, 378 were recurring dead matter and zero were recalled. Blast Radius operates beneath HCRC, determining which records to bury and how far an incoming prompt may reach into the codebase. This work contributes to the broader goal of Algosophy: making large language models and agentic coding more reusable and sustainable.
Commentsmajor revisions are needed and this will be restored later on
