通过预测提示影响范围，减少代码代理的冗余计算与资源浪费。
Blast Radius
- 构建双向上下文-代码通道预测提示影响范围，指导记忆管理。
- 在七款OpenAI模型上降低17%-26%的令牌消耗，零召回错误。
- 适合关注LLM可持续性与高效代码生成的研究者与开发者。
代理式编程面临成本高昂和令牌浪费的问题。我们提出Blast Radius，一个预测性内存管理模块，通过耦合上下文与代码通道估算输入提示的影响范围。NECROPHORESIS实现可逆淘汰，将失效上下文原样归档；反复出现的无用内容（重复死物，RDM）被识别并永久埋藏。我们在波兰上下文空间中建立可逆上下文淘汰机制，使保留、重复性与淘汰行为可度量，并将上下文熵与复活概率关联。在七款OpenAI模型上，Blast Radius降低17%-26%的令牌消耗，溢出率最低，且保持字节级可逆。450个被埋内容中，378个为重复死物，无一被召回。该系统位于HCRC之下，决定哪些记录应被埋藏以及提示可触及代码库的深度。本工作推动‘算法智慧’目标：让大语言模型与代理式编程更可复用、更可持续。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。