Blast Radius· Blast Radius
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 r
减少 AI 代理代码执行时的令牌浪费和成本问题。
- 核心方法
- 引入Blast Radius，一种预测性内存管理层，通过结合上下文和代码通道来估计即将到达提示的影响范围，使用NECROPHORESIS存档不再需要的上下文，RDM识别并处理重复出现的脚本。
- 适合谁读
- 研究者 / 工程师
- 要解决的问题
- AI 代理在代码执行中面临日益严重的价格昂贵和令牌浪费的问题。
- 关键实验
- 在七个OpenAI模型上测试，评估了Blast Radius对令牌消耗、溢出率的影响，并进行了378次成功的上下文再现试验。
- 主要贡献
- Blast Radius在多个OpenAI模型中减少17-26%的令牌消耗，达到最低的溢出率，并确保字节完全可逆。
- 意义与局限
- 提升了AI代理操作的效率和经济性，但可能需要进一步研究其在不同上下文下的适用性和长期影响。