# Blast Radius

arXiv: https://arxiv.org/abs/2608.07440 · HTML: https://mlsanity.com/paper/2608.07440/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Agent memory systems, one of 16 directions in LLM agents and tool use.
- Builds on 25 of its 67 references that are in the map.
- First posted on arXiv 7 Aug 2026.

## Placed in

- LLM agents and tool use / [Agent memory systems](https://mlsanity.com/agents/agent-memory-systems/)

## Builds on (most cited first, 25 of 25)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [Efficient Streaming Language Models with Attention Sinks](https://mlsanity.com/paper/2309.17453/) (2023)
- [Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection](https://mlsanity.com/paper/2310.11511/) (2023)
- [SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](https://mlsanity.com/paper/2405.15793/) (2024)
- [MemGPT: Towards LLMs as Operating Systems](https://mlsanity.com/paper/2310.08560/) (2023)
- [Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation](https://mlsanity.com/paper/2302.09664/) (2023)
- [Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory](https://mlsanity.com/paper/2504.19413/) (2025)
- [Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs](https://mlsanity.com/paper/2310.01801/) (2023)
- [Scissorhands: Exploiting the Persistence of Importance Hypothesis for LLM KV Cache Compression at Test Time](https://mlsanity.com/paper/2305.17118/) (2023)
- [LongRoPE: Extending LLM Context Window Beyond 2 Million Tokens](https://mlsanity.com/paper/2402.13753/) (2024)
- [LLMLingua: Compressing Prompts for Accelerated Inference of Large Language Models](https://mlsanity.com/paper/2310.05736/) (2023)
- [The Power of Noise: Redefining Retrieval for RAG Systems](https://mlsanity.com/paper/2401.14887/) (2024)
- [Compressing Context to Enhance Inference Efficiency of Large Language Models](https://mlsanity.com/paper/2310.06201/) (2023)
- [To Believe or Not to Believe Your LLM](https://mlsanity.com/paper/2406.02543/) (2024)
- [Recursively Summarizing Enables Long-Term Dialogue Memory in Large Language Models](https://mlsanity.com/paper/2308.15022/) (2023)
- [Mixture of Attention Spans: Optimizing LLM Inference Efficiency with Heterogeneous Sliding-Window Lengths](https://mlsanity.com/paper/2406.14909/) (2024)
- [Synergizing RAG and Reasoning: A Systematic Review](https://mlsanity.com/paper/2504.15909/) (2025)
- [Attention Entropy is a Key Factor: An Analysis of Parallel Context Encoding with Full-attention-based Pre-trained Language Models](https://mlsanity.com/paper/2412.16545/) (2024)
- [MemMachine: A Ground-Truth-Preserving Memory System for Personalized AI Agents](https://mlsanity.com/paper/2604.04853/) (2026)
- [The Missing Memory Hierarchy: Demand Paging for LLM Context Windows](https://mlsanity.com/paper/2603.09023/) (2026)
- [ContextWeaver: Selective and Dependency-Structured Memory Construction for LLM Agents](https://mlsanity.com/paper/2604.23069/) (2026)
- [Density functions of periodic sequences](https://mlsanity.com/paper/2205.02226/) (2022)
- [High Performance Canny Edge Detector using Parallel Patterns for Scalability on Modern Multicore Processors](https://mlsanity.com/paper/1710.07745/) (2017)
- [Heaviside Continuity of Rolling Coefficients for Eliminating Epistemic Entropy in Large Language Models](https://mlsanity.com/paper/2607.04562/) (2026)

## Abstract (arXiv)

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.