mlsanityData to 14 Oct 2026

Blast Radius

arXiv 2608.07440 ↗First posted 7 Aug 2026cs.AIcited by 0

On the map: LLM agents and tool use → Agent memory systems

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.

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.

Builds on

25 of 67 references.

Closest ancestors · 3

Same direction, newest first

  1. 2026ContextWeaver: Selective and Dependency-Structured Memory Construction for LLM Agents24 Apr
  2. 2026MemMachine: A Ground-Truth-Preserving Memory System for Personalized AI Agents6 Apr
  3. 2025Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory28 Apr

Other references · 22

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  2. 2023SWE-bench: Can Language Models Resolve Real-World GitHub Issues?cited by 3,373
  3. 2023Efficient Streaming Language Models with Attention Sinkscited by 2,186
  4. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,839
  5. 2024SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineeringcited by 1,737
  6. 2023MemGPT: Towards LLMs as Operating Systemscited by 1,389
  7. 2023Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generationcited by 819
  8. 2023Model Tells You What to Discard: Adaptive KV Cache Compression for LLMscited by 474
  9. 2023Scissorhands: Exploiting the Persistence of Importance Hypothesis for LLM KV Cache Compression at Test Timecited by 439
  10. 2024LongRoPE: Extending LLM Context Window Beyond 2 Million Tokenscited by 313
  11. 2023LLMLingua: Compressing Prompts for Accelerated Inference of Large Language Modelscited by 287
  12. 2024The Power of Noise: Redefining Retrieval for RAG Systemscited by 281
10 more
  1. 2023Compressing Context to Enhance Inference Efficiency of Large Language Modelscited by 189
  2. 2024To Believe or Not to Believe Your LLMcited by 120
  3. 2023Recursively Summarizing Enables Long-Term Dialogue Memory in Large Language Modelscited by 62
  4. 2024Mixture of Attention Spans: Optimizing LLM Inference Efficiency with Heterogeneous Sliding-Window Lengthscited by 44
  5. 2025Synergizing RAG and Reasoning: A Systematic Reviewcited by 27
  6. 2024Attention Entropy is a Key Factor: An Analysis of Parallel Context Encoding with Full-attention-based Pre-trained Language Modelscited by 26
  7. 2026The Missing Memory Hierarchy: Demand Paging for LLM Context Windowscited by 8
  8. 2022Density functions of periodic sequencescited by 2
  9. 2017High Performance Canny Edge Detector using Parallel Patterns for Scalability on Modern Multicore Processorscited by 1
  10. 2026Heaviside Continuity of Rolling Coefficients for Eliminating Epistemic Entropy in Large Language Modelscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Why Does CLAUDE.md Keep Growing? Catastrophic Remembering in Agentic Coding
  2. 2026Toward Reliable Context Compression for Long-Horizon Agents: An Empirical Study of Execution Instability
  3. 2026MemDecay: Region-Aware KV Cache Eviction for Efficient LLM Agent Inference
  4. 2026Memory as Infrastructure: Reliability Engineering for Persistent Agent Memory in Months-Long LLM-Assisted Development
  5. 2026Adapting Context Compression for Long-Horizon Agents with Counterfactual Continuations
  6. 2025ACON: Optimizing Context Compression for Long-horizon LLM Agents
  7. 2026PROJECTMEM: A Local-First, Event-Sourced Memory and Judgment Layer for AI Coding Agents
  8. 2026Memory for Autonomous LLM Agents:Mechanisms, Evaluation, and Emerging Frontiers