{
  "schema_version": "1.1",
  "id": "archive:https://arxiv.org/abs/2608.07440v1",
  "slug": "2608-07440v1-1gi5t78",
  "url": "https://feed7.dev/p/2608-07440v1-1gi5t78",
  "title": "Blast Radius",
  "why_included": "Blast Radius predicts which code and context a prompt will reach, then reversibly archives unused history. Across seven OpenAI models, it cut token consumption by 17–26%.",
  "summary": "Blast Radius manages coding-agent memory by estimating a prompt’s reach across context and code. Across **seven OpenAI models**, it reduced token use by **17–26%** while keeping archived context byte-exact and reversible.",
  "practical_implication": "For long-running agents, consider eviction policies that archive rather than summarize context, and track repeated transcripts separately. The paper classified **378 of 450** evicted records as recurring dead matter.",
  "agent_context": "Blast Radius manages coding-agent memory by estimating a prompt’s reach across context and code. Across **seven OpenAI models**, it reduced token use by **17–26%** while keeping archived context byte-exact and reversible.\n\nFor long-running agents, consider eviction policies that archive rather than summarize context, and track repeated transcripts separately. The paper classified **378 of 450** evicted records as recurring dead matter.\n\nThe evidence comes from the authors’ tested policies and models. **Zero archived records were recalled**, but that observation does not establish how eviction behaves across other repositories, workflows, or longer horizons.",
  "source": {
    "name": "arXiv",
    "url": "https://arxiv.org/abs/2608.07440v1",
    "published_at": "2026-08-07T17:23:53.000Z"
  },
  "source_class": "blog_post",
  "content_type": "Paper",
  "layer": "context",
  "domains": [
    "coding"
  ],
  "topics": [
    "context-engineering",
    "context-caching",
    "agent-memory"
  ],
  "verification": {
    "status": "needs_review",
    "label": "Needs Review",
    "method": "unverified",
    "verified_at": null
  },
  "uncertainty": [
    "The evidence comes from the authors’ tested policies and models. **Zero archived records were recalled**, but that observation does not establish how eviction behaves across other repositories, workflows, or longer horizons."
  ],
  "connected_context": {
    "meaning": "This narrows long-context memory management to a reversible eviction problem: repeated prompt debris can be removed without lossy summarization or deleting its source record. It complements durable shared-memory proposals but does not show that archived material is useful later—the absence of recalls leaves retrieval policy, provenance, and long-horizon behavior unresolved.",
    "corpus_size": 409,
    "generated_at": "2026-08-10T10:05:42.678Z",
    "connections": [
      {
        "title": "Chained Recursive Language Models for Multi-Iteration Reasoning",
        "source_name": "arXiv",
        "source_url": "https://arxiv.org/abs/2608.05124v1",
        "feed7_url": "https://feed7.dev/p/2608-05124v1-05haobv",
        "reason": "Chained RLM preserves summaries between fresh contexts, whereas Blast Radius archives evicted records byte-exactly; together they expose a tradeoff between compact carried state and reversible source preservation."
      },
      {
        "title": "TencentCloud/TencentDB-Agent-Memory",
        "source_name": "GitHub",
        "source_url": "https://github.com/TencentCloud/TencentDB-Agent-Memory",
        "feed7_url": "https://feed7.dev/p/tencentdb-agent-memory-0gx8nnn",
        "reason": "The memory hub provides a governed destination for reusable context, while Blast Radius addresses which prompt records should leave active context; combining the ideas would require an explicit recall policy that Blast Radius did not exercise."
      },
      {
        "title": "WTF Is the Context Layer? The Missing Infrastructure for Production Agents — Prukalpa Sankar",
        "source_name": "AI Engineer",
        "source_url": "https://www.youtube.com/watch?v=8G_1-3IO4ZQ",
        "feed7_url": "https://feed7.dev/p/wtf-is-the-context-layer-the-missing-infrastructure-for-production-agent-0t47xqf",
        "reason": "Shared, versioned context separates durable organizational knowledge from an individual agent prompt, reinforcing Blast Radius’s distinction between preserving a record and keeping it continuously in active context."
      }
    ]
  },
  "lifecycle": "Current",
  "published_at": "2026-08-07T17:23:53.000Z",
  "modified_at": "2026-08-07T17:23:53.000Z",
  "supersedes": [],
  "expires_at": null,
  "formats": {
    "html": "https://feed7.dev/p/2608-07440v1-1gi5t78",
    "json": "https://feed7.dev/p/2608-07440v1-1gi5t78.json",
    "markdown": "https://feed7.dev/p/2608-07440v1-1gi5t78.md"
  }
}