{
  "schema_version": "1.1",
  "id": "s13:https://arxiv.org/abs/2611.03601v1",
  "slug": "2611-03601v1-03z1nfj",
  "url": "https://feed7.dev/p/2611-03601v1-03z1nfj",
  "title": "DiabAgent: Toward Agentic Physiological Control",
  "why_included": "DiabAgent evaluates sustained agentic glucose control with a simulator and 212-task benchmark. In the reported setup, its agent framework scored above the OpenAPS baseline on COGI.",
  "summary": "DiabAgent combines the **APC framework**, DiabetSim simulator, and SweetBench benchmark. SweetBench instantiates **32 scenario designs as 212 tasks**; with Claude Opus 5.5 and hourly decisions, APC scored 73.5 COGI versus 71.2 for the OpenAPS baseline.",
  "practical_implication": "For builders of long-running tool agents, the setup highlights per-user adaptation, accumulated experience, and context such as meals or exercise. The authors also explore combining frequent rule-based control with less frequent agent decisions.",
  "agent_context": "DiabAgent combines the **APC framework**, DiabetSim simulator, and SweetBench benchmark. SweetBench instantiates **32 scenario designs as 212 tasks**; with Claude Opus 5.5 and hourly decisions, APC scored 73.5 COGI versus 71.2 for the OpenAPS baseline.\n\nFor builders of long-running tool agents, the setup highlights per-user adaptation, accumulated experience, and context such as meals or exercise. The authors also explore combining frequent rule-based control with less frequent agent decisions.\n\nThis is a virtual research evaluation for type 1 diabetes control. The supplied material does not establish safety or effectiveness in real clinical use.",
  "source": {
    "name": "arXiv",
    "url": "https://arxiv.org/abs/2611.03601v1",
    "published_at": "2026-11-02T18:41:02.000Z"
  },
  "source_class": "blog_post",
  "content_type": "Paper",
  "layer": "benchmark",
  "domains": [
    "research",
    "data"
  ],
  "topics": [
    "agent-evals",
    "agent-reliability",
    "tool-use"
  ],
  "verification": {
    "status": "needs_review",
    "label": "Needs Review",
    "method": "unverified",
    "verified_at": null
  },
  "uncertainty": [
    "This is a virtual research evaluation for type 1 diabetes control. The supplied material does not establish safety or effectiveness in real clinical use."
  ],
  "connected_context": {
    "meaning": "DiabAgent adds a simulated, personalized control benchmark with explicit experience and context, and compares its agent to an established controller. The result supports evaluating agents on sustained decisions in a domain-specific simulator, while the virtual setting leaves real-world clinical safety unresolved.",
    "corpus_size": 990,
    "generated_at": "2026-11-03T13:56:32.625Z",
    "connections": [
      {
        "title": "Simulated Control Evals",
        "source_name": "arXiv",
        "source_url": "https://arxiv.org/abs/2610.31593v1",
        "feed7_url": "https://feed7.dev/p/2610-31593v1-1lanp1p",
        "reason": "Both evaluate consequential agent control in simulated environments; Simulated Control Evals specifically cautions that simulated results are deployment-specific and do not replace executed safety evidence."
      },
      {
        "title": "Patient-specific rubric-based evaluation of large language models across longitudinal cancer care",
        "source_name": "arXiv",
        "source_url": "https://arxiv.org/abs/2610.35847v1",
        "feed7_url": "https://feed7.dev/p/2610-35847v1-0se27hb",
        "reason": "Both concern clinical agent evaluation across context-dependent decisions; the cancer-care benchmark shows why aggregate performance may obscure failures that vary by workflow phase."
      },
      {
        "title": "AgentHPOBench: A Benchmark For Evaluating LLM Agents as Sequential Hyperparameter Optimizers",
        "source_name": "arXiv",
        "source_url": "https://arxiv.org/abs/2607.29626v1",
        "feed7_url": "https://feed7.dev/p/2607-29626v1-1dfg6xz",
        "reason": "DiabAgent emphasizes accumulated experience and per-user adaptation, while AgentHPOBench tests whether agents improve through sequential history; together they point to evaluating sustained behavior, not only isolated outputs."
      }
    ]
  },
  "lifecycle": "Current",
  "published_at": "2026-11-02T18:41:02.000Z",
  "modified_at": "2026-11-02T18:41:02.000Z",
  "supersedes": [],
  "expires_at": null,
  "formats": {
    "html": "https://feed7.dev/p/2611-03601v1-03z1nfj",
    "json": "https://feed7.dev/p/2611-03601v1-03z1nfj.json",
    "markdown": "https://feed7.dev/p/2611-03601v1-03z1nfj.md"
  }
}