{
  "schema": "vedokrok.public-item.v1",
  "release_id": "MHC-RPUB-20260920-75ad787a",
  "url": "/knowledge/detect-stagnation-separately-from-completion",
  "id": "MHC-D-RESEARCH-0947",
  "version": "0.1.0",
  "title": "Detect stagnation separately from completion",
  "summary": "More motion is not the same thing as more progress.",
  "kind": "protocol",
  "body": "Track a small progress signal—remaining checklist items, failing tests, unresolved claims, changed artifacts or another task-specific state. If several iterations repeat without reducing the remaining work, stop the normal loop and trigger replanning or human review. Do not let lack of progress masquerade as persistence.",
  "limits": [
    "Some valid work has delayed visible progress; choose signals that fit the task rather than using one generic iteration count."
  ],
  "topics": [
    "union-agent-loop-reliability"
  ],
  "intents": [],
  "source_ids": [
    "RS-A938C271AB252914"
  ],
  "evidence": [
    {
      "claim": "Long-horizon agent failure syntheses report compounding planning/execution failures and stalled behavior, supporting explicit progress diagnostics rather than outcome-only monitoring.",
      "source_id": "RS-A938C271AB252914",
      "role": "supports",
      "note": "Some valid work has delayed visible progress; choose signals that fit the task rather than using one generic iteration count.",
      "locator": "See source record"
    }
  ],
  "use_when": [
    "An agent is still acting but the task state is not improving."
  ],
  "avoid_when": [
    "Some valid work has delayed visible progress; choose signals that fit the task rather than using one generic iteration count."
  ],
  "example": "If three coding iterations leave the same two tests failing with nearly identical edits, switch from retrying to diagnosis.",
  "check": "The loop can identify 'not done and not improving' as a state distinct from both success and ordinary progress.",
  "steps": [
    "The loop can identify 'not done and not improving' as a state distinct from both success and ordinary progress."
  ],
  "sources": [
    {
      "id": "RS-A938C271AB252914",
      "title": "Beyond the Leaderboard: A Synthesis of Tool-Use, Planning, and Reasoning Failures in Large Language Model Agents",
      "url": "https://arxiv.org/abs/2607.05775"
    }
  ],
  "relations": [],
  "collections": [
    {
      "id": "RC-043A908C9263BF6A",
      "title": "Make the agent loop finish, recover and stay inspectable",
      "url": "/collections/make-the-agent-loop-finish-recover-and-stay-inspectable"
    }
  ]
}