{
  "schema_version": "1.1",
  "id": "s13:https://arxiv.org/abs/2608.02553v1",
  "slug": "2608-02553v1-12y8joy",
  "url": "https://feed7.dev/p/2608-02553v1-12y8joy",
  "title": "A Taxonomy of Cognitive Capability Gaps in Generative and Agentic AI",
  "why_included": "This survey organizes long-horizon agent weaknesses into five capability gaps, offering a useful checklist for harness design and evaluation rather than a new implementation.",
  "summary": "The survey groups cognitive capability gaps into **five dimensions**: persistent state, goal-directed autonomy, self-monitoring and control, environment interaction, and learning and adaptation. It also proposes a conceptual **ACIA architecture** and discusses cognition-focused evaluation.",
  "practical_implication": "Use the taxonomy as a review checklist for long-running coding agents: inspect how state persists, goals remain bounded, failures are detected, tools affect the environment, and feedback changes later behavior. It can also help separate harness problems from model limitations.",
  "agent_context": "The survey groups cognitive capability gaps into **five dimensions**: persistent state, goal-directed autonomy, self-monitoring and control, environment interaction, and learning and adaptation. It also proposes a conceptual **ACIA architecture** and discusses cognition-focused evaluation.\n\nUse the taxonomy as a review checklist for long-running coding agents: inspect how state persists, goals remain bounded, failures are detected, tools affect the environment, and feedback changes later behavior. It can also help separate harness problems from model limitations.\n\nThis is a literature-organizing framework, not a validated agent stack or benchmark result. The supplied material offers no implementation details, comparative measurements, or evidence that ACIA improves reliability in deployed systems.",
  "source": {
    "name": "arXiv",
    "url": "https://arxiv.org/abs/2608.02553v1",
    "published_at": "2026-08-03T17:37:38.000Z"
  },
  "source_class": "blog_post",
  "content_type": "Paper",
  "layer": "agent",
  "domains": [
    "research"
  ],
  "topics": [
    "agent-memory",
    "agent-reliability",
    "harness-engineering"
  ],
  "verification": {
    "status": "needs_review",
    "label": "Needs Review",
    "method": "unverified",
    "verified_at": null
  },
  "uncertainty": [
    "This is a literature-organizing framework, not a validated agent stack or benchmark result. The supplied material offers no implementation details, comparative measurements, or evidence that ACIA improves reliability in deployed systems."
  ],
  "connected_context": {
    "meaning": "This consolidates scattered agent-reliability concerns into five review dimensions, helping teams distinguish missing model capability from missing harness support. It confirms that durable state, bounded goals, monitoring, controlled action, and adaptation should be assessed separately. Because ACIA is conceptual, the taxonomy organizes requirements but does not validate an architecture or replace task-specific controls and evaluations.",
    "corpus_size": 340,
    "generated_at": "2026-08-04T10:05:44.081Z",
    "connections": [
      {
        "title": "AI Agents for Performance: Ship Faster, Pay Less — Rajat Shah, Netflix",
        "source_name": "AI Engineer",
        "source_url": "https://www.youtube.com/watch?v=CgsWxRUY5Eo",
        "feed7_url": "https://feed7.dev/p/ai-agents-for-performance-ship-faster-pay-less-rajat-shah-netflix-1c2tvq2",
        "reason": "Netflix’s bounded optimization workflow supplies a concrete instance of the taxonomy’s state, environment-interaction, and self-monitoring dimensions through commit-linked evidence, canaries, and engineer release gates."
      },
      {
        "title": "The Physics of Multi-Turn Long-Horizon Planning: From Pre-training to Post-training via Single- and Multi-Teacher On-Policy Agentic Distillation",
        "source_name": "arXiv",
        "source_url": "https://arxiv.org/abs/2607.24720v1",
        "feed7_url": "https://feed7.dev/p/2607-24720v1-0gihy13",
        "reason": "The finding that long-horizon planning needs explicit state transitions and compositional trajectories provides experimental support for treating persistent state and goal-directed autonomy as separable capability gaps."
      },
      {
        "title": "Learning on the Job: The Future of Post-Training — Raymond Feng, Applied Compute",
        "source_name": "AI Engineer",
        "source_url": "https://www.youtube.com/watch?v=k35LeKZEhiE",
        "feed7_url": "https://feed7.dev/p/learning-on-the-job-the-future-of-post-training-raymond-feng-applied-com-17u0m7t",
        "reason": "Production-harness training directly concerns the taxonomy’s learning-and-adaptation dimension, while its non-replayable feedback problem shows why naming that capability does not establish a workable update mechanism."
      },
      {
        "title": "Build for the Memo, Not the Demo — Shawn Chan, China Resources Holdings",
        "source_name": "AI Engineer",
        "source_url": "https://www.youtube.com/watch?v=tJFjeMBKbIY",
        "feed7_url": "https://feed7.dev/p/build-for-the-memo-not-the-demo-shawn-chan-china-resources-holdings-0i3s3oo",
        "reason": "Claim provenance, uncertainty, contradiction checks, and logged approval turn the taxonomy’s self-monitoring and controlled interaction dimensions into explicit output and release contracts for a high-stakes domain."
      }
    ]
  },
  "lifecycle": "Current",
  "published_at": "2026-08-03T17:37:38.000Z",
  "modified_at": "2026-08-03T17:37:38.000Z",
  "supersedes": [],
  "expires_at": null,
  "formats": {
    "html": "https://feed7.dev/p/2608-02553v1-12y8joy",
    "json": "https://feed7.dev/p/2608-02553v1-12y8joy.json",
    "markdown": "https://feed7.dev/p/2608-02553v1-12y8joy.md"
  }
}