{
  "schema_version": "1.1",
  "id": "s13:https://arxiv.org/abs/2611.06914v1",
  "slug": "2611-06914v1-1tz1eo5",
  "url": "https://feed7.dev/p/2611-06914v1-1tz1eo5",
  "title": "A Framework for Context Enrichment and Selective Robustness in LLM Social Agents",
  "why_included": "The paper tests whether richer prompts make simulated LLM agents less brittle. Its selective-robustness criterion may help builders distinguish useful context from wording that merely changes behavior.",
  "summary": "The framework compares four prompt enrichments: neutral padding, generic social background, descriptive grounding, and normative grounding. It defines selective robustness as resisting meaning-preserving prompt changes while responding directionally to relevant changes in the world. In a Prisoner’s Dilemma-like game, enrichment produced distinct behavior across **two models**.",
  "practical_implication": "When evaluating an agent, vary prompt wording separately from decision-relevant facts. Check that behavior stays stable under the first and changes appropriately under the second; adding background alone is not evidence of better grounding.",
  "agent_context": "The framework compares four prompt enrichments: neutral padding, generic social background, descriptive grounding, and normative grounding. It defines selective robustness as resisting meaning-preserving prompt changes while responding directionally to relevant changes in the world. In a Prisoner’s Dilemma-like game, enrichment produced distinct behavior across **two models**.\n\nWhen evaluating an agent, vary prompt wording separately from decision-relevant facts. Check that behavior stays stable under the first and changes appropriately under the second; adding background alone is not evidence of better grounding.\n\nThe results are from a social simulation, and the paper says enrichment effects varied by model. The material does not establish which prompt type generalizes to coding agents or real tasks.",
  "source": {
    "name": "arXiv",
    "url": "https://arxiv.org/abs/2611.06914v1",
    "published_at": "2026-11-04T18:58:23.000Z"
  },
  "source_class": "blog_post",
  "content_type": "Paper",
  "layer": "context",
  "domains": [
    "research"
  ],
  "topics": [
    "context-engineering",
    "prompting",
    "agent-reliability"
  ],
  "verification": {
    "status": "needs_review",
    "label": "Needs Review",
    "method": "unverified",
    "verified_at": null
  },
  "uncertainty": [
    "The results are from a social simulation, and the paper says enrichment effects varied by model. The material does not establish which prompt type generalizes to coding agents or real tasks."
  ],
  "connected_context": {
    "meaning": "This paper separates robustness to meaning-preserving prompt variation from responsiveness to relevant changes in the world, and tests the distinction in a social simulation with two models. It gives an evaluation principle for context behavior, but does not show that any enrichment method transfers to coding agents or real tasks.",
    "corpus_size": 1009,
    "generated_at": "2026-11-05T11:04:12.602Z",
    "connections": [
      {
        "title": "Learning When to Trust via Selective Context Preference Optimization",
        "source_name": "arXiv",
        "source_url": "https://arxiv.org/abs/2608.06377v1",
        "feed7_url": "https://feed7.dev/p/2608-06377v1-0rvbpra",
        "reason": "Both frame robustness as using relevant evidence while resisting misleading or irrelevant context; this paper adds a direct distinction between wording changes and decision-relevant world changes."
      },
      {
        "title": "AISPA: User-Centric System Prompt Auditing for Large Language Model Applications",
        "source_name": "arXiv",
        "source_url": "https://arxiv.org/abs/2607.28617v1",
        "feed7_url": "https://feed7.dev/p/2607-28617v1-1cbh1qu",
        "reason": "Both motivate behavioral evaluation of prompts rather than relying on prompt inspection alone; AISPA audits instruction properties, while this framework tests response stability and direction under controlled changes."
      }
    ]
  },
  "lifecycle": "Current",
  "published_at": "2026-11-04T18:58:23.000Z",
  "modified_at": "2026-11-04T18:58:23.000Z",
  "supersedes": [],
  "expires_at": null,
  "formats": {
    "html": "https://feed7.dev/p/2611-06914v1-1tz1eo5",
    "json": "https://feed7.dev/p/2611-06914v1-1tz1eo5.json",
    "markdown": "https://feed7.dev/p/2611-06914v1-1tz1eo5.md"
  }
}