{
  "schema_version": "1.1",
  "id": "archive:https://arxiv.org/abs/2608.06377v1",
  "slug": "2608-06377v1-0rvbpra",
  "url": "https://feed7.dev/p/2608-06377v1-0rvbpra",
  "title": "Learning When to Trust via Selective Context Preference Optimization",
  "why_included": "MIST tests whether models use good context while resisting bad context, exposing agents that appear robust only because they ignore external evidence altogether.",
  "summary": "MIST renders each reasoning item under **four matched conditions**: clean, misleading, correct-context, and irrelevant-context. Its **SC2W** metric counts cases where misleading context flips an otherwise correct answer to wrong.",
  "practical_implication": "Evaluate retrieval-augmented agents for selective trust, not only prompt-injection resistance. The proposed **SCOPE** method trains on matched preference pairs balanced across all four conditions so resistance does not come from ignoring useful context.",
  "agent_context": "MIST renders each reasoning item under **four matched conditions**: clean, misleading, correct-context, and irrelevant-context. Its **SC2W** metric counts cases where misleading context flips an otherwise correct answer to wrong.\n\nEvaluate retrieval-augmented agents for selective trust, not only prompt-injection resistance. The proposed **SCOPE** method trains on matched preference pairs balanced across all four conditions so resistance does not come from ignoring useful context.\n\nThe abstract reports reduced susceptibility on popular open models while preserving other-condition accuracy, but provides no numerical effect sizes here. Broader generalization beyond the benchmark's reasoning items remains an open question from the supplied material.",
  "source": {
    "name": "arXiv",
    "url": "https://arxiv.org/abs/2608.06377v1",
    "published_at": "2026-08-06T17:59:58.000Z"
  },
  "source_class": "blog_post",
  "content_type": "Paper",
  "layer": "benchmark",
  "domains": [
    "research"
  ],
  "topics": [
    "agent-evals",
    "agent-reliability",
    "context-engineering"
  ],
  "verification": {
    "status": "needs_review",
    "label": "Needs Review",
    "method": "unverified",
    "verified_at": null
  },
  "uncertainty": [
    "The abstract reports reduced susceptibility on popular open models while preserving other-condition accuracy, but provides no numerical effect sizes here. Broader generalization beyond the benchmark's reasoning items remains an open question from the supplied material."
  ],
  "connected_context": {
    "meaning": "This turns context robustness into a selective-trust problem: an agent must resist misleading material without becoming insensitive to correct evidence. The matched four-condition design and per-item SC2W flips sharpen evaluation beyond aggregate accuracy, while the supplied evidence does not establish effect size or transfer beyond the benchmark.",
    "corpus_size": 390,
    "generated_at": "2026-08-08T10:05:57.056Z",
    "connections": [
      {
        "title": "The Illusion of Robustness: Aggregate Accuracy Hides Prediction Flips under Task-Irrelevant Context",
        "source_name": "arXiv",
        "source_url": "https://arxiv.org/abs/2607.12963v1",
        "feed7_url": "https://feed7.dev/p/2607-12963v1-1oc0qmr",
        "reason": "MIST operationalizes the earlier warning about hidden per-item flips and extends it by separating misleading, irrelevant, correct, and clean context rather than testing irrelevant noise alone."
      },
      {
        "title": "Resist and Update: Counterfactual Report Coordinates for Incentive-Compatible LLMs",
        "source_name": "arXiv",
        "source_url": "https://arxiv.org/abs/2607.12985v1",
        "feed7_url": "https://feed7.dev/p/2607-12985v1-1yo2sej",
        "reason": "Both separate resistance from useful updating; SCOPE trains this balance with matched preferences, while Resist and Update reports a training-free control whose deployable form lost resistance."
      },
      {
        "title": "MedPRESS: A Multi-turn Benchmark for Patient-Pressure-Induced Medical Sycophancy in LLMs",
        "source_name": "arXiv",
        "source_url": "https://arxiv.org/abs/2608.02520v1",
        "feed7_url": "https://feed7.dev/p/2608-02520v1-16negmk",
        "reason": "MedPRESS tests whether judgment survives escalating interpersonal pressure, complementing MIST’s test of whether judgment survives misleading retrieved context."
      }
    ]
  },
  "lifecycle": "Current",
  "published_at": "2026-08-06T17:59:58.000Z",
  "modified_at": "2026-08-06T17:59:58.000Z",
  "supersedes": [],
  "expires_at": null,
  "formats": {
    "html": "https://feed7.dev/p/2608-06377v1-0rvbpra",
    "json": "https://feed7.dev/p/2608-06377v1-0rvbpra.json",
    "markdown": "https://feed7.dev/p/2608-06377v1-0rvbpra.md"
  }
}