{
  "schema_version": "1.1",
  "id": "auto-91ef3aae9d",
  "slug": "learning-when-to-trust-via-selective-context-preference--91ef3aae9d",
  "url": "https://feed7.dev/p/learning-when-to-trust-via-selective-context-preference--91ef3aae9d",
  "title": "Learning When to Trust via Selective Context Preference Optimization",
  "why_included": "Test whether agents use good context while resisting misleading context, rather than appearing robust by ignoring evidence.",
  "summary": "MIST tests whether models use good context while resisting bad context, exposing agents that appear robust only because they ignore external evidence altogether.",
  "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": "2026-08-06T00:00:00.000Z"
  },
  "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": [
    "Automatically selected from source material; feed7 has not independently tested the claim."
  ],
  "connected_context": null,
  "lifecycle": "New",
  "published_at": "2026-08-06T00:00:00.000Z",
  "modified_at": "2026-08-06T00:00:00.000Z",
  "supersedes": [],
  "expires_at": null,
  "formats": {
    "html": "https://feed7.dev/p/learning-when-to-trust-via-selective-context-preference--91ef3aae9d",
    "json": "https://feed7.dev/p/learning-when-to-trust-via-selective-context-preference--91ef3aae9d.json",
    "markdown": "https://feed7.dev/p/learning-when-to-trust-via-selective-context-preference--91ef3aae9d.md"
  }
}