Yancheng Zhu, Yifan Yuan · 2026 · arXiv
DOI: 10.48550/arXiv.2610.31314 · open-access PDF
大型语言模型可以重复指令,但无法继续服从它。我们在长远对话中研究这种回忆遵守分离,并定义了状态完整性崩溃:模型在记忆中保留了声明的限制,但停止将其应用到以后的转折中。我们引入了StateTrack-Bench,一个控制的对话套件,涵盖数字,格式,角色/人,事实记忆和逻辑规则限制。
Machine translation (Meta M2M100); the English original follows.
Large language models can repeat an instruction while failing to keep obeying it. We study this recall-compliance dissociation in long-horizon dialogue and define State Integrity Collapse: a model preserves a stated constraint in memory but stops applying it to later turns. We introduce StateTrack-Bench, a controlled suite of conversations covering numerical, format, role/persona, factual-memory, and logical-rule constraints. Across seven provider-pinned model snapshots and five dialogue-depth probes, strict joint retention ranges from 62.4% to 100.0%, with degradation concentrated in symbolic
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.31314, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange