AI 中文总结
提出一种零推理成本的前瞻性记忆检索项，通过显式承诺账本和显著性提升，在合成任务上显著提高困难层级的召回率，且不损害其他案例。
AI 中文摘要
个人记忆库的检索是回顾性的：它呈现与查询相似的内容，而对用户承诺要做的事情视而不见。我们描述了一种记忆检索的前瞻项，它在查询时不产生任何推理成本。承诺被保存在一个显式账本中，作为带日期或触发条件的条目；与触发条目相关联的记忆项会获得显著性提升，并以乘法方式混合到基于嵌入的检索中，从而保持相关性的主导地位。在基于TriggerBench已发布结构建模的合成前瞻性记忆任务集上（48个盲法撰写的对话，175个任务），该术语在默认混合权重下将困难层级的recall@5从0.000提升至0.955，在底层变体下提升至1.000，在53个已解决承诺任务中零误提升。盲法撰写还产生了一个范围发现：只有17-29%的自然措辞的承诺-触发对能击败嵌入相似性，因此该术语在少数真实案例中起作用，并且必须对其余案例无害，事实也确实如此。我们将预计算的承诺关联定位为分层设计的常开底层，其扩展层是查询时的前瞻。结果是初步的：评估集由作者构建，对TriggerBench本身的评估是数据发布后的后续工作。
英文摘要
Retrieval over a personal memory store is retrospective: it surfaces what resembles the query, and it is blind to what the user has committed to do. We describe a prospective term for memory retrieval that costs no inference at query time. Commitments are held in an explicit ledger as dated or trigger-conditioned entries; memory items linked to a firing entry receive a salience boost, blended multiplicatively into embedding-based retrieval so that relevance remains sovereign. On a synthetic prospective-memory task set modeled on TriggerBench's published structure (48 blind-authored dialogues, 175 tasks), the term raised recall@5 on the hard stratum from 0.000 to 0.955 at the default blend weight and to 1.000 under a floor variant, with zero false boosts across 53 resolved-commitment tasks. Blind authorship also produced a scope finding: only 17-29% of naturally phrased commitment-trigger pairs defeat embedding similarity, so the term matters on a real minority of cases and must do no harm on the rest, which it does not. We position precomputed commitment linkage as the always-on floor of a layered design whose expansion layer is query-time prospection. Results are preliminary: the evaluation set is author-constructed, and evaluation on TriggerBench proper is committed follow-up work once its data is released.
Comments7 pages. Code and data: https://github.com/Groffitti/memory-that-looks-forward
