Madeleine: Learning Involuntary Recall for Conversational Memory from Simulated Lives

arXiv:2610.01118 · cs.CL, cs.AI, cs.IR · Submitted 2026-10-01 · Read on arXiv

cs.CL, cs.AI, cs.IR

Submitted: 2026-10-01

Updated: 2026-10-07

Comments: 18 pages, 4 figures. v2: adds three-seed results for the HyperMem plug-in and an evaluation with human-written triggers (Appendix D)

License: http://creativecommons.org/licenses/by/4.0/

The gist: A long-term conversational assistant must recall the right memory at the right moment, yet the memory that matters most is often not similar to what the user says now.

Terminology

Abstract

A long-term conversational assistant must recall the right memory at the right moment, yet the memory that matters most is often not similar to what the user says now. Current systems recover such associations by letting an LLM reason at write or read time, at a cost of hundreds to over a thousand LLM calls per memory bank and up to several thousand context tokens per query. We argue that association is a learnable relevance: the pointwise mutual information of memories under how human lives unfold. We introduce Madeleine, which learns amortized association: offline, an LLM life simulator writes simulated lives, whose cue-trigger pairs teach a query encoder a residual association on top of frozen similarity; online, it calls no LLM and plugs into any vector memory by replacing only the query encoder. On LoCoMo-Plus under the official protocol, Madeleine (I) reaches 66.6 when plugged into HyperMem, the highest among all systems evaluated under this protocol; (II) used alone, reaches the score of HyperMem as released (52.4 vs. 52.9) with zero LLM calls and about 1/21 of its answer context; and (III) lifts T-Mem by 26.2 points, significantly outperforms the same untrained backbone inside both systems, and leaves ordinary QA intact on the 4B backbone.

Sources

Related papers