AdMem: Expectation-Grounded Procedural Memory for Long-Horizon Task-Solving Agents

arXiv:2611.20605v1 Announce Type: new
Abstract: An agent that carries memory across tasks is only as good as the entries it keeps. We begin from an observation that is easy to reproduce and uncomfortable for the field: naively accumulating cross-task experience can make an agent \emph{worse} than one with no memory at all. On AgentBoard, a workflow-induction memory solves fewer tasks than a memoryless ReAct agent in seven of eight domains, and a per-step procedural store with no surrounding structure loses half of ReAct's completions on Jericho. We argue that the missing ingredients are per-action credit assignment and an explicit life cycle for stored entries, and present AdMem, which supplies both. Before each action the actor commits to an expected outcome; a concurrently running critic scores the realized outcome against that expectation and writes a procedural entry carrying a binary reward and a reflection, so credit lands on the action that earned it and no environment reward is required. Each entry then carries a scalar utility, updated online under a noisy-OR reward model, that ranks retrieval jointly with context similarity and drives eviction and merging, giving the store a forgetting and consolidation policy instead of unbounded growth. Across 707 tasks in eight AgentBoard domains AdMem solves 441 against 388 for ReAct and 312 for the workflow-induction baseline — a pooled gain significant under a two-sided Fisher exact test, concentrated in the domains that supply transferable cross-task structure. All memory stays human-readable text, which is what makes the failures above diagnosable — and, as we discuss, also makes the store an auditable but attackable surface.
This article has been indexed from cs.AI updates on arXiv.org

Read the original article:

AdMem: Expectation-Grounded Procedural Memory for Long-Horizon Task-Solving Agents