Oblivion: Self-Adaptive Agentic Memory Control through Decay-Driven Activation

arXiv:2604.00131 · cs.CL, cs.AI · Submitted 2026-03-31 · Read on arXiv

cs.CL, cs.AI

Submitted: 2026-03-31

Updated: 2026-09-01

Comments: EMNLP 2026 (main)

Code: https://github.com/necresearch/oblivion

License: http://creativecommons.org/licenses/by-nc-sa/4.0/

The gist: Human memory adapts through selective forgetting: experiences become less accessible over time but can be reactivated by reinforcement or contextual cues.

Terminology

Abstract

Human memory adapts through selective forgetting: experiences become less accessible over time but can be reactivated by reinforcement or contextual cues. In contrast, memory-augmented LLM agents rely on "always-on" retrieval and "flat" memory storage, causing high interference and latency as histories grow. We introduce Oblivion, a memory control framework that casts forgetting as decay-driven reductions in accessibility -- not explicit deletion. Oblivion decouples memory control into read and write paths. The read path decides when to consult memory, based on agent uncertainty and memory buffer utility, avoiding redundant always-on access. The write path decides what to strengthen, by reinforcing memories contributing to forming the response. Together, this enables hierarchical memory organization that maintains persistent high-level strategies while dynamically loading details as needed. We evaluate on both static and dynamic long-horizon interaction benchmarks. Oblivion outperforms both direct and memory-augmented baselines, while reducing token cost by up to 73% at 120K interaction spans. These results show that treating memory as a control problem -- deciding when to retrieve and what to reinforce -- is essential for sustaining long-horizon agent performance.

Sources

Related papers