D-MEM: Dopamine-Gated Agentic Memory via Reward Prediction Error Routing

Yuru Song; Qi Xin

Home/Archive/arXiv

arXiv · 2603.14597

D-MEM: Dopamine-Gated Agentic Memory via Reward Prediction Error Routing

Yuru Song·Qi Xin

View original source ↗Read source document ↗Export metadata ↓

Abstract

Autonomous LLM agents require structured long-term memory, yet current "append-and-evolve" systems like A-MEM face O(N^2) write-latency and excessive token costs. We introduce D-MEM (Dopamine-Gated Agentic Memory), a biologically inspired architecture that decouples short-term interaction from cognitive restructuring via a Fast/Slow routing system based on Reward Prediction Error (RPE). A lightweight Critic Router evaluates stimuli for Surprise and Utility. Routine, low-RPE inputs are bypassed or cached in an O(1) fast-access buffer. Conversely, high-RPE inputs, such as factual contradictions or preference shifts, trigger a "dopamine" signal, activating the O(N) memory evolution pipeline to reshape the agent's knowledge graph. To evaluate performance under realistic conditions, we introduce the LoCoMo-Noise benchmark, which injects controlled conversational noise into long-term sessions. Evaluations demonstrate that D-MEM reduces token consumption by over 80%, eliminates O(N^2) bottlenecks, and outperforms baselines in multi-hop reasoning and adversarial resilience. By selectively gating cognitive restructuring, D-MEM provides a scalable, cost-efficient foundation for lifelong agentic memory.

Explore related subjects

q-bio.NC cs.AI

Keep this discovery

Explore connections, maps & timelines

BibTeX RIS

Yuru Song, Qi Xin. 2026-03-15. D-MEM: Dopamine-Gated Agentic Memory via Reward Prediction Error Routing. https://arxiv.org/abs/2603.14597

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

Only what exists can cause: An intrinsic powers view of free will

This essay addresses the implications of integrated information theory (IIT) for free will. IIT is a theory of what consciousness is and of how its presence and quality can be accounted for in physical terms. According to IIT, the presence of consciousness is accounted for by a maximum of cause-effect power in the brain. Moreover, the way an experience feels is accounted for by how that cause-effect power is structured. If IIT is right, we do have free will in a genuine sense: we have alternatives, reasons, and values, we make decisions, and we-not our neurons or atoms-are the cause of our willed actions and bear responsibility for them. IIT's argument for genuine free will hinges on the proper understanding of consciousness as intrinsic existence, captured by its intrinsic powers ontology: what exists absolutely, in physical terms, are intrinsic entities, and only what exists can cause.

q-bio.NC↗

arXiv2026

Seeing the imagined: latent functional alignment in visual imagery decoding from fMRI data

Recent progress in visual brain decoding from fMRI has been enabled by large-scale datasets such as the Natural Scenes Dataset (NSD) and powerful diffusion-based generative models. While current pipelines are primarily optimized for perception, their performance under mental-imagery remains less well understood. In this work, we study how a state-of-the-art (SOTA) perception decoder (DynaDiff) can be adapted to reconstruct imagined content from the NSD-Imagery benchmark. We propose a latent functional alignment (LFA) approach that maps imagery-evoked activity to the pretrained model's semantic content-enriched conditioning space, by adding a simple alignment module, while keeping the original remaining components frozen. To mitigate the limited amount of matched imagery-perception supervision, we further introduce a neural retrieval-based augmentation strategy that selects semantically related NSD perception trials from the same participants. Across four subjects, LFA consistently improves high-level semantic reconstruction metrics relative to the frozen pretrained baseline and a voxel-space ridge alignment baseline, and enables above-chance decoding from multiple cortical regions. These results suggest that semantic structure learned from perception can be leveraged to stabilize and improve visual imagery decoding under out-of-distribution conditions.

q-bio.NC↗

arXiv2026

Deep Learning in Infant Functional Neuroimaging: Challenges, Advances, and Future Directions

Infancy is a critical developmental window characterized by rapid functional brain reorganization, during which large-scale networks emerge, individualized connectome signatures continue to form, and early deviations may shape long-term cognitive and clinical outcomes. Functional MRI (fMRI) offers an opportunity to study these processes in vivo, yet extracting developmentally meaningful information from it remains challenging due to comparatively short scan duration, structured motion artifacts, variable scan states, and rapid brain maturation. Amid these challenges, deep learning has expanded the capacity of computational neuroimaging by learning robust representations from noisy, high-dimensional data, integrating complex spatial and temporal information, and capturing the nonlinear and rapidly evolving organization of the developing brain. Here, we review recent advances in deep learning for infant functional neuroimaging, synthesizing progress across input representation formatting, population and individualized brain mapping, longitudinal trajectory forecasting, robust and explainable model evaluation, and biological translation. Collectively, these methodological advances mark a paradigm shift in infant functional neuroimaging from descriptive, group-level analyses toward reliable, individualized, and developmentally grounded models. Future progress will depend on larger and more diverse longitudinal datasets, developmentally appropriate model designs, rigorous and standardized evaluation, and integration of computational predictions with biological mechanisms towards clinically meaningful outcomes. Addressing these priorities will help establish deep learning as a robust framework for understanding early functional brain development, identifying developmental variation at the individual level, and ultimately supporting earlier and precise assessment of neurodevelopmental risk.

q-bio.NC↗