PsychoAgent: An Affect-Sensitive Cognitive Architecture for Conflict-Aware Memory in LLM Agents
2026-08-07 • Artificial Intelligence
Artificial IntelligenceComputation and LanguageHuman-Computer Interaction
AI summaryⓘ
The authors created PsychoAgent, a system that helps AI remember things not just by topic but also by emotions and conflicts, similar to how humans do. It keeps factual and emotional memories separate, then decides what to use based on both relevance and emotional importance. In tests, PsychoAgent found more important memories related to conflicts than other methods, though it sometimes missed some topic matches. Human reviewers slightly preferred its responses, but differences weren't statistically strong. The study shows that including emotions in memory retrieval can help AI better mimic human thought processes during conflicts.
Large Language ModelsCognitive ArchitectureAffective MemorySemantic MemoryMemory RetrievalConflict AwarenessExecutive ControllerRelevance RankingHuman-like CognitionMemory Salience
Authors
Mohammad Amanlou, Parham Abed Azad, Farbod Davoodi, Mostafa Masumi, Behnam Bahrak, Abdol-Hossein Vahabie
Abstract
Human-like cognition does not select past experience by topical similarity alone: affective significance and unresolved conflict also shape what becomes accessible. We present PsychoAgent, a cognitive architecture for LLM agents that separates factual and affective memory and integrates both through a conflict-aware executive controller. Affective memories are first filtered by semantic relevance and then re-ranked by salience, preserving topical fit while allowing emotionally important traces to enter the prompt. Across three controlled conflict scenarios, the full architecture retrieved more conflict-critical memories than semantic-affective and single-memory RAG baselines (0.933 vs. 0.500 and 0.667), with a small semantic-similarity cost. Five blinded raters evaluated 27 outputs. After within-rater standardization, the full architecture had the highest overall mean (+0.22 SD), but corrected pairwise differences were not significant. A three-day illustrative trace further shows persistent affect, offline memory recombination, and selective memory reweighting. The findings support affect-sensitive retrieval as an inspectable mechanism for modeling human-like conflict effects in LLM agents.