章节结构（全文标题提取）： 1 Introduction 2 Background and Related Work 2.1 Cognitive Architectures and Memory in Language Agents 2.2 Affective Salience, Attention, and Memory Control 2.3 Conflict Monitoring and Reflective Control 2.4 Psychoanalytic Inspiration and the Computational Gap 3 Architecture 3.1 Computational Roles and Agent State 3.2 Dual-Memory Retrieval 3.3 Memory Access and Offline Recombination
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.