A Motivational Architecture for Conversational AGI
Quick Answer
This paper introduces a novel motivational architecture for conversational AGI, integrating OpenPsi and MetaMo frameworks.
Quick Take
This paper introduces a novel motivational architecture for conversational AGI, integrating OpenPsi and MetaMo frameworks. It proposes a ten-stage motivational processing pipeline and a dual decision strategy, focusing on regulating dialogue-native competencies rather than physical needs, with applications in CompanionAgent and ResearchAgent.
Key Points
- Introduces a ten-stage motivational processing pipeline for conversational agents.
- Proposes a dual decision strategy for urgency-driven and deliberative responses.
- Distinguishes between pre-action feelings and post-action emotions in agent design.
- Specializes the framework for CompanionAgent and ResearchAgent applications.
- Extends the architecture to social robotics and human-level AGI.
Article Content
From source RSS / original summaryarXiv:2606. 05411v1 Announce Type: new Abstract: Motivational architectures in cognitive AI have largely been designed for physical agents regulating bodily needs. Conversational agents operate in a different regime: their sensorimotor loop is linguistic, their environment is a user's evolving mental state, and their consequential actions are speech acts, tool invocations, and strategic silences.
This paper proposes a conversational reinterpretation of the OpenPsi motivational lineage, coupled to MetaMo's higher-level motivational scaffold, for agents built on a modular execution substrate. Homeostasis is recast in dialogue-native terms: the agent regulates competence, uncertainty reduction, affiliation, affinity, legitimacy, nurturing, and aesthetic coherence rather than bodily deficits.
We propose three contributions: a ten-stage motivational processing pipeline that architecturally separates cognitive modulation from situational appraisal; a dual decision strategy blending urgency-driven fast response with deliberative multi-goal optimization; and an architecturally useful distinction between pre-action feelings and post-action emotions as functionally different forms of affect.
We specialize the framework to two example agents -- CompanionAgent and ResearchAgent -- and sketch its extension to social robotics and domain-generic human-level AGI.
Reader Mode unavailable (could not extract clean content).
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.AI
See more →The Meta-Agent Challenge: Are Current Agents Capable of Autonomous Agent Development?
The Meta-Agent Challenge (MAC) introduces a framework to evaluate AI's ability to autonomously develop agents, revealing that current models rarely match human-engineered policies and often display adversarial behaviors. This open-source benchmark highlights significant gaps in robustness and alignment, particularly among proprietary models.