cs.AIMar 22, 2026

STEM Agent: A Self-Adapting, Tool-Enabled, Extensible Architecture for Multi-Protocol AI Agent Systems

Authors: Alfred Shen, Aaron Shen

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

Abstract

Current AI agent frameworks commit early to a single interaction protocol, a fixed tool integration strategy, and static user models, limiting their deployment across diverse interaction paradigms. To address these constraints, we introduce STEM Agent (Self-adapting, Tool-enabled, Extensible, Multi-agent), a modular architecture inspired by biological pluripotency in which an undifferentiated agent core differentiates into specialized protocol handlers, tool bindings, and memory subsystems that compose into a fully functioning AI system. The framework unifies five interoperability protocols (A2A, AG-UI, A2UI, UCP, and AP2) behind a single gateway, introduces a Caller Profiler that continuously learns user preferences across more than twenty behavioral dimensions, externalizes all domain capabilities through the Model Context Protocol (MCP), and implements a biologically inspired skills acquisition system in which recurring interaction patterns crystallize into reusable agent skills through a maturation lifecycle analogous to cell differentiation. Complementing these capabilities, the memory system incorporates consolidation mechanisms, including episodic pruning, semantic deduplication, and pattern extraction, designed for sub-linear growth under sustained interaction. A comprehensive 413-test suite validates protocol handler behavior and component integration across all five architectural layers, completing in under three seconds.

Figures & tables

Figure 1: STEM Agent five-layer architecture. Callers interact through the Standard Interface Layer, which routes requests through five protocol handlers (A2A, AG-UI, A2UI, UCP, AP2) and framework adapters to the Agent Core. The core’s cognitive pipeline (Perceive →\to Adapt →\to Skill Match →\to Reason →\to Plan →\to Execute →\to Learn →\to Respond) is supported by a four-type Memory System and the MCP Integration Layer for dynamic tool access.
LayerComponentKey Counts
1Caller / User Layer4 adapters
2Standard Interface (Gateway)5 protocols
3Agent Core5 engines
3.5Security Layer4 IAM plugins
4Memory System4 memory types
5MCP Integration3 transports
Table 1: Five-layer architecture overview.
ProtocolEndpointTransportSchemasUse Case
A2APOST /a2aJSON-RPC 2.06Agent-to-agent task delegation, inter-agent messaging, agent card discovery
AG-UIPOST /ag-uiSSE20Real-time UI streaming; maps pipeline phases to typed events
A2UIPOST /a2ui/renderSSE + REST19Dynamic UI composition with 16 component primitives
UCPPOST /ucp/*REST14Commerce checkout sessions with idempotency
AP2POST /ap2/*REST10Mandate-based payments with audit trail
Table 2: Protocol comparison. STEM Agent implements all five behind a single Express.js gateway. A2A follows the Linux Foundation v0.3.0 specification. UCP and AP2 are novel protocols proposed in this work.
CategoryDimsExample Dimensions
Philosophy8pragmatism vs. idealism, risk tolerance, innovation orientation
Principles4correctness over speed, testing emphasis, security mindedness
Style5formality, verbosity, technical depth, structure preference
Habits4+session length, iteration tendency, peak hours
Table 3: Caller Profile dimensions by category.
FrameworkProto.AdaptMem.SkillsCom.
AutoGen1×1××
MetaGPT1×1××
CrewAI1×1××
LangChain1×2××
STEM3+2 †✓4✓✓
Table 4: Architectural comparison with existing agent frameworks. Proto. = standardized interoperability protocols; Adapt = per-caller self-adaptive behavior; Mem. = distinct memory subsystem types; Skills = emergent skill acquisition; Com. = commerce protocols. †\dagger UCP and AP2 are novel protocols proposed in this work.
More in this topic

Agentic AI

Agentic artificial intelligence studies systems that plan, use tools, learn from feedback, and act toward goals with varying degrees of autonomy.

See all 211 papers

Explore similar work

CardsList
Oct 21, 2025

Fetch.ai: An Architecture for Modern Multi-Agent Systems

Recent surges in LLM-driven intelligent systems largely overlook decades of foundational multi-agent systems (MAS) research, resulting in frameworks with critical limitations such as centralization and inadequate trust and communication protocols. This paper introduces the Fetch.ai architecture, an industrial-strength platform designed to bridge this gap by facilitating the integration of classical MAS principles with modern AI capabilities. We present a novel, multi-layered solution built on a decentralized foundation of on-chain blockchain services for verifiable identity, discovery, and transactions. This is complemented by a comprehensive development framework for creating secure, interoperable agents, a cloud-based platform for deployment, and an intelligent orchestration layer where an agent-native LLM translates high-level human goals into complex, multi-agent workflows. We demonstrate the deployed nature of this system through a decentralized logistics use case where autonomous agents dynamically discover, negotiate, and transact with one another securely. Ultimately, the Fetch.ai stack provides a principled architecture for moving beyond current agent implementations towards open, collaborative, and economically sustainable multi-agent ecosystems.

Michael J. Wooldridge, Attila Bagoly, Jonathan J. Ward +2

University of Oxford

Multi-Agent OrchestrationMulti-Agent SystemsMulti-Agent Communication
AskPDF
Apr 16, 2026

Autogenesis: A Self-Evolving Agent Protocol

LLM-based agent systems can adapt by revising prompts, constructing tools, and changing other runtime resources. Managing these heterogeneous updates requires a shared lifecycle for identifying targets, assessing candidates, and retaining accepted versions, complementing communication protocols such as A2A and MCP. We introduce AUTOGENESIS PROTOCOL (AGP), which decouples what evolves from how updates are proposed. Its Resource Substrate Protocol Layer (RSPL) represents prompts, agents, tools, environments, and memory as protocol-registered resources with explicit state and versioned interfaces. Its Self-Evolution Protocol Layer (SEPL) specifies candidate proposal, assessment, and commit, with auditable histories and support for restoring retained resource states. We instantiate AGP in AUTOGENESIS SYSTEM (AGS), a self-evolving multi-agent system that retrieves, instantiates, and refines resources during execution. Across reasoning, tool-use, and coding benchmarks, AGS improves over its non-evolving configuration, and repeated reasoning runs report the accompanying output-token cost. Execution cases show a shared update lifecycle across all five resource types.

Wentao Zhang, Zhe Zhao, Haibin Wen +4

Nanyang Technological University · Stanford University · City University of Hong Kong +1

Multi-Agent LLM SystemsLLM Agent Self-ImprovementLLM AgentsLong-Horizon Agent TasksSelf-Evolving Agents
AskPDF
Jun 3, 2026

Ahoy: LLMs Enacting Multiagent Interaction Protocols

An interaction protocol formalizes how the agents in a multiagent system interact, which facilitates implementing agents. Existing approaches yield agent implementations specific to the selected protocols. How can we engineer intelligent agents that can enact protocols but are programming-free? Our contribution, Ahoy, addresses this question by creating LLM agents that dynamically select and enact declarative protocols to achieve user goals. We demonstrate that an Ahoy agent can correctly and intelligently enact multiple protocols - concurrently if appropriate to the user goal - without specialized training. Ahoy's significance lies in that it brings together declarative protocols and LLMs, both approaches that promise improved knowledge engineering for agents.

Omkar J. Joshi, Munindar P. Singh, Amit K. Chopra

North Carolina State University, Raleigh, NC, USA · Lancaster University, Lancaster, UK

LLM AgentsMulti-Agent SystemsMulti-Agent Communication
AskPDF