Skip to main content

The Four Agentic Paradigms: Technical Deep Dive

Overview

This document provides detailed analysis of each paradigm's architecture, implementation patterns, and practical applications.


Paradigm 1: Latent Space Clinician (LSC)

Position in Taxonomy

  • Knowledge Source: Implicit (parametric memory)
  • Agency Objective: Event Cognition (understanding/synthesis)

Core Philosophy

"Trust the model's emergent reasoning capabilities to function like an experienced clinical assistant, providing insights."

The LSC treats the LLM's parameters as an internalized medical curriculum, leveraging vast knowledge encoded during pre-training to perform creative synthesis and clinical reasoning without external tools.

Architecture Overview

┌─────────────────────────────────────────────────────────────────┐
│ LATENT SPACE CLINICIAN │
├─────────────────────────────────────────────────────────────────┤
│ INPUT │
│ ├── Dialogue History (H_t) │
│ ├── Current Query (Q_t) │
│ └── Observations (O_t) │
├─────────────────────────────────────────────────────────────────┤
│ DECOMPOSITION │
│ ├── Prompt Engineering / Chain-of-Thought │
│ ├── Tree of Thoughts (possibility exploration) │
│ └── Structured Query Generation │
├─────────────────────────────────────────────────────────────────┤
│ PLANNING │
│ ├── Internal Deliberative Cycle │
│ │ └── Consistency Check → Adjust → Iterate │
│ └── Analogical Reasoning Cycle │
│ └── Plans → Record → Reference │
├─────────────────────────────────────────────────────────────────┤
│ MEMORY │
│ ├── Parametric: Prompts, Templates, Clinical Corpus │
│ │ └── Injection into Latent Space (Strategy + Context) │
│ └── Non-Parametric: Context Extension, Recursive Summary │
│ └── Memory Proxy → Patient/Symptom Tracking │
├─────────────────────────────────────────────────────────────────┤
│ OUTPUT: Clinical Snapshot │
└─────────────────────────────────────────────────────────────────┘

Technical Components

1. Strategic Planning (Decomposition)

StrategyDescriptionExample Systems
Implicit AssociationProbabilistic pattern matching from trainingBioGPT, BioBART
Chain-of-ThoughtExplicit reasoning chains mimicking diagnostic logicMed-PaLM, Chain of Diagnosis
Causal AlignmentDecomposition based on domain-specific causal mechanismsMedAgents
Multi-PerspectiveBreaking queries into specialist viewpointsMDagents

2. Strategic Planning (Iteration)

  • Self-Consistency: Generate multiple reasoning paths, aggregate via voting
  • Counterfactual Reasoning: Challenge hypotheses by altering assumptions
  • Predictive Validation: Update representations after each turn for coherence

3. Memory Management

TypeFunctionTechniques
ParametricInternalized medical curriculumIn-context learning, Instruction fine-tuning
Non-ParametricPatient context windowLong-context models (Clinical ModernBERT), Recursive summarization

4. Collaboration

  • Single-Agent: General practitioner model; efficient but cognitively limited
  • Multi-Agent (Dominant): Central orchestrator synthesizes specialist outputs
  • Multi-Agent (Distributed): Peer-to-peer debate without central controller

5. Evolution

  • Continual Learning: Regularization to prevent catastrophic forgetting
  • Experience Replay: Periodically retrain on successful diagnoses
  • Model Expansion: Allocate new capacity for emerging medical knowledge

Strengths & Weaknesses

StrengthsWeaknesses
Zero-shot reasoning on novel casesHallucination risk
Pattern recognition from vast trainingKnowledge staleness
Creative synthesisOpaque reasoning process
No external dependency latencyCannot verify against current sources

Best Use Cases

  • Medical education and tutoring
  • Preliminary clinical inquiry
  • Patient-friendly report summarization
  • Hypothesis generation

Paradigm 2: Grounded Synthesizer (GS)

Position in Taxonomy

  • Knowledge Source: Explicit (external verification)
  • Agency Objective: Event Cognition (understanding/synthesis)

Core Philosophy

"LLMs should function as powerful natural language interfaces to reliable external information rather than as knowledge creators."

The GS operates under strict explicit knowledge grounding, retrieving, integrating, and citing verifiable external evidence to construct an accurate clinical snapshot.

Architecture Overview

┌─────────────────────────────────────────────────────────────────┐
│ GROUNDED SYNTHESIZER │
├─────────────────────────────────────────────────────────────────┤
│ INPUT │
│ ├── Dialogue History (H_t) │
│ ├── Current Query (Q_t) │
│ └── Observations (O_t) │
├─────────────────────────────────────────────────────────────────┤
│ DECOMPOSITION │
│ ├── Sub-query Generation (q_1 ... q_K) │
│ └── Query Dependency Graph Construction │
├─────────────────────────────────────────────────────────────────┤
│ ACTION EXECUTION │
│ ├── Knowledge-Based: Structured DB/KG queries │
│ ├── Search Engine: Forage → Constrain → Attribute │
│ └── Tool-Use: Deterministic calculators, risk scores │
├─────────────────────────────────────────────────────────────────┤
│ MEMORY │
│ ├── Parametric: Semantic translator, Query generator │
│ └── Non-Parametric: Evidential ledger (firewalled context) │
│ ├── Noise Filtering │
│ ├── Compression │
│ └── Conflict Detection │
├─────────────────────────────────────────────────────────────────┤
│ ITERATION │
│ ├── Cyclical Gap-Filling (schema completion) │
│ ├── Evidence Hierarchy Resolution (conflict handling) │
│ └── Progressive Deepening (granularity refinement) │
├─────────────────────────────────────────────────────────────────┤
│ OUTPUT: Grounded Clinical Snapshot with Citations │
└─────────────────────────────────────────────────────────────────┘

Technical Components

1. Strategic Planning (Decomposition)

StrategyDescription
Logical Inquiry PathwayMap queries to verified clinical workflows
Multi-hop Dependency GraphOrchestrate sequential/concurrent retrieval
Data-Driven TriggersDynamic sub-query generation based on findings

2. Action Execution (Unique to Explicit Paradigms)

Knowledge-Based Actions:

  • Formal queries over medical knowledge graphs
  • Axiomatic logical operations with audit trails
  • Schema-enforced semantic constraints

Search Engine Actions:

1. FORAGE: Multi-round strategic query sequence
2. CONSTRAIN: Firewall retrieved content from model parameters
3. ATTRIBUTE: Mandate fine-grained citation pointers

Tool-Use Actions:

  • Drug dosage calculators
  • Clinical risk stratification scores
  • Pharmacokinetic simulation engines

3. Memory Management

TypeFunction
ParametricSemantic translation, Query generation, Fluent synthesis
Non-ParametricEvidential ledger with strict compartmentalization

Critical Design: Information compartmentalization prevents "knowledge contamination" where verified external facts blend with potentially hallucinated internal knowledge.

4. Collaboration

  • Asymmetric human-agent partnership (cognitive augmentation)
  • GS acts as verifiable information provider, not autonomous decision-maker
  • Multi-agent: Evidence aggregation hub or data flow pipeline

Strengths & Weaknesses

StrengthsWeaknesses
Verifiable, auditable outputsLimited to retrieved knowledge
Source-traceable reasoningRetrieval bottlenecks
Mitigates hallucinationMulti-hop reasoning latency
High trustworthinessDependent on external source currency

Best Use Cases

  • EHR query interfaces
  • Clinical guideline lookup
  • Administrative data analysis
  • Regulatory-compliant decision support

Paradigm 3: Emergent Planner (EP)

Position in Taxonomy

  • Knowledge Source: Implicit (parametric memory)
  • Agency Objective: Goal Execution (autonomous action)

Core Philosophy

"Grant the LLM high autonomy to dynamically devise multi-step plans to achieve complex clinical goals based on internal procedural intuition."

The EP operates as an active digital collaborator that autonomously shapes workflow trajectories through self-directed planning and execution.

Architecture Overview

┌─────────────────────────────────────────────────────────────────┐
│ EMERGENT PLANNER │
├─────────────────────────────────────────────────────────────────┤
│ INPUT │
│ ├── Dialogue History (H_t) │
│ ├── Current Query (Q_t) │
│ └── Observations (O_t) │
├─────────────────────────────────────────────────────────────────┤
│ DECOMPOSITION │
│ ├── Implicit Cognitive Frameworks (NLU → Analysis → Diagnosis) │
│ ├── Cognitive Map Construction │
│ └── Self-Consistency Path Generation │
├─────────────────────────────────────────────────────────────────┤
│ PLANNING │
│ ├── Tree-Planner (probabilistic action space) │
│ └── Follow Queries → Specific Actions │
├─────────────────────────────────────────────────────────────────┤
│ ITERATION │
│ ├── Self-Reflection and Critique │
│ ├── Feedback from Interaction History │
│ └── Dynamic Plan Adjustment │
├─────────────────────────────────────────────────────────────────┤
│ MEMORY │
│ ├── Parametric: Workflow patterns, Procedural intuition │
│ │ └── Meta-Knowledge interaction and evaluation │
│ └── Non-Parametric: Dynamic log, Status highlight │
│ └── External interface (Supervise/Control) │
├─────────────────────────────────────────────────────────────────┤
│ OUTPUT: Autonomous Workflow Execution │
└─────────────────────────────────────────────────────────────────┘

Technical Components

1. Strategic Planning (Decomposition)

StrategyDescription
Self-ConsistencyGenerate diverse reasoning paths, aggregate via voting
Tree-PlannerConstruct cognitive map before execution
Cognitive CycleInternalize expert-level frameworks as implicit scaffolds
Graph TransformersCapture relational structure of medical concepts

2. Strategic Planning (Iteration)

  • Self-Reflection: Internal adversarial process to identify flaws
  • Reflexion Framework: Self-corrective capability for complex reasoning
  • Dialogue-Driven Feedback: Adapt strategies based on patient responses

3. Memory Management

TypeFunction
ParametricCentral engine for autonomous planning; encodes procedural knowledge
Non-ParametricTactical workspace; dynamic log of workflow state

Key Insight: Parametric memory encodes not just declarative knowledge but procedural knowledge — the sequential actions and decision logic underlying clinical practice.

4. Collaboration

  • Single-Agent: Autonomous practitioner steering dialogue
  • Multi-Agent (Dominant): Central coordinator for meta-planning, delegates to workers
  • Multi-Agent (Distributed): Peer negotiation for conflict resolution

5. Evolution

  • Outcome-Driven Learning: Reinforce decision paths based on clinical results
  • Meta-Learning: Abstract generalizable heuristics from experience
  • Proactive Self-Repair: Identify capability limits, trigger targeted learning

Strengths & Weaknesses

StrengthsWeaknesses
Flexible multi-step planningAction hallucination risk
Creative problem-solvingPotential for outdated procedures
Adapts to open-ended tasksDifficult to audit
Autonomous workflow progressionMay exceed safety boundaries

Best Use Cases

  • Open-ended clinical problem-solving
  • Novel/undocumented clinical scenarios
  • Health education facilitation
  • Shared decision-making support

Paradigm 4: Verifiable Workflow Automator (VWA)

Position in Taxonomy

  • Knowledge Source: Explicit (external verification)
  • Agency Objective: Goal Execution (autonomous action)

Core Philosophy

"Agent autonomy is strictly constrained within pre-defined, verifiable clinical workflows or decision trees."

The VWA serves as an intelligent natural language interface that drives deterministic, protocol-based process engines, ensuring maximum safety and predictability.

Architecture Overview

┌─────────────────────────────────────────────────────────────────┐
│ VERIFIABLE WORKFLOW AUTOMATOR │
├─────────────────────────────────────────────────────────────────┤
│ INPUT │
│ ├── Dialogue History (H_t) │
│ ├── Current Query (Q_t) │
│ └── Observations (O_t) │
├─────────────────────────────────────────────────────────────────┤
│ DECOMPOSITION │
│ ├── High-Level Objective Mapping │
│ ├── PICO Structuring (Population, Intervention, Comparison) │
│ └── Sub-Objective Generation │
├─────────────────────────────────────────────────────────────────┤
│ PLANNING │
│ ├── Node Selection in Pre-Defined Workflow │
│ └── Graph-of-Thought Clinical Pathway Navigation │
├─────────────────────────────────────────────────────────────────┤
│ ACTION EXECUTION │
│ ├── Knowledge-Based: Vector DB queries, KG traversal │
│ ├── Search Engine: Query optimization + validation │
│ └── Tool-Use: SQL generation, clinical calculators │
├─────────────────────────────────────────────────────────────────┤
│ ITERATION │
│ ├── Closed-Loop Locate-and-Correct │
│ ├── RL-Based Path Policy Optimization │
│ └── Hierarchical Cyclic Execution │
├─────────────────────────────────────────────────────────────────┤
│ MEMORY │
│ ├── Parametric: Semantic processor, Intent translator │
│ └── Non-Parametric: Clinical axiom repository, State register │
│ ├── Static: Evidence triplets, EHR graphs │
│ └── Dynamic: Action history, Entity maps │
├─────────────────────────────────────────────────────────────────┤
│ OUTPUT: Protocol-Compliant Workflow Execution │
└─────────────────────────────────────────────────────────────────┘

Technical Components

1. Strategic Planning (Decomposition)

StrategyDescription
Structured MappingAlign patient state to verified clinical workflow
PICO DecompositionStandardize queries into clinical elements
Graph-of-ThoughtNavigate logical sub-tasks in decision graph
Safety BoundariesHalt execution when outside workflow distribution

2. Strategic Planning (Iteration)

  • Locate-and-Correct: Feedback from tool retrieval for precise alignment
  • RL Path Optimization: Learn to minimize diagnostic costs while maximizing accuracy
  • Hierarchical Execution: Multi-stage collaborative graph with delegation

3. Action Execution

Knowledge-Based:

  • RAG over vectorized EHRs (CardioTRAP, CLI-RAG)
  • Medical knowledge graph traversal (MedRAG)
  • Hierarchical diagnostic KG queries

Search Engine:

  • Context-aware query generation (MeSH mapping)
  • Programmatic validation with entropy metrics
  • Mandatory transparency (traceable evidence chain)

Tool-Use:

  • SQL generation for EHR databases
  • Clinical calculator invocation
  • Expert system delegation

4. Collaboration

  • Single-Agent: Sequential checklist execution
  • Multi-Agent (Dominant): Attending physician model with MAKAR/TeamMedAgents
  • Multi-Agent (Distributed): Care pathway pipeline (DAG-based handoffs)

5. Evolution

  • Workflow Component Refinement: Evolutionary algorithms for prompt/tool optimization
  • Behavioral Adaptation: Learn collaborative strategies from outcome feedback
  • Meta-Tool Learning: Optimize interaction patterns with external systems

Strengths & Weaknesses

StrengthsWeaknesses
Maximum safety and predictabilityRigid; struggles with anomalies
High trustworthiness and traceabilityOptimization paradox in team settings
Protocol complianceRequires significant engineering investment
Auditable decision chainsLimited to pre-defined workflows

Best Use Cases

  • High-stakes clinical execution
  • Standardizable care pathways
  • Triage and screening systems
  • Regulatory-compliant automation

Comparative Summary Table

DimensionLSCGSEPVWA
KnowledgeImplicitExplicitImplicitExplicit
AgencyCognitionCognitionExecutionExecution
Primary StrengthCreative synthesisVerifiable outputFlexible planningSafe automation
Primary WeaknessHallucinationRetrieval limitsAction driftRigidity
Planning StyleReasoning chainsQuery decompositionCognitive mapsProtocol mapping
Memory FocusContext extensionEvidence ledgerWorkflow logState register
CollaborationPeer consultationEvidence hubTask negotiationCare pipeline
EvolutionContinual learningStrategy refinementMeta-learningWorkflow tuning
Best ForEducation, inquiryDecision supportNovel problemsStandard workflows

Selection Guidance

Choose LSC when:

  • Exploring hypotheses with limited data
  • Need creative pattern recognition
  • Low-stakes advisory context
  • Human expert available for validation

Choose GS when:

  • Accuracy and verifiability are paramount
  • Working with structured knowledge bases
  • Need auditable decision trails
  • Integration with existing data systems

Choose EP when:

  • Tasks require multi-step autonomous action
  • Situations are novel or undocumented
  • Flexibility outweighs predictability needs
  • Building adaptive patient education systems

Choose VWA when:

  • High-stakes clinical execution required
  • Standard protocols exist and should be followed
  • Maximum auditability needed
  • Regulatory compliance is essential