Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.swarms.world/llms.txt

Use this file to discover all available pages before exploring further.

Reasoning agents are sophisticated agents that employ advanced cognitive strategies to improve problem-solving performance beyond standard language model capabilities. Unlike traditional prompt-based approaches, reasoning agents implement structured methodologies that enable them to think more systematically, self-reflect, collaborate, and iteratively refine their responses. These agents are inspired by cognitive science and human reasoning processes, incorporating techniques such as:
  • Multi-step reasoning: Breaking down complex problems into manageable components
  • Self-reflection: Evaluating and critiquing their own outputs
  • Iterative refinement: Progressively improving solutions through multiple iterations
  • Collaborative thinking: Using multiple reasoning pathways or agent perspectives
  • Memory integration: Learning from past experiences and building knowledge over time
  • Meta-cognitive awareness: Understanding their own thinking processes and limitations

​
Available Reasoning Agents

Agent NameTypeResearch PaperKey FeaturesBest Use Cases
Self-Consistency AgentConsensus-basedSelf-Consistency Improves Chain of Thought Reasoning (Wang et al., 2022)Multiple independent reasoning paths, majority voting aggregation, concurrent execution, validation modeMathematical problem solving, high-accuracy requirements, decision making
Reasoning DuoCollaborativeNovel dual-agent architectureSeparate reasoning and execution agents, collaborative problem solving, task decomposition, cross-validationComplex analysis tasks, multi-step problem solving, research and planning
IRE AgentIterativeIterative Reflective Expansion frameworkHypothesis generation, path simulation, error reflection, dynamic revisionComplex reasoning tasks, research problems, strategy development
Reflexion AgentSelf-reflectiveReflexion: Language Agents with Verbal Reinforcement Learning (Shinn et al., 2023)Self-evaluation, experience memory, adaptive improvement, learning from failuresContinuous improvement tasks, long-term projects, quality refinement
GKP AgentKnowledge-basedGenerated Knowledge Prompting (Liu et al., 2022)Knowledge generation, multi-perspective reasoning, information synthesisKnowledge-intensive tasks, research questions, fact-based reasoning
Agent JudgeEvaluationAgent-as-a-JudgeQuality assessment, structured evaluation, performance metrics, feedback generationQuality control, output evaluation, performance assessment

​
Agent Architectures

​
Self-Consistency Agent

Implements multiple independent reasoning paths with consensus-building to improve response reliability and accuracy through majority voting mechanisms. Use Cases: Mathematical problem solving, high-stakes decision making, answer validation, quality assurance Self-Consistency Agent Guide

​
Reasoning Duo

Dual-agent collaborative system that separates reasoning and execution phases, enabling specialized analysis and task completion through coordinated agent interaction. Use Cases: Complex analysis tasks, multi-step problem solving, research and planning, verification workflows Reasoning Duo Guide

​
IRE Agent (Iterative Reflective Expansion)

Sophisticated reasoning framework employing iterative hypothesis generation, simulation, and refinement through continuous cycles of testing and meta-cognitive reflection. Use Cases: Complex reasoning tasks, research problems, strategy development, iterative learning IRE Agent Guide

​
Reflexion Agent

Advanced self-reflective system implementing actor-evaluator-reflector architecture for continuous improvement through experience-based learning and memory integration. Use Cases: Continuous improvement tasks, long-term projects, adaptive learning, quality refinement Reflexion Agent Guide

​
GKP Agent (Generated Knowledge Prompting)

Knowledge-driven reasoning system that generates relevant information before answering queries, implementing multi-perspective analysis through coordinated knowledge synthesis. Use Cases: Knowledge-intensive tasks, research questions, fact-based reasoning, information synthesis GKP Agent Guide

​
Agent Judge

Specialized evaluation system for assessing agent outputs and system performance, providing structured feedback and quality metrics through comprehensive assessment frameworks. Use Cases: Quality control, output evaluation, performance assessment, model comparison Agent Judge Guide

​
Implementation Guide

​
Unified Interface via Reasoning Agent Router

The ReasoningAgentRouter provides a centralized interface for accessing all reasoning agent implementations: 
from swarms.agents import ReasoningAgentRouter

# Initialize router with specific reasoning strategy
router = ReasoningAgentRouter(
    swarm_type="self-consistency",
    model_name="claude-sonnet-4-6",
    num_samples=5,
    max_loops=3
)

# Execute reasoning process
result = router.run("Analyze the optimal solution for this complex business problem")
print(result)
Reasoning Agent Router Reference

​
Direct Agent Implementation

from swarms.agents import SelfConsistencyAgent, ReasoningDuo, ReflexionAgent

# Self-Consistency Agent for high-accuracy requirements
consistency_agent = SelfConsistencyAgent(
    model_name="claude-sonnet-4-6",
    num_samples=5
)

# Reasoning Duo for collaborative analysis workflows
duo_agent = ReasoningDuo(
    model_names=["claude-sonnet-4-6", "gpt-5.4"]
)

# Reflexion Agent for adaptive learning scenarios
reflexion_agent = ReflexionAgent(
    model_name="claude-sonnet-4-6",
    max_loops=3,
    memory_capacity=100
)

​
Choosing the Right Reasoning Agent

ScenarioRecommended AgentWhy?
High-stakes decisionsSelf-ConsistencyMultiple validation paths ensure reliability
Complex research tasksReasoning Duo + GKPCollaboration + knowledge synthesis
Learning & improvementReflexionBuilt-in self-improvement mechanisms
Mathematical problemsSelf-ConsistencyProven effectiveness on logical reasoning
Quality assessmentAgent JudgeSpecialized evaluation capabilities
Iterative refinementIREDesigned for progressive improvement