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.

The Iterative Reflective Expansion (IRE) Algorithm is a sophisticated reasoning framework that employs iterative hypothesis generation, simulation, and refinement to solve complex problems. It leverages a multi-step approach where an AI agent generates initial solution paths, evaluates their effectiveness through simulation, reflects on errors, and dynamically revises reasoning strategies.

​
Architecture

​
Workflow

  1. Generate initial hypotheses
  2. Simulate paths
  3. Reflect on errors
  4. Revise paths
  5. Select promising paths
  6. Synthesize solution

​
Class: IterativeReflectiveExpansion

​
Parameters

ParameterTypeDefaultDescription
agentAgentNoneThe Swarms agent instance used to perform reasoning tasks
max_loopsint5Maximum number of loops for the reasoning process
return_listboolFalseIf True, returns the conversation as a list of messages
return_dictboolFalseIf True, returns the conversation as a dictionary
promptstrGENERAL_REASONING_AGENT_SYS_PROMPTThe system prompt for the agent

​
Methods

MethodDescription
generate_initial_hypothesesGenerates an initial set of reasoning hypotheses based on the problem input
simulate_pathSimulates a given reasoning path and evaluates its effectiveness
meta_reflectPerforms meta-cognitive reflection on the provided error information
revise_pathRevises the reasoning path based on the provided feedback
select_promising_pathsSelects the most promising reasoning paths from a list of candidates
synthesize_solutionSynthesizes a final solution from the promising paths and historical memory
runExecutes the Iterative Reflective Expansion process on the provided problem

​
Example

from swarms import IterativeReflectiveExpansion

agent = IterativeReflectiveExpansion(
    max_loops=3,
)

agent.run("What is the 40th prime number?")