Package com.tnsai.quality.validation.parallel

Enum Class AggregationStrategy

java.lang.Object

java.lang.Enum<AggregationStrategy>

com.tnsai.quality.validation.parallel.AggregationStrategy

All Implemented Interfaces:

Serializable, Comparable<AggregationStrategy>, Constable

public enum AggregationStrategy
extends Enum<AggregationStrategy>

Strategy for aggregating results from multiple LLM agents.

Different strategies provide different trade-offs between consensus, quality, and coverage of responses.

Nested Class Summary

Nested classes/interfaces inherited from class java.lang.Enum

Enum.EnumDesc<E extends Enum<E>>

Enum Constant Summary

Enum Constants

Enum Constant	Description
BEST_OF	Best-of-N - select the response with highest confidence score.
CONSENSUS	Consensus - extract and combine common points from all responses.
ENSEMBLE	Ensemble - combine all unique insights from every response.
VOTING	Majority voting - select the most common response.

Method Summary

Modifier and Type	Method	Description
static AggregationStrategy	forTaskType(String taskType)	Suggests the best strategy for a given task type.
String	getDescription()	Gets the description of this strategy.
boolean	requiresSynthesis()	Whether this strategy requires LLM synthesis to combine results.
static AggregationStrategy	valueOf(String name)	Returns the enum constant of this class with the specified name.
static AggregationStrategy[]	values()	Returns an array containing the constants of this enum class, in the order they are declared.

Methods inherited from class java.lang.Enum

compareTo, describeConstable, equals, getDeclaringClass, hashCode, name, ordinal, toString, valueOf

Methods inherited from class java.lang.Object

getClass, notify, notifyAll, wait, wait, wait

Enum Constant Details

VOTING

public static final AggregationStrategy VOTING

Majority voting - select the most common response. Best for: Classification, yes/no decisions, categorical outputs.

BEST_OF

public static final AggregationStrategy BEST_OF

Best-of-N - select the response with highest confidence score. Best for: Quality-critical tasks, when confidence scores are reliable.

CONSENSUS

public static final AggregationStrategy CONSENSUS

Consensus - extract and combine common points from all responses. Best for: Code review (common issues), fact extraction, validation.

ENSEMBLE

public static final AggregationStrategy ENSEMBLE

Ensemble - combine all unique insights from every response. Best for: Brainstorming, comprehensive analysis, creative tasks.

Method Details

values

public static AggregationStrategy[] values()

Returns an array containing the constants of this enum class, in the order they are declared.

Returns:

an array containing the constants of this enum class, in the order they are declared

valueOf

public static AggregationStrategy valueOf(String name)

Returns the enum constant of this class with the specified name. The string must match exactly an identifier used to declare an enum constant in this class. (Extraneous whitespace characters are not permitted.)

Parameters:

name - the name of the enum constant to be returned.

Returns:

the enum constant with the specified name

Throws:

IllegalArgumentException - if this enum class has no constant with the specified name

NullPointerException - if the argument is null

getDescription

public String getDescription()

Gets the description of this strategy.

requiresSynthesis

public boolean requiresSynthesis()

Whether this strategy requires LLM synthesis to combine results. VOTING and BEST_OF can work without LLM, while CONSENSUS and ENSEMBLE typically need an LLM to synthesize the combined output.

forTaskType

public static AggregationStrategy forTaskType(String taskType)

Suggests the best strategy for a given task type.

Parameters:

taskType - the type of task

Returns:

recommended strategy