Heavy Thinking Orchestration (CONCEPT:AHE-3.4)¶
Overview¶
Two-stage parallel-then-deliberate reasoning pipeline with tiered complexity gating, trajectory pruning/shuffling, iterative refinement, and KG-native trajectory persistence (CONCEPT:AHE-3.4). The former HeavyThinkingOrchestrator is now consolidated into the unified ParallelEngine (same code path for a 1-agent call up to a 300-agent swarm).
Implementation Details¶
- Source Code:
agent_utilities/graph/parallel_engine.py - Pillar: AHE
Documentation Coverage¶
This is an auto-generated dedicated concept page to ensure 100% documentation coverage across the ecosystem.
Continual Learning & Experience (CONCEPT:AHE-3.4)¶
Overview¶
Experience distillation via cross-rollout critique (CONCEPT:AHE-3.4), decomposed context retrieval (CONCEPT:AHE-3.4), and Memory-Aware Test-Time Scaling (CONCEPT:AHE-3.4).
Implementation Details¶
- Source Code:
agent_utilities/graph/verification.py - Pillar: AHE
Documentation Coverage¶
This is an auto-generated dedicated concept page to ensure 100% documentation coverage across the ecosystem.
KG-Native Agentic Task Detection (CONCEPT:AHE-3.4)¶
Overview¶
Evaluates topological complexity to route dense API toolchains to complex models.
Implementation Details¶
- Source Code:
agent_utilities/graph/_router_impl.py - Pillar: AHE
Documentation Coverage¶
This is an auto-generated dedicated concept page to ensure 100% documentation coverage across the ecosystem.
Topological Reasoning Detection (CONCEPT:AHE-3.4)¶
Overview¶
Maps user queries to MathematicalFoundationNode or quantitative financial concepts to trigger reasoning models.
Implementation Details¶
- Source Code:
agent_utilities/graph/_router_impl.py - Pillar: AHE
Documentation Coverage¶
This is an auto-generated dedicated concept page to ensure 100% documentation coverage across the ecosystem.