Hybrid Learning Architecture

What is Hybrid Learning?

ATLAS separates learning into two phases: offline foundation training (one-time, compute-intensive) and runtime continual learning (continuous, lightweight). This architecture solves the enterprise AI constraint: lack of high-quality preference data for complex business tasks. Key insight: Train a teacher once on math reasoning (where data is abundant and logic is clear), then apply that reasoning to any domain (CRM, telecom, debugging) without domain-specific retraining.

The Two-Phase Paradigm

Phase 1: Offline Foundation Training (Atlas Core)

Establish deep, generalizable skills through reinforcement learning:

Offline RL Training (24-48 hours)
├── SFT Warmup: Base reasoning capabilities
├── GRPO Training: Adaptive teaching skills
└── Output: Teacher model with foundational knowledge

Characteristic	Detail
Compute requirement	Minimum 2 GPUs (1 for vLLM, 1 for training)
Training data	~900 curated dual-agent demonstrations from Arc-ATLAS-Teach-v0
Foundation domain	Mathematics (reasoning, sequential thinking, problem decomposition)
Transfer capability	Math-trained reasoning generalizes to debugging, coding, analytical tasks
Cost model	One-time; amortized over all deployments

Phase 2: Runtime Continual Learning (Atlas SDK)

The atlas-sdk runtime adapts pre-trained teachers to specific tasks:

Runtime Loop (continuous)
├── Task Analysis: Identify performance gaps via rewards
├── Experimentation: Adjust teaching prompts and strategies
├── Trace Export: Capture high-signal interactions
└── Output: Data for next GRPO cycle + incremental improvements

Characteristic	Detail
Infrastructure	Managed APIs in SDK
Speed	Improves over hours vs full retraining cycles
Safety	Non-degradation guarantee via reward guardrails
Feedback loop	Feeds fresh traces into next offline training job

Performance Comparison

Training Approach	Time to Deploy	Performance Gain	Cost	Generalization
Fine-tuning	1-2 weeks	+10-15%	$1000s	Poor
Few-shot prompting	Minutes	+3-5%	~$1	Limited
ATLAS (Runtime + GRPO)	Hours	+15.7% baseline	API + GPU	Excellent

*With pre-trained teacher models

Cross-Domain Transfer Results

Why Mathematics as Foundation?

Clear correctness: Verifiable ground truth (unlike business tasks)
Abundant data: Thousands of well-structured problems
Pure reasoning: Systematic thinking, problem decomposition, logical flow
Complexity gradient: Simple arithmetic → AIME-level competition problems

Our Teacher trained on ~7,000 math problems achieved 46% accuracy on AIME-25 (top-10 SOTA level).

Validated Transfer

Mathematics → Telecom (τ²-bench):

Teacher trained only on math problems
Applied to telecom troubleshooting (no telecom training)
Result: 24.0% pass@1 (vs 18.0% for GPT-4.1, Claude 3.7)

Mathematics → CRM (CRMArena-Pro):

Same math-trained teacher
Applied to policy compliance tasks
Result: 54% task completion (vs ~35% for leading models)
Critical accuracy: 69.2% identifying policy violations

→ Full methodology in Technical Report

Quick Start

Offline Foundation

Download pre-trained teacher or train custom:

# Option 1: Pre-trained
huggingface-cli download Arc-Intelligence/ATLAS-8B-Thinking

# Option 2: Custom (2+ GPUs)
scripts/launch.sh 2 src/atlas_core/configs/recipe/teacher_sft.yaml
scripts/launch_with_server.sh 1 1 src/atlas_core/configs/recipe/teacher_rcl.yaml

Run GRPO on Exported Traces

atlas-core offline-pipeline \
  --export-path traces/runtime.jsonl \
  --wandb-project atlas-production

Deploy Enhanced Model

Point SDK at new checkpoint:

teacher:
  llm:
    provider: huggingface
    model: /models/atlas-teacher-grpo
    temperature: 0.2

Next Steps

Adaptive Dual-Agent Reasoning

Two-pass dual-agent mechanism

Offline Training Guide

Run GRPO training pipeline

Training Configuration

Hydra composition and overrides

SDK Runtime

Export traces and manage runtime learning

References

ATLAS Technical Report - Sections 3.1-3.3 on hybrid architecture
GRPO Algorithm - Foundation for offline training
SDK Runtime Guide - Export traces and continual learning

Getting Started

SDK Guides

Examples

Training

Core Concepts

Reference

Benchmarks

Hybrid Learning Architecture

What is Hybrid Learning?

The Two-Phase Paradigm

Phase 1: Offline Foundation Training (Atlas Core)

Phase 2: Runtime Continual Learning (Atlas SDK)

Performance Comparison

Cross-Domain Transfer Results

Why Mathematics as Foundation?

Validated Transfer

Quick Start

Next Steps

Adaptive Dual-Agent Reasoning

Offline Training Guide

Training Configuration

SDK Runtime

References

​What is Hybrid Learning?

​The Two-Phase Paradigm

​Phase 1: Offline Foundation Training (Atlas Core)

​Phase 2: Runtime Continual Learning (Atlas SDK)

​Performance Comparison

​Cross-Domain Transfer Results

​Why Mathematics as Foundation?

​Validated Transfer

​Quick Start

​Next Steps

Adaptive Dual-Agent Reasoning

Offline Training Guide

Training Configuration

SDK Runtime

​References

What is Hybrid Learning?

The Two-Phase Paradigm

Phase 1: Offline Foundation Training (Atlas Core)

Phase 2: Runtime Continual Learning (Atlas SDK)

Performance Comparison

Cross-Domain Transfer Results

Why Mathematics as Foundation?

Validated Transfer

Quick Start

Next Steps

References