# Atlas: Orchestrating Heterogeneous Models and Tools for Multi-Domain Complex Reasoning

arXiv: https://arxiv.org/abs/2601.03872 · HTML: https://mlsanity.com/paper/2601.03872/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 26 of its 74 references that are in the map.
- First posted on arXiv 7 Jan 2026.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)
- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 26 of 26)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [Qwen2.5-Coder Technical Report](https://mlsanity.com/paper/2409.12186/) (2024)
- [Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement](https://mlsanity.com/paper/2409.12122/) (2024)
- [RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedback](https://mlsanity.com/paper/2309.00267/) (2023)
- [InternLM2 Technical Report](https://mlsanity.com/paper/2403.17297/) (2024)
- [ReTool: Reinforcement Learning for Strategic Tool Use in LLMs](https://mlsanity.com/paper/2504.11536/) (2025)
- [Large Multimodal Agents: A Survey](https://mlsanity.com/paper/2402.15116/) (2024)
- [Tool-Star: Empowering LLM-Brained Multi-Tool Reasoner via Reinforcement Learning](https://mlsanity.com/paper/2505.16410/) (2025)
- [TableVQA-Bench: A Visual Question Answering Benchmark on Multiple Table Domains](https://mlsanity.com/paper/2404.19205/) (2024)
- [The Avengers: A Simple Recipe for Uniting Smaller Language Models to Challenge Proprietary Giants](https://mlsanity.com/paper/2505.19797/) (2025)
- [OmniRouter: Budget and Performance Controllable Multi-LLM Routing](https://mlsanity.com/paper/2502.20576/) (2025)
- [UI-S1: Advancing GUI Automation via Semi-online Reinforcement Learning](https://mlsanity.com/paper/2509.11543/) (2025)
- [TemplateRL: Structured Template-Guided Reinforcement Learning for LLM Reasoning](https://mlsanity.com/paper/2505.15692/) (2025)
- [ICL-Router: In-Context Learned Model Representations for LLM Routing](https://mlsanity.com/paper/2510.09719/) (2025)
- [GUI-Shepherd: Reliable Process Reward and Verification for Long-Sequence GUI Tasks](https://mlsanity.com/paper/2509.23738/) (2025)
- [AStar: Boosting Multimodal Reasoning with Automated Structured Thinking](https://mlsanity.com/paper/2502.02339/) (2025)
- [Route to Reason: Adaptive Routing for LLM and Reasoning Strategy Selection](https://mlsanity.com/paper/2505.19435/) (2025)
- [HunyuanOCR Technical Report](https://mlsanity.com/paper/2511.19575/) (2025)
- [Tool-integrated Reinforcement Learning for Repo Deep Search](https://mlsanity.com/paper/2508.03012/) (2025)
- [Tool-Augmented Policy Optimization: Synergizing Reasoning and Adaptive Tool Use with Reinforcement Learning](https://mlsanity.com/paper/2510.07038/) (2025)
- [Orion: A Unified Visual Agent for Multimodal Perception, Advanced Visual Reasoning and Execution](https://mlsanity.com/paper/2511.14210/) (2025)

## Built on by (most cited first, 11 of 11)

- [OPID: On-Policy Skill Distillation for Agentic Reinforcement Learning](https://mlsanity.com/paper/2606.26790/) (2026)
- [SEED: Self-Evolving On-Policy Distillation for Agentic Reinforcement Learning](https://mlsanity.com/paper/2607.14777/) (2026)
- [Spark: Strategic Policy-Aware Exploration via Dynamic Branching for Long-Horizon Agentic Learning](https://mlsanity.com/paper/2601.20209/) (2026)
- [ProactiveMobile: A Comprehensive Benchmark for Boosting Proactive Intelligence on Mobile Devices](https://mlsanity.com/paper/2602.21858/) (2026)
- [Android Coach: Improve Online Agentic Training Efficiency with Single State Multiple Actions](https://mlsanity.com/paper/2604.07277/) (2026)
- [Uno-Orchestra: Parsimonious Agent Routing via Selective Delegation](https://mlsanity.com/paper/2605.05007/) (2026)
- [ZipRL: Adaptive Multi-Turn Context Compression with Hindsight Response Replay](https://mlsanity.com/paper/2605.28069/) (2026)
- [Implicit Hierarchical GRPO: Decoupling Tool Invocation from Execution for Tool-Integrated Mathematical Reasoning](https://mlsanity.com/paper/2605.18500/) (2026)
- [Maestro: Reinforcement Learning to Orchestrate Hierarchical Model-Skill Ensembles](https://mlsanity.com/paper/2605.22177/) (2026)
- [SwarmBench: Can Large Language Models Act as Agent Swarm Orchestrators?](https://mlsanity.com/paper/2608.30661/) (2026)
- [What Can Component-Replacement Evidence Establish? A Critical Scoping Review of Local Decisions in LLM Agents](https://mlsanity.com/paper/2609.39989/) (2026)

## Abstract (arXiv)

The integration of large language models (LLMs) with external tools has significantly expanded the capabilities of AI agents. However, as the diversity of both LLMs and tools increases, selecting the optimal model-tool combination becomes a high-dimensional optimization challenge. Existing approaches often rely on a single model or fixed tool-calling logic, failing to exploit the performance variations across heterogeneous model-tool pairs. In this paper, we present ATLAS (Adaptive Tool-LLM Alignment and Synergistic Invocation), a dual-path framework for dynamic tool usage in cross-domain complex reasoning. ATLAS operates via a dual-path approach: (1) training-free cluster-based routing that exploits empirical priors for domain-specific alignment, and (2) RL-based multi-step routing that explores autonomous trajectories for out-of-distribution generalization. Extensive experiments across 15 benchmarks demonstrate that our method outperforms closed-source models like GPT-4o, surpassing existing routing methods on both in-distribution (+10.1%) and out-of-distribution (+13.1%) tasks. Furthermore, our framework shows significant gains in visual reasoning by orchestrating specialized multi-modal tools.