# RoboAware: Learning to Coordinate Embodied Skills from Counterfactual Outcomes

arXiv: https://arxiv.org/abs/2610.11480 · HTML: https://mlsanity.com/paper/2610.11480/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Agent skill learning and evolution, one of 16 directions in LLM agents and tool use.
- Builds on 43 of its 84 references that are in the map.
- First posted on arXiv 8 Oct 2026.

## Placed in

- LLM agents and tool use / [Agent skill learning and evolution](https://mlsanity.com/agents/agent-skill-learning-and-evolution/)

## Builds on (most cited first, 30 of 43)

- [SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics](https://mlsanity.com/paper/2506.01844/) (2025)
- [robosuite: A Modular Simulation Framework and Benchmark for Robot Learning](https://mlsanity.com/paper/2009.12293/) (2020)
- [Fast-WAM: Do World Action Models Need Test-time Future Imagination?](https://mlsanity.com/paper/2603.16666/) (2026)
- [LIBERO-PRO: Towards Robust and Fair Evaluation of Vision-Language-Action Models Beyond Memorization](https://mlsanity.com/paper/2510.03827/) (2025)
- [StarVLA: A Lego-like Codebase for Vision-Language-Action Model Developing](https://mlsanity.com/paper/2604.05014/) (2026)
- [ABot-M0: VLA Foundation Model for Robotic Manipulation with Action Manifold Learning](https://mlsanity.com/paper/2602.11236/) (2026)
- [CaP-X: A Framework for Benchmarking and Improving Coding Agents for Robot Manipulation](https://mlsanity.com/paper/2603.22435/) (2026)
- [RynnVLA-002: A Unified Vision-Language-Action and World Model](https://mlsanity.com/paper/2511.17502/) (2025)
- [ASPIRE: Agentic /Skills Discovery for Robotics](https://mlsanity.com/paper/2607.00272/) (2026)
- [MolmoAct2: Action Reasoning Models for Real-world Deployment](https://mlsanity.com/paper/2605.02881/) (2026)
- [Harness VLA: Steering Frozen VLAs into Reliable Manipulation Primitives via Memory-Guided Agents](https://mlsanity.com/paper/2607.08448/) (2026)
- [TOPReward: Token Probabilities as Hidden Zero-Shot Rewards for Robotics](https://mlsanity.com/paper/2602.19313/) (2026)
- [RDT2: Exploring the Scaling Limit of UMI Data Towards Zero-Shot Cross-Embodiment Generalization](https://mlsanity.com/paper/2602.03310/) (2026)
- [Playful Agentic Robot Learning](https://mlsanity.com/paper/2606.19419/) (2026)
- [RHO: Your Coding Agent is Secretly a Roboticist](https://mlsanity.com/paper/2606.16458/) (2026)
- [InternVLA-A1.5: Unifying Understanding, Latent Foresight, and Action for Compositional Generalization](https://mlsanity.com/paper/2607.04988/) (2026)
- [Faster-WAM: Efficient Inference-Time Future Conditioning for Robust World Action Models](https://mlsanity.com/paper/2608.04404/) (2026)
- [SwitchVLA: Execution-Aware Task Switching for Vision-Language-Action Models](https://mlsanity.com/paper/2506.03574/) (2025)
- [VLS: Steering Pretrained Robot Policies via Vision-Language Models](https://mlsanity.com/paper/2602.03973/) (2026)
- [GaP: A Graph-as-Policy Multi-Agent Self-Learning Harness For Variational Automation Tasks](https://mlsanity.com/paper/2607.05369/) (2026)
- [World-Language-Action Model for Unified World Modeling, Language Reasoning, and Action Synthesis](https://mlsanity.com/paper/2606.05979/) (2026)
- [Large Reward Models: Generalizable Online Robot Reward Generation with Vision-Language Models](https://mlsanity.com/paper/2603.16065/) (2026)
- [VoLo: A Physical Orchestrator for Open-Vocabulary Long-Horizon Manipulation](https://mlsanity.com/paper/2606.07723/) (2026)
- [What Matters in Orchestrating Robot Policies: A Systematic Study of Hierarchical VLA Agents](https://mlsanity.com/paper/2606.10267/) (2026)
- [RoboHarness: Memory-Driven Orchestration of Heterogeneous Robot Policies for Long-Horizon Planning](https://mlsanity.com/paper/2607.18060/) (2026)
- [Addressing the Orchestration Gap in Generalist Robots via Physical Agency](https://mlsanity.com/paper/2607.21725/) (2026)
- [Learning Actionable Manipulation Recovery via Counterfactual Failure Synthesis](https://mlsanity.com/paper/2603.13528/) (2026)
- [Act-Observe-Rewrite: Multimodal Coding Agents as In-Context Policy Learners for Robot Manipulation](https://mlsanity.com/paper/2603.04466/) (2026)
- [PRTS: A Primitive Reasoning and Tasking System via Contrastive Representations](https://mlsanity.com/paper/2604.27472/) (2026)
- [Towards Long-horizon Embodied Agents with Tool-Aligned Vision-Language-Action Models](https://mlsanity.com/paper/2605.13119/) (2026)

## Abstract (arXiv)

Embodied coding agents can combine modular robot skills with frozen end-to-end policies, yet effective composition requires anticipating which policy family will succeed in the current physical state. We present RoboAware, which builds on coding agents' skill orchestration by learning only a state-conditioned responsibility coordinator from counterfactual outcomes. Inspired by the success of REPL, we propose the P5 schema and formulate a hierarchical MDP based on it. P5 organizes skills uniformly into five semantic stages, defining where responsibility can be compared. To address the lack of counterfactual branch outcomes in existing work, we introduce State-Locked Counterfactual Branching (SCB), which restores the same training state to generate and execute a code block from each admissible family, exposing outcomes that selected-branch experience leaves unobserved. Building on this, we propose Execution-Aware Learning (EAL), which combines Monte Carlo tree search with Q-learning to distill these outcomes into family-conditioned values. At deployment, the coordinator selects the policy family according to observable context, and the frozen coding agent generates the next local code block. Comprehensive single-episode evaluations on 100 tasks show that RoboAware reaches a 77.0% overall success rate, with SOTA averages of 90.0% on RoboSuite, 73.8% on diverse LIBERO-Pro task clusters, and 90.0% on challenging RoboTwin bimanual tasks, outperforming existing code-as-policy and VLA-harness baselines.