Skip to content

CAPEX: Efficiently Distilling Foundation Model Behavior into Deployable Robot Policies through Experience-Adaptive Reasoning

Sep 2026 · 0 citations · 54 references
Computer Science

TL;DR

CAPEX, an experience-conditioned demonstration collection framework that uses execution experience from previous attempts to adapt how frequently the foundation model must observe, reason, and replan, is introduced and suggests that foundation models can serve as scalable sources of reusable robot experience.

Abstract

Robot learning has largely relied on human-teleoperated demonstrations to acquire effective learnable behaviors. However, human-operated data collection processes can be unintuitive, difficult to scale, and inherently asynchronous. We explore an alternative: distilling physical behavior from general-purpose multimodal foundation models into deployable robot policies by using the foundation model itself as an autonomous demonstrator. While sufficiently capable models can generate successful zero-shot manipulation trajectories, repeatedly invoking them during physical execution is slow and expensive, limiting their utility as scalable data generators. As a solution, we introduce CAPEX, an experience-conditioned demonstration collection framework that uses execution experience from previous attempts to adapt how frequently the foundation model must observe, reason, and replan. We evaluate across RoboCasa tasks and on physical Franka and bimanual YAM-arm platforms, measuring task success, model calls, token usage, collection time, and cost. We further train Diffusion Policy and ACT on matched sets of human-teleoperated and foundation-model-generated demonstrations to evaluate the downstream learning value of autonomously collected data. We find that CAPEX increases the number of successful demonstrations by 4.3x while reducing the cost per successful demonstration by 80%. Policies trained on CAPEX-generated data approach the performance of those trained on matched human demonstrations; with longer training, this gap largely closes for policies trained from scratch. These results suggest that foundation models can serve as scalable sources of reusable robot experience. Project page: https://capex-paper.github.io/

View source

Similar papers

Sep 2026

Learning Beyond What Humans Can Demonstrate

Behavior cloning for robot manipulation relies on expert demonstrations. However, for tasks that require dynamic stability, precise contact timing, or dexterous coordination, human operators may find it hard or even impossible to collect data. We study this infeasible-demonstration regime and propose GLIDE: Guardrails...

Yu-Chen Song, Aditya Mittal, Unnat Jain · 1 citation
Preprint Oct 2026

CoEvolve: Self-Evolving Code Policies from Skills to Strategies for Humanoid Robots

Recent advances in Vision-Language-Action (VLA) models and World Action Models (WAMs) have expanded the manipulation and whole body capabilities of individual robots. Yet a single robot remains limited by its embodiment, and many real world tasks require capabilities that can only emerge through cooperation. Existing m...

Zi-Cheng Liu, Haochen Wu, Jia-Wei He et al. · 0 citations
Sep 2026

RACaP: Agentic Reasoning, Acting, and Coding as Policies for Evolvable Robot Learning

RACaP is introduced, an agentic framework that moves coding to evolution and uses a Reasoning-and-Acting loop to call frozen, typed Policy APIs at deployment and shows that separating reusable code from runtime decisions supports continued evolution, effective transfer, and efficient long-horizon control.

Ze-Xi Li, Ye-Hang Zhang, Hao-Jian Huang et al. · 6 citations · ⚡1
Preprint Oct 2026

RoboDoctor: Training-Free Recursive Self-Improvement for Robot Policies

Generalist robot policies and language-model agents provide complementary capabilities, but completing a task also requires adapting their use to the consequences of physical interaction. We study execution as a locus of adaptation: feedback guides the current action and supplies evidence for revising subsequent decisi...

He-Yang Yu, Hao-Min Li, Si-Hang Li et al. · 1 citation

DynaHarness: A Dynamic Physical Harness for Self-Evolving Robot Agents

Pretrained robot policies provide useful action priors, but long-horizon manipulation still requires coordination between semantic reasoning and physical execution. Semantic reasoning operates at a coarser timescale than physical interaction, while episode-level failures provide limited guidance on which system compone...

Hao-Yuan Deng, Jie-Bin Liu, Teng-Xiao Zhang et al. · 2 citations

CodeActionBench: Evaluating Agentic Code-as-Policy for Embodied Manipulation

CodeActionBench is introduced, a benchmark of 25 manipulation tasks that evaluates this capability through agentic Code-as-Policy and provides a controlled testbed for measuring how general-purpose models translate their capabilities into manipulation behavior and for examining typical failure scenarios in that process...

Yiheng Lyu, Xueying Jiang, Wen-Hao Li et al. · 3 citations

Related blog posts

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.