Newest papers

AgenticRoboRL: Bringing Coding-Agent Post-Training to Agentic Robotics

Xinxin Liu, Bingxin Xu, Wenrui Bao, Ming Li, Wentao Bao, Chen Chen, Yuzhang Shang · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.28589 · cited by 0 works (OpenAlex) · open-access PDF

Portuguese

Os sistemas de robótica de verificação de agentes combinam os planejadores com armários robóticos para realizar tarefas complexas de manipulação do quadro. O trabalho recente melhora esses sistemas através de armários melhores e memória externa, mas baseia-se em poderosos modelos de fonte fechada como planejadores e não melhora as próprias capacidades dos planejadores. Em contraste, os agentes de codificação melhoraram substancialmente através da pós-treinamento do modelo em si. Portanto, investigamos se o pós-treinamento também pode melhorar os planejadores robóticos. No entanto, aplicá-lo através de armários robóticos requer acomodar diferentes mecanismos de execução, incluindo a invocação de habilidades do VLA e a geração de código de controle. Para este fim, introduzimos o AgenticRoboRL,

Machine translation (Meta M2M100); the English original follows.

Abstract

Agentic robotics systems combine planners with robot harnesses to perform complex manipulation tasks. Recent work improves these systems through better harnesses and external memory, but relies on powerful closed-source models as planners and does not improve the planners' own capabilities. In contrast, coding agents have improved substantially by post-training the model itself. We therefore investigate whether post-training can also improve robot planners. However, applying it across robot harnesses requires accommodating different execution mechanisms, including VLA skill invocation and control-code generation. To this end, we introduce AgenticRoboRL, a framework for post-training robot planners across different harnesses. The training recipe combines supervised fine-tuning with multi-turn reinforcement learning. To accommodate different execution mechanisms, harness-specific adapters connect recorded planner interactions with task outcomes, enabling a common RL training pipeline while keeping execution components fixed. On LIBERO-PRO, AgenticRoboRL raises the success rate of a 9B-parameter planner from 18.1% to 71.0% without external memory, approaching the 72.1% achieved by Codex (GPT-5.5) with external memory. These results demonstrate post-training as an effective approach for improving robot planners. We will release the framework and trained planner checkpoints.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Robot, Robotics, Planner, Artificial intelligence, Computer science, Task (project management)

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange