paper-with-me

홈 › Papers

EmbodiedSWE: Coding Agents for Long Horizon Dexterous Robotics

2026-09-23 · Haoxiang You, Zeyu Shen, Yilang Liu, Zhicheng Zheng, Lihan Zha, Kashu Yamazaki, Mingtong Zhang, Suning Huang, Jiankai Sun, Qianzhong Chen, Lucy He, Kaiyuan Liu, Haoran Chang, Katerina Fragkiadaki, Dhruv Shah, Mac Schwager, Peter Henderson, Ian Abraham, Canwen Xu hf

We study coding agents for long-horizon, dexterous robotics and ask whether their solutions can provide scalable supervision for learning general robot policies. To test this, we develop EMBODIEDSWE-BENCH, a simulation benchmark for coding agents spanning contact-rich manipulation, deformable objects, and long-horizon tasks requiring up to half an hour of continuous interaction. We find that frontier coding agents can solve complex long-horizon tasks and transfer prior solutions across both tasks and embodiments. We also design supporting tools that help agents more effectively solve these tasks. However, the resulting solutions require substantial iterative interaction and are typically specialized to individual task instances. We therefore introduce EMBODIEDSWE-GEN, which expands a single solution from coding agent into large diverse trajectories for training a VLA. VLA performance improves with more generated demonstrations, and agent-aided diversification improves generalization to held-out task variations. We also show that a VLA finetuned solely on coding-agent-generated simulation demonstrations completes a long-horizon task on real robot. Together, our framework uses coding agents to solve complex robotics tasks and turn verified solutions into scalable supervision for robot policies.

📄 PDF Abstract BibTeX arXiv:2609.27308

Code (3)

Aaron617/agent-arXiv-daily ★ 10
EmbodiedSWE/EmbodiedSWE ★ 41
arxivsub/arXivSub_daily_arxiv ★ 4

Similar Papers 제목 키워드 기반

Sequential Dexterity: Chaining Dexterous Policies for Long-Horizon Manipulation

2023-09-02 · Yuanpei Chen, Chen Wang, Li Fei-Fei, C. Karen Liu

Many real-world manipulation tasks consist of a series of subtasks that are significantly different from one another. Such long-horizon, complex tasks highlight the potential of dexterous hands, which possess adaptabilit…

Reinforcement Learning (RL)

NL2Repo-Bench: Towards Long-Horizon Repository Generation Evaluation of Coding Agents

2025-12-14 · Jingzhe Ding, Shengda Long, Changxin Pu, Huan Zhou 외 arxiv

Recent advances in coding agents suggest rapid progress toward autonomous software development, yet existing benchmarks fail to rigorously evaluate the long-horizon capabilities required to build complete software system…

Code Generation

LabDex: A Hierarchical Benchmark for Dexterous Manipulation in Laboratories

2026-08-19 · Zhipeng Tang, Sihang Chen, Sha Zhang, Peihao Yang 외 arxiv

Autonomous laboratories hold great promise for accelerating scientific discovery. To achieve this vision, robots are supposed to dexterously manipulate diverse labware and instruments and execute long-horizon, state-depe…

Hand-in-the-Loop: Improving VLA Policies for Dexterous Manipulation via Seamless Hand-Arm Intervention

2026-05-14 · Zhuohang Li, Liqun Huang, Wei Xu, Zhengming Zhu 외 arxiv

Vision-Language-Action (VLA) models are prone to compounding errors in dexterous manipulation, where high-dimensional action spaces and contact-rich dynamics amplify small policy deviations over long horizons. While Inte…

DexDrummer: In-Hand, Contact-Rich, and Long-Horizon Dexterous Robot Drumming

2026-03-23 · Hung-Chieh Fang, Amber Xie, Jennifer Grannen, Kenneth Llontop 외 arxiv

Performing in-hand, contact-rich, and long-horizon dexterous manipulation remains an unsolved challenge in robotics. Prior hand dexterity works have considered each of these three challenges in isolation, yet do not comb…

Reinforcement LearningTrajectory Planning