arXiv AI October 12, 2026 By Octi Zhang, Iretiayo Akinola, Rosario Scalise, Mateo Guaman Castro, Patrick Yin, Tobias Widmer, Miles Macklin, Chris Amevor, Dylan Turpin, Dirk Van Gelder, Jan Carius, Ankur Handa, Gavriel State, Yunrong Guo, Yashraj Narang

AlphaNIST: Emergent Assembly Skills from Binary Task Rewards

Read the original on arXiv AI →

AlphaNIST demonstrates that a single reinforcement‑learning policy can master 20 diverse assembly tasks on the NIST Assembly Task Board #1 using only a sparse binary reward, without demonstrations, progress shaping, scripted primitives, or per‑task tuning. The policy achieves 98.2% overall training success and can complete ten assembly pairs in a single episode, discovering dexterous, planning‑like behaviors such as selecting future grasps and reorienting parts using surrounding geometry. The work shows that task‑agnostic rewards can enable robots to learn complex manipulation strategies autonomously.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv AI

Jun 26

Play2Perfect: What Matters in Dexterous Play Pretraining for Precise Assembly?

arXiv:2606. 26428v1 Announce Type: cross Abstract: Multi-fingered robots promise the speed and dexterity of human hands, yet challenging problems such as precise assembly have remained out of reach.

By Tyler Ga Wei Lum, Kushal Kedia, C. Karen Liu, Jeannette Bohg

reinforcement-learning robotics fine-tuning

arXiv Machine Learning

Sep 21

From Pretraining to Proficiency: Real-World Subtask RL for Long-Horizon Manipulation with Minimal Human Intervention

The paper introduces PARTS, a real‑world subtask reinforcement learning framework that fine‑tunes a pretrained robot policy by focusing on critical bottleneck subtasks while keeping the base policy frozen. It uses agent‑generated selectors and success verifiers to provide local rewards, enabling learning even when full‑task successes are rare. Experiments on bimanual YAM and single‑arm Franka robots show that PARTS raises complete‑task success from 32% to 61% and from 50% to 95%, respectively, with only tens of minutes of real‑world RL rollouts and minimal human intervention.

By Sichang Su, Benjamin Yang, Zhiyun Deng, Boyuan Liang, Yip Fun Yeung, Zelin Wang, Lingfeng Sun

agents reinforcement-learning robotics fine-tuning

arXiv Computer Vision

Oct 2

InterEvolve: Test-Time Evolution of Reward Programs for Humanoid Loco-Manipulation

arXiv:2610.02196v1 Announce Type: cross Abstract: We study test-time evolution for humanoid loco-manipulation: solving tasks that a controller was never trained for by repurposing its existing skills...

By Zhuo Lin, Sirui Xu, Liuyu Bian, Yu-Xiong Wang, Liang-Yan Gui

llms agents robotics

arXiv Machine Learning

Jun 2

Coherent Off-Policy Improvement of Large Behavior Models with Learned Rewards

arXiv:2606. 02194v1 Announce Type: new Abstract: Distilling expert demonstration data into large generative models using behavioral cloning is a scalable approach to learning capable policies for robotic control, particularly for dexterous manipulation.

By Christian Scherer, Joe Watson, Theo Gruner, Daniel Palenicek, Ingmar Posner, Jan Peters

reinforcement-learning robotics fine-tuning

arXiv AI

Aug 21

EXIMO: VLM Guided Exploration of VLA Policies

arXiv:2608. 19891v1 Announce Type: new Abstract: How to efficiently finetune robot policies to learn new tasks on the fly?

By Bhavya Sukhija, Oliver Groth, Mohit Shridhar, Tim Hertweck, Michael Bloesch, Markus Wulfmeier, Abbas Abdolmaleki, Martin Riedmiller

llms reinforcement-learning robotics fine-tuning multimodal

Hugging Face Trending Papers

3d ago

LADDER: A Long-Horizon Robot Manipulation Benchmark

LADDER is a long‑horizon robot manipulation benchmark that scales from 1 to 10 subgoals within the same environment, covering 145 tasks across three suites and two embodiments. The benchmark evaluates low‑level policies and orchestration methods, showing that while low‑level policies perform well on single‑subgoal tasks, they fail on extended tasks, and orchestration improves performance but is limited by execution errors. Tool‑selection orchestration with GPT‑Policy achieves the highest success rate (~62%) but at significant time and cost.

llms agents robotics benchmarks