TARC (Time‑Adaptive Robotic Control) is a reinforcement‑learning framework that lets a policy predict both a control action and how long it should be applied, thereby learning temporally extended actions. By optimizing task performance under constraints on the number of control switches, TARC can adapt its control rate online, using high‑frequency feedback only when necessary. Experiments on a high‑speed RC car, a Unitree Go1 quadruped, and a vision‑language action model show that TARC matches the performance of high‑frequency discrete‑time controllers while operating at less than half their control frequency.
By Arnav Sukhija, Lenart Treven, Jin Cheng, Florian D\"orfler, Stelian Coros, Andreas Krause
arXiv:2608. 03483v1 Announce Type: cross Abstract: Existing chunk-based Vision-Language-Action (VLA) models execute a fixed number of actions (i.
By Weichen Xu, Zhenhua Liu, Lin Luo, Yaobo Liang, Chengtang Yao, Qingyu Mei, Jian Cao, Xixin Cao, Xing Zhang, Jiaolong Yang, Baining Guo
arXiv:2606. 25700v1 Announce Type: new Abstract: When fine-tuning Large Language Models (LLMs), there has been success in minimizing both memory usage and computation with Parameter-Efficient Fine-Tuning (PEFT), like Low Rank Adaptation (LoRA).
By Samuel Valland Lyngset, Tor Viljen Raanaas, Gard Sveipe, Eirik M{\o}ller Nilsen, Jim Torresen, Kai Olav Ellefsen, Tobias L{\o}mo
arXiv:2608. 02508v1 Announce Type: new Abstract: Learning-based memory systems for self-evolving LLM agents face two tightly coupled challenges.
By Yi Yang, Zhennan Chen, Yihong Zhuang, Tiehan Fan, Yinan Chen, Jian Li, Jian Yang, Ying Tai
arXiv:2607. 09042v1 Announce Type: new Abstract: Reinforcement learning (RL) is increasingly used to post-train vision-language-action (VLA) models, but every update consumes robot rollouts that are slow and costly to collect, making sample efficiency a central concern.
By Iris Xu, Sunshine Jiang, John Marangola, Nitish Dashora, Richard Li, Thomas Liu, Zexue He, Yuheng Zhi, Alex Pentland, Pulkit Agrawal, Zhang-Wei Hong
arXiv:2603. 04910v2 Announce Type: replace-cross Abstract: Imitation learning from human demonstrations has achieved significant success in robotic control, yet most visuomotor policies still condition on single-step observations or short-context histories, making them struggle with non-Markovian tasks that require long-term memory.
By Yuheng Lei, Zhixuan Liang, Hongyuan Zhang, Ping Luo
arXiv:2609.39794v1 Announce Type: new
Abstract: Vision-Language-Action (VLA) models have shown strong promise for general-purpose robotic manipulation, yet adapting them to new tasks and domains rema...
By Zaijing Li, Rui Shao, Bing Hu, Haoyu Zhang, Dongmei Jiang, Liqiang Nie
arXiv:2606. 26183v1 Announce Type: cross Abstract: Building a generalist robot that can leverage prior knowledge for continuous task adaptation remains a significant challenge.
By Zhihao Gu, Lin Wang
arXiv:2606. 16978v1 Announce Type: cross Abstract: For residual learning that refines existing behavior, sample efficiency depends on two things: how much information each rollout returns, and how efficiently the learner uses that information.
By Kai Ploeger, Jan Peters
The paper introduces Divide-and-Remember (D&R), a recursive memory method for vision-language-action (VLA) policies that optimises memory by maximizing the conditional mutual information between actions and memory given observations. D&R recursively divides the full history into top‑K selections over 2K tokens, using a shared lightweight selector across all recursion blocks to handle unbounded histories efficiently. Evaluated on the RoboMME benchmark of 16 long‑horizon manipulation tasks, D&R achieves state‑of‑the‑art success rates with consistent gains across all suites while using only 64 tokens, and similar improvements are observed in real‑robot experiments.
By Xuehui Yu, Eason Yu, Meiyi Wang, Haozhe Du, Stefano V. Albrecht, Harold Soh
The paper introduces MI‑SARSA, an on‑policy temporal‑difference algorithm that incorporates mutual‑information regularization to model bounded rationality in reinforcement learning. By penalizing state‑specific deviations from a learned marginal action prior, the algorithm selectively uses state information only when the expected return outweighs the informational cost, yielding a reward‑complexity tradeoff. MI‑SARSA also predicts reaction times, showing that stronger information penalties lead to simpler policies, lower control costs, and faster responses, while regularization mitigates performance loss after environmental shifts at the expense of asymptotic return.
By James Wu, Chris R. Sims
arXiv:2606. 08452v1 Announce Type: new Abstract: In many real-world settings, data streams are nonstationary and arrive sequentially, requiring learning systems to adapt continuously without retraining from scratch.
By Nazreen Shah, Govinda Arya, Bharath B. N., Ranjitha Prasad