The paper introduces an admission‑audit protocol for continual embodied agents, arguing that update admission should balance error control with retained learning opportunities within a fixed interaction budget. It critiques a range‑based confidence gate for failing to certify unchanged old‑task behavior, and proposes a paired‑binomial construction that reduces this burden when outcome disagreements are rare. Experiments on a one‑step pushing diagnostic show that fresh paired checks admit a significant portion of updates while the range‑based gate admits none, and a learned‑dynamics stress test helps distinguish model bias from feedback‑selection error.
By Qinzhen Ma, Ruihai Wu
arXiv:2605. 26343v2 Announce Type: replace Abstract: Mechanistic interpretability seeks to explain a model's behaviour by finding its circuit: the sparse subgraph of the model's computation that is causally responsible for it.
By Barsat Khadka
The paper introduces Cross-Behavior Policy Optimization (CBPO), a method that unifies offline demonstrations and policy-generated rollouts into a single regression loss using a fixed-reference target. CBPO eliminates the need for separate supervised fine‑tuning and reinforcement learning objectives, allowing positive and negative offline completions, reference responses, and current and historical rollouts to share a common reward‑labeled format and replay buffer. Experiments on two model scales and four mathematical reasoning benchmarks show that CBPO, especially the CBPO‑Unified variant, outperforms baseline methods in avg@32 and pass@32 metrics, with historical rollouts providing additional gains.
By Du Cheng, Junyu Lu, Jingfan Zhang, Yuzhuo Zhang, Haoxuan Jia, Shichao Weng
The paper introduces ActObs, a supervised fine‑tuning method that, unlike standard approaches, also predicts environment observations in agent trajectories. While both ActObs and action‑only training perform similarly after initial fine‑tuning, ActObs diverges during subsequent reinforcement learning, yielding higher pass@k scores on several benchmarks and better cross‑domain task performance. The authors attribute this advantage to ActObs’s joint supervision, which preserves observation gradients and prevents the policy from over‑specializing on actions alone.
By Juzheng Zhang, Disha Makhija, Manoj Ghuhan Arivazhagan, Vinayshekhar Bannihatti Kumar, Rashmi Gangadharaiah
arXiv:2610.28798v1 Announce Type: new
Abstract: Iterative ML agents develop models by editing code, running experiments, reading a validation score, and choosing what to try next. In current harnesse...
By Kehui Yao, Chuanbo Hu, Jiao Chen, Ramin Giahi, Reza Yousefi Maragheh, Lalitesh Morishetti, Ziwei Hong, Yiyun Su, Jianpeng Xu, Evren Korpeoglu, Kannan Achan
arXiv:2610.00360v1 Announce Type: cross
Abstract: Reinforcement learning (RL) for dexterous manipulation must discover finger-object contacts and then control the object precisely; the action noise t...
By Haoyu Wang, Siyuan Qian, Yanjun Li, Zeyu Zhang, Yandong Guo, Boxin Shi, Hao Tang
arXiv:2608. 01130v1 Announce Type: new Abstract: A broad range of models face the mismatch where they are updated through trajectory losses but are evaluated by downstream task reward.
By Yuyang Shen
The paper introduces Nous, a framework that separates learning, calibration, and revision certification for belief‑based agent memory. It shows that learning and certifying useful memory decisions can require quadratically fewer records than source calibration, and provides finite‑sample certificates for policy improvement without needing to recover source reliability. Experiments on MiniGrid environments demonstrate that the new certificate reliably accepts improvements over incumbents, outperforming earlier methods.
By Pranav Singh
The paper introduces Online Surrogate Repair (OSR), a closed‑loop algorithm that decouples the frequency of high‑fidelity evaluations from the length of an agent’s search by selectively updating a surrogate model with sparse, high‑fidelity data. An acquisition rule determines which candidate designs receive expensive evaluations, and the resulting labels refine the surrogate for subsequent episodes. Experiments on synthetic environments and the MADE benchmark show that OSR can reduce regret more efficiently than fixed‑surrogate approaches, requiring fewer oracle queries than high‑fidelity feedback after every episode.
By Xiaotang Feng, Philip Torr, Bruno Andreis
arXiv:2606. 30068v1 Announce Type: new Abstract: Joint-embedding predictive (JEPA-style) objectives learn representations by predicting future latents.
By Ayan Pendharkar
arXiv:2605. 20256v2 Announce Type: replace Abstract: Reinforcement learning has become a cornerstone for aligning and unlocking the reasoning capabilities of large-scale models.
By Xikai Zhang, Yongzhi Li, Likang Xiao, Yingze Zhang, Yanhua Cheng, Quan Chen, Peng Jiang, Wenjun Wu, Liu Liu
arXiv:2605. 03065v2 Announce Type: replace Abstract: Generative control policies (GCPs), such as diffusion- and flow-based control policies, have emerged as effective parameterizations for robot learning.
By Sarvesh Patil, Mitsuhiko Nakamoto, Manan Agarwal, Shashwat Saxena, Jesse Zhang, Giri Anantharaman, Cleah Winston, Chaoyi Pan, Douglas Chen, Nai-Chieh Huang, Zeynep Temel, Oliver Kroemer, Sergey Levine, Abhishek Gupta, Hongkai Dai, Paarth Shah, Max Simchowitz