CST‑WM is a causally structured world model designed for embodied visual tracking, where a robot must keep a moving target visible and recover it after occlusion or drift. The model separates state into target‑evidence, robot, and observation branches, removing direct action‑to‑target‑evidence edges to prevent causal hallucination and instead letting actions influence evidence through robot motion and resulting views. Evaluated on EVT‑Bench, Habitat 3.0, and real‑world trials with a Unitree Go2 quadruped, CST‑WM outperforms reactive trackers and other world‑model baselines in following, distance control, safety, and re‑acquisition, achieving 20 of 30 successful real‑world recoveries versus 14 for TrackVLA.
By Junyi Hu, Shuaihang Yuan, Jiazhao Liang, Yi Fang
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
arXiv:2607. 23602v1 Announce Type: cross Abstract: Controllers based on sampling and latent world models assign a predicted terminal cost to each candidate action sequence, choose the minimum, execute its first action block, and replan.
By Liangyu Li, Qingwen Liu, Mingqing Liu
arXiv:2510. 14807v3 Announce Type: replace Abstract: We revisit exploration collapse in reinforcement learning with verifiable rewards (RLVR), from the perspective of the \emph{candidate distribution} for next-token prediction.
By Ruotian Peng, Yi Ren, Zhouliang Yu, Weiyang Liu, Yandong Wen
arXiv:2606. 09115v1 Announce Type: new Abstract: Offline reinforcement learning (RL) offers a path to policy improvement from logged data alone, using historical returns or other measurable outcomes as world feedback.
By Lena Krieger, Xuan Zhao, Zhuo Cao, Qin Wang, Hanno Scharr, Ira Assent
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:2606. 17043v1 Announce Type: cross Abstract: When pretrained VLA policies are fine-tuned through online RL, each rollout episode produces only a single binary outcome (success or failure), yet the actor update requires per-transition supervision.
By Tongyan Fang, Siyuan Huang, Naiyu Fang, Ganlong Zhao, Zhongjin Luo, Jianbo Liu, Xiaogang Wang, Ying Dong, Hongsheng Li
GigaBrain-WBC-0.5 is a Behavior World Model that uses a causal Transformer to predict next actions, states, and a distribution over latent behavior commands for humanoid whole-body control. It incorporates an automatic terrain-annotation pipeline to recover 3D contact geometry from motion data, allowing the model to learn how terrain and objects influence dynamics. The system detects implausible commands online, retracts them onto learned behaviors, and achieves high success rates in terrain interaction, command robustness, and fall recovery, with promising hardware trials on different robots.
By Ziyang Cheng, Tianshu Tang, Jinxin Lan, Xinze Chen, Yuhan Gong, Zhichao Liu, Changzhong Wu, Yahao Mao, Zongyan Deng, Mingxuan Ma, Huasen Xi, Yilong Liu, Yutong Wu, Xiaofeng Wang, Yang Wang, Yun Ye, Guan Huang, Xiaojie Jin, Zheng Zhu, Jiwen Lu
The paper introduces LP‑BTS, a learning‑guided planning framework for mobile charging in large, dynamic action spaces. It uses a graph proposal policy to narrow candidate stops, a value critic to evaluate leaf nodes, and edge‑budgeted PUCT to compare short simulated futures before action selection. Experiments on a 30‑scenario battery‑life benchmark show LP‑BTS achieving the highest survival and alive‑AUC, outperforming domain‑engineered baselines and heuristic policies.
By Liang-Ching Tao, Pi-Chung Wang
arXiv:2609. 03241v1 Announce Type: cross Abstract: A reasoning model can improve from its own on-policy experience, but this inner loop is fragile: terminal verifiers provide reliable yet sparse supervision, while dense same-model guidance can reinforce false confidence or overconcentrate learning on a narrow solution mode.
By Zixun Huang, Kishan Panaganti, Haitao Mi, Leowei Liang
arXiv:2608. 07719v1 Announce Type: new Abstract: Offline reinforcement learning repeatedly trains policies from a fixed transition pool, making redundant data costly across seeds and hyperparameters, while naive subsampling can remove rare transitions needed for long-horizon credit assignment.
By Ibne Farabi Shihab, Sanjeda Akter, Abu Sa-Adat Mohamed Moon-Im Al Ahsan, Md Najmus Swaqeeb, Anuj Sharma
arXiv:2608. 02958v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) policies trained by behavior cloning fail silently: from the action stream alone, a collapsing rollout looks much like one making clean progress, because imitation supplies no notion of progress.
By Inkyu Sa, Konstantin Stulov, Rajat Bhageria