arXiv 论文速递

揭示LLM智能体可轻易篡改自身执行轨迹，动摇异步监控、事故调查与合规审计的信任根基，对智能体安全治理具有警示意义。

Asynchronous monitoring, incident investigations, and compliance audits primarily rely on agent traces to reconstruct what happened. These analyses assume that LLM agents cannot ta…

针对世界模型只拟合事实转移、难以区分反事实动作的问题，提出动作判别式世界模型，提升MPC在候选动作比较中的决策可靠性。

Latent world models are typically trained to predict factual transitions, whereas model predictive control (MPC) must compare alternative actions from the same state. A model can t…

指出具身强化学习中仅传梯度仍会泄露轨迹隐私，提出时序梯度反演攻击，对分布式学习的隐私保护假设构成重要挑战。

Distributed learning in embodied reinforcement-learning agents offers a degree of privacy by retaining raw sensor data on-device and transmitting only policy gradients to the serve…

Conspiratorial discourse on social media is not always expressed through explicit claims or stable lexical markers. The same surface content may express endorsement, legitimate con…

Coding agents have demonstrated enormous success in solving complex programming problems. To leverage their potential for robot systems, this work introduces Robot Agentic Programm…

解决世界动作模型联合生成视频与动作时难以完成长时程任务的难题，以滚动想象机制提升机器人操作的长程规划与执行能力。

World Action Models (WAMs) couple action generation with future visual prediction for robotic manipulation. However, completing the joint video-action denoising process at each rep…

将编码智能体引入任务与运动规划，用代码生成统一离散决策与连续运动约束，为TAMP提供可泛化的新范式。

Task and motion planning (TAMP) problems remain difficult even with full observability and object-centric states because discrete decisions are tightly coupled to geometric, kinema…

Online misinformation increasingly appears in spoken formats such as news clips, podcasts, interviews, political speeches, and social media videos, creating a need for fact-checkin…

Foundation models are post-trained with reinforcement learning (RL) to maximize specific rewards, such as human alignment, correctness, or instruction following. This post-training…

Existing point tracking models face a fundamental tradeoff: they can either track a sparse set of query points over long horizons, or track all points across only short clips. We i…

An acceptance protocol is developed for sensor-coordinate and polarity binding in mechatronic commissioning. Candidate generation is separated from release authority. Requirements …

Pre-logit steering adapts a frozen language model to a test-time reward by adding vectors to its final hidden states. Unregularized reward optimization can substantially alter the …