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…

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…

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…

提出滚动想象机制解决世界动作模型联合视频-动作生成的长期一致性问题，提升机器人操作中的未来预测与动作规划能力。

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，缓解离散决策与连续运动紧耦合难题，为TAMP提供新的通用求解范式。

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…

利用已有策略预测强化学习结果，降低后训练评估成本，为基座模型RL后训练的效果预判提供高效工具。

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

通过去重3D场景表示突破点跟踪的稀疏长时与稠密短时权衡，实现长时程稠密跟踪，对视频理解与机器人感知有重要价值。

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 …