10 accepted papers
Planning collaboration strategies for multi-agent embodied systems remains a core challenge for LLM-based planners, which often fail to capture the physical and coordination constraints of realworld environments. To address this, we present EvoCF, an agentic memory-driven evolutionary counterfactual…
Web search is a cornerstone for deep research agents, enabling them to acquire and reason over knowledge beyond static corpora. Yet most existing systems follow rigid ReAct-style tool chains locked into fixed workflow structures, which hinders their ability to flexibly handle diverse query types and…
Generalizing policies across environments with altered dynamics remains a key challenge in reinforcement learning, particularly in offline settings where direct interaction or fine-tuning is impractical. We introduce Masked Skill Token Training (MSTT), a fully offline hierarchical RL framework that…
Safe and successful deployment of robots requires not only the ability to generate complex plans but also the capacity to frequently replan and correct execution errors. This paper addresses the challenge of long-horizon trajectory planning under temporally extended objectives in a receding horizon
Long-horizon planning in robotic manipulation tasks requires translating underspecified, symbolic goals into executable control programs satisfying spatial, temporal, and physical constraints. However, language model-based planners often struggle with long-horizon task decomposition, robust constrai…
Operating effectively in complex environments while complying with specified constraints is crucial for the safe and successful deployment of robots that interact with and operate around people. In this letter, we focus on generating long-horizon trajectories that adhere to static and temporally-ext
The vast applications of deep generative models are anchored in three core capabilities---*generating* new instances, *reconstructing* inputs, and learning compact *representations*---across various data types, such as discrete text/protein sequences and continuous images. Existing model families, l…
In this work, we focus on the problem of safe policy transfer in reinforcement learning: we seek to leverage existing policies when learning a new task with specified constraints. This problem is important for safety-critical applications where interactions are costly and unconstrained exploration c…
We present an information-theoretically motivated constraint for self-supervised representation learning from multiple related domains. In contrast to previous self-supervised learning methods, our approach learns from multiple domains, which has the benefit of decreasing the build-in bias of indivi…
We introduce a self-supervised learning method that focuses on beneficial properties of representation and their abilities in generalizing to real-world tasks. The method incorporates rotation invariance into the feature learning framework, one of many good and well-studied properties of visual repr…