Related papers: ContextFlow: Hierarchical Task-State Alignment for…

State abstraction is an effective technique for planning in robotics environments with continuous states and actions, long task horizons, and sparse feedback. In object-oriented environments, predicates are a particularly useful form of…

Agentic workflows in large language model systems integrate retrieval, reasoning, and memory, but existing frameworks suffer from scalability and reproducibility limitations due to fragmented data orchestration, serialization overhead, and…

Multi-agent frameworks powered by large language models (LLMs) have demonstrated great success in automated planning and task execution. However, the effective adjustment of agentic workflows during execution has not been well studied. An…

In the endeavor to make autonomous robots take actions, task planning is a major challenge that requires translating high-level task descriptions to long-horizon action sequences. Despite recent advances in language model agents, they…

LLM agents can reason and use tools, but they often break down on long-horizon tasks due to unbounded context growth and accumulated errors. Common remedies such as context compression or retrieval-augmented prompting introduce trade-offs…

This paper addresses the poor finite-horizon performance of existing online \emph{restless bandit} (RB) algorithms, which stems from the prohibitive sample complexity of learning a full \emph{Markov decision process} (MDP) for each agent.…

Language-model agent systems commonly rely on reactive prompting, in which a single instruction guides the model through an open-ended sequence of reasoning and tool-use steps, leaving control flow and intermediate state implicit and making…

As LLM agents transition from short, static problem solving to executing complex, long-horizon tasks in dynamic environments, the ability to handle user interruptions, such as adding requirement or revising goals, during mid-task execution…

As Large Language Model (LLM) agents become more widespread, associated misalignment risks increase. While prior research has studied agents' ability to produce harmful outputs or follow malicious instructions, it remains unclear how likely…

Goal representation affects the performance of Hierarchical Reinforcement Learning (HRL) algorithms by decomposing the complex learning problem into easier subtasks. Recent studies show that representations that preserve temporally abstract…

Recent vision-language-action (VLA) systems have demonstrated strong capabilities in embodied manipulation. However, most existing VLA policies rely on limited observation windows and end-to-end action prediction, which makes them brittle…

Power grid fault diagnosis is a critical process hindered by its reliance on manual, error-prone methods. Technicians must manually extract reasoning logic from dense regulations and attempt to combine it with tacit expert knowledge, which…

Large language model (LLM) agents are fundamentally bottlenecked by finite context windows on long-horizon tasks. As trajectories grow, retaining tool outputs and intermediate reasoning in-context quickly becomes infeasible: the working…

Large language models (LLMs) have shown promise as interactive agents that solve tasks through extended sequences of environment interactions. While prior work has primarily focused on system-level optimizations or algorithmic improvements,…

Long-Horizon (LH) tasks in Human-Scene Interaction (HSI) are complex multi-step tasks that require continuous planning, sequential decision-making, and extended execution across domains to achieve the final goal. However, existing methods…

Accurate perception of dynamic traffic scenes is crucial for high-level autonomous driving systems, requiring robust object motion estimation and instance segmentation. However, traditional methods often treat them as separate tasks,…

Embodied AI research is increasingly moving beyond single-task, single-environment policy learning toward multi-task, multi-scene, and multi-model settings. This shift substantially increases the engineering overhead and development time…

Heterogeneous scientific workflows consist of numerous types of tasks that require executing on heterogeneous resources. Asynchronous execution of those tasks is crucial to improve resource utilization, task throughput and reduce workflows'…

Recent progress on long-horizon agentic tasks has been driven largely by scaling up individual agents through stronger models, better tools, and more effective scaffolding. In contrast, much less is understood about scaling out: whether…

We contend that embodied learning is fundamentally a lifecycle problem rather than a single-stage optimization. Systems that optimize only one link (data collection, simulation, learning, or deployment) rarely sustain improvement or…