This study presents an Exploratory Retrieval-Augmented Planning (ExRAP) framework, designed to tackle continual instruction following tasks of embodied agents in dynamic, non-stationary environments. The framework enhances Large Language Models' (LLMs) embodied reasoning capabilities by efficiently exploring the physical environment and establishing the environmental context memory, thereby effectively grounding the task planning process in time-varying environment contexts. In ExRAP, given multiple continual instruction following tasks, each instruction is decomposed into queries on the environmental context memory and task executions conditioned on the query results. To efficiently handle these multiple tasks that are performed continuously and simultaneously, we implement an exploration-integrated task planning scheme by incorporating the information-based exploration into the LLM-based planning process. Combined with memory-augmented query evaluation, this integrated scheme not only allows for a better balance between the validity of the environmental context memory and the load of environment exploration, but also improves overall task performance. Furthermore, we devise a temporal consistency refinement scheme for query evaluation to address the inherent decay of knowledge in the memory. Through experiments with VirtualHome, ALFRED, and CARLA, our approach demonstrates robustness against a variety of embodied instruction following scenarios involving different instruction scales and types, and non-stationarity degrees, and it consistently outperforms other state-of-the-art LLM-based task planning approaches in terms of both goal success rate and execution efficiency.

Current radiation therapy treatment planning is limited by suboptimal plan quality, inefficiency, and high costs. This perspective paper explores the complexity of treatment planning and introduces Human-Centric Intelligent Treatment Planning (HCITP), an AI-driven framework under human oversight, which integrates clinical guidelines, automates plan generation, and enables direct interactions with operators. We expect that HCITP will enhance efficiency, potentially reducing planning time to minutes, and will deliver personalized, high-quality plans. Challenges and potential solutions are discussed.

Generative AI, large language models, and agentic AI have emerged separately of urban planning. However, the convergence between AI and urban planning presents an interesting opportunity towards AI urban planners. Existing studies conceptualizes urban planning as a generative AI task, where AI synthesizes land-use configurations under geospatial, social, and human-centric constraints and reshape automated urban design. We further identify critical gaps of existing generative urban planning studies: 1) the generative structure has to be predefined with strong assumption: all of adversarial generator-discriminator, forward and inverse diffusion structures, hierarchical zone-POI generative structure are predefined by humans; 2) ignore the power of domain expert developed tools: domain urban planners have developed various tools in the urban planning process guided by urban theory, while existing pure neural networks based generation ignore the power of the tools developed by urban planner practitioners. To address these limitations, we outline a future research direction agentic urban AI planner, calling for a new synthesis of agentic AI and participatory urbanism.

Autonomous error correction is critical for domestic robots to achieve reliable execution of complex long-horizon tasks. Prior work has explored self-reflection in Large Language Models (LLMs) for task planning error correction; however, existing methods are constrained by inflexible self-reflection mechanisms that limit their effectiveness. Motivated by these limitations and inspired by human cognitive adaptation, we propose the Flexible Constructivism Reflection Framework (FCRF), a novel Mentor-Actor architecture that enables LLMs to perform flexible self-reflection based on task difficulty, while constructively integrating historical valuable experience with failure lessons. We evaluated FCRF on diverse domestic tasks through simulation in AlfWorld and physical deployment in the real-world environment. Experimental results demonstrate that FCRF significantly improves overall performance and self-reflection flexibility in complex long-horizon robotic tasks.

This study presents an Exploratory Retrieval-Augmented Planning (ExRAP) framework, designed to tackle continual instruction following tasks of embodied agents in dynamic, non-stationary environments. The framework enhances Large Language Models' (LLMs) embodied reasoning capabilities by efficiently exploring the physical environment and establishing the environmental context memory, thereby effectively grounding the task planning process in time-varying environment contexts. In ExRAP, given multiple continual instruction following tasks, each instruction is decomposed into queries on the environmental context memory and task executions conditioned on the query results. To efficiently handle these multiple tasks that are performed continuously and simultaneously, we implement an exploration-integrated task planning scheme by incorporating the information-based exploration into the LLM-based planning process. Combined with memory-augmented query evaluation, this integrated scheme not only allows for a better balance between the validity of the environmental context memory and the load of environment exploration, but also improves overall task performance.

Long-term planning, as in reinforcement learning (RL), involves finding strategies: actions that collectively work toward a goal rather than individually optimizing their immediate outcomes. As part of a strategy, some actions are taken at the expense of short-term benefit to enable future actions with even greater returns. These actions are only advantageous if followed up by the actions they facilitate, consequently, they would not have been taken if those follow-ups were not available. In this paper, we quantify such dependencies between planned actions with strategic link scores: the drop in the likelihood of one decision under the constraint that a follow-up decision is no longer available. We demonstrate the utility of strategic link scores through three practical applications: (i) explaining black-box RL agents by identifying strategically linked pairs among decisions they make, (ii) improving the worst-case performance of decision support systems by distinguishing whether recommended actions can be adopted as standalone improvements or whether they are strategically linked hence requiring a commitment to a broader strategy to be effective, and (iii) characterizing the planning processes of non-RL agents purely through interventions aimed at measuring strategic link scores - as an example, we consider a realistic traffic simulator and analyze through road closures the effective planning horizon of the emergent routing behavior of many drivers.

A flight trajectory defines how exactly a quadrocopter moves in the three-dimensional space from one position to another. Automatic flight trajectory planning faces challenges such as high computational effort and a lack of precision. Hence, when low computational effort or precise control is required, programming the flight route trajectory manually might be preferable. However, this requires in-depth knowledge of how to accurately plan flight trajectories in three-dimensional space. We propose planning quadrocopter flight trajectories manually using the Programming by Demonstration (PbD) approach -- simply drawing the trajectory in the three-dimensional space by hand. This simplifies the planning process and reduces the level of in-depth knowledge required. We implemented the approach in the context of the Quadcopter Lab at Ulm University. In order to evaluate our approach, we compare the precision and accuracy of the trajectories drawn by a user using our approach as well as the required time with those manually programmed using a domain specific language. The evaluation shows that the Drawjectory workflow is, on average, 78.7 seconds faster without a significant loss of precision, shown by an average deviation 6.67 cm.

Mobility systems worldwide confront escalating challenges--aging infrastructure, increasing environmental impacts from transportation emissions, and widening service provision gaps that exacerbate social inequalities. Addressing these challenges demands smart and adaptive planning strategies to effectively leverage both mature and emerging technologies--including autonomous driving, vehicle electrification, low-latency communication, and Mobility-as-a-Service (MaaS) platforms. Shared Automated Electric Mobility Systems (SAEMS), exemplified by demand-responsive autonomous transit and passenger car services, autonomous electric micro-mobility systems, and unmanned aerial vehicle (UAV) delivery services, present a conceptual framework for integrating and leveraging these existing and promising technologies and addressing the escalating challenges. However, the full advantages and potential side effects of SAEMS often remain uncertain due to environmental, technological, and socioeconomic factors. This ambiguity underscores the importance of integrating a broad spectrum of domain knowledge and perspectives--ranging from land use zoning to charging infrastructure engineering, and from local business operations to residents' daily experiences-- into coherent planning processes.

Motion planning in complex scenarios is the core challenge in autonomous driving. Conventional methods apply predefined rules or learn from driving data to plan the future trajectory. Recent methods seek the knowledge preserved in large language models (LLMs) and apply them in the driving scenarios. Despite the promising results, it is still unclear whether the LLM learns the underlying human logic to drive. In this paper, we propose an InstructDriver method to transform LLM into a motion planner with explicit instruction tuning to align its behavior with humans. We derive driving instruction data based on human logic (e.g., do not cause collisions) and traffic rules (e.g., proceed only when green lights). We then employ an interpretable InstructChain module to further reason the final planning reflecting the instructions. Our InstructDriver allows the injection of human rules and learning from driving data, enabling both interpretability and data scalability. Different from existing methods that experimented on closed-loop or simulated settings, we adopt the real-world closed-loop motion planning nuPlan benchmark for better evaluation. InstructDriver demonstrates the effectiveness of the LLM planner in a real-world closed-loop setting. Our code is publicly available at https://github.com/bonbon-rj/InstructDriver.

As Large Language Models (LLMs) have shown significant intelligence, the progress to leverage LLMs as planning modules of autonomous agents has attracted more attention. This survey provides the first systematic view of LLM-based agents planning, covering recent works aiming to improve planning ability. We provide a taxonomy of existing works on LLM-Agent planning, which can be categorized into Task Decomposition, Plan Selection, External Module, Reflection and Memory. Comprehensive analyses are conducted for each direction, and further challenges for the field of research are discussed.