While Vision-Language Models (VLMs) post-trained with Reinforcement Learning (RL) show impressive general reasoning, their evaluation is often confined to language-dominant tasks (e.g., math). This raises a critical question: can RL post-training truly extend the inherent capability boundary of a base VLM, particularly for visual-centric spatial tasks where it initially fails? To investigate this, we introduce Ariadne, a framework utilizing synthetic mazes for multi-step spatial reasoning where task difficulty (e.g., path length, turns) is precisely controlled. We leverage this controllable environment to train VLMs using Reinforcement Learning with Verified Rewards (RLVR) in a difficulty-aware curriculum. Surprisingly, post-RLVR training, the VLM achieves over 50% accuracy on a problem set where the base model scored 0%, demonstrating that our approach expands the model's initial capability boundary. To assess real-world viability, we evaluate out-of-distribution (OOD) generalization on practical benchmarks. Despite training only on synthetic maze samples, Ariadne achieves significant zero-shot improvements, averaging 16% on MapBench (e.g., museum navigation) and 24% on ReasonMap (subway transfer tasks). These results confirm that our method not only broadens the model's fundamental limits but also enhances its generalization to real-world spatial reasoning. We acknowledge our study is limited to the post-training phase, given the opaqueness of pre-training data, and hope our research motivates further work on specialized, capability-extending alignment.

Efficiency is essential to support ever-growing datasets, especially for Deep Learning (DL) systems. DL frameworks have traditionally embraced deferred execution-style DL code -- supporting symbolic, graph-based Deep Neural Network (DNN) computation. While scalable, such development is error-prone, non-intuitive, and difficult to debug. Consequently, more natural, imperative DL frameworks encouraging eager execution have emerged but at the expense of run-time performance. Though hybrid approaches aim for the "best of both worlds," using them effectively requires subtle considerations. Our key insight is that, while DL programs typically execute sequentially, hybridizing imperative DL code resembles parallelizing sequential code in traditional systems. Inspired by this, we present an automated refactoring approach that assists developers in determining which otherwise eagerly-executed imperative DL functions could be effectively and efficiently executed as graphs. The approach features novel static imperative tensor and side-effect analyses for Python. Due to its inherent dynamism, analyzing Python may be unsound; however, the conservative approach leverages a speculative (keyword-based) analysis for resolving difficult cases that informs developers of any assumptions made. The approach is: (i) implemented as a plug-in to the PyDev Eclipse IDE that integrates the WALA Ariadne analysis framework and (ii) evaluated on nineteen DL projects consisting of 132 KLOC. The results show that 326 of 766 candidate functions (42.56%) were refactorable, and an average relative speedup of 2.16x on performance tests was observed with negligible differences in model accuracy. The results indicate that the approach is useful in optimizing imperative DL code to its full potential.

Autonomous robot exploration (ARE) is the process of a robot autonomously navigating and mapping an unknown environment. Recent Reinforcement Learning (RL)-based approaches typically formulate ARE as a sequential decision-making problem defined on a collision-free informative graph. However, these methods often demonstrate limited reasoning ability over graph-structured data. Moreover, due to the insufficient consideration of robot motion, the resulting RL policies are generally optimized to minimize travel distance, while neglecting time efficiency. To overcome these limitations, we propose GRATE, a Deep Reinforcement Learning (DRL)-based approach that leverages a Graph Transformer to effectively capture both local structure patterns and global contextual dependencies of the informative graph, thereby enhancing the model's reasoning capability across the entire environment. In addition, we deploy a Kalman filter to smooth the waypoint outputs, ensuring that the resulting path is kinodynamically feasible for the robot to follow. Experimental results demonstrate that our method exhibits better exploration efficiency (up to 21.5% in distance and 21.3% in time to complete exploration) than state-of-the-art conventional and learning-based baselines in various simulation benchmarks. We also validate our planner in real-world scenarios.

We investigate two fundamental problems in mobile computing: exploration and rendezvous, with two distinct mobile agents in an unknown graph. The agents may communicate by reading and writing information on whiteboards that are located at all nodes. They both move along one adjacent edge at every time-step. In the exploration problem, the agents start from the same arbitrary node and must traverse all the edges. We present an algorithm achieving collective exploration in $m$ time-steps, where $m$ is the number of edges of the graph. This improves over the guarantee of depth-first search, which requires $2m$ time-steps. In the rendezvous problem, the agents start from different nodes of the graph and must meet as fast as possible. We present an algorithm guaranteeing rendezvous in at most $\frac{3}{2}m$ time-steps. This improves over the so-called `wait for Mommy' algorithm which is based on depth-first search and which also requires $2m$ time-steps. Importantly, all our guarantees are derived from a more general asynchronous setting in which the speeds of the agents are controlled by an adversary at all times. Our guarantees generalize to weighted graphs, when replacing the number of edges $m$ with the sum of all edge lengths. We show that our guarantees are met with matching lower-bounds in the asynchronous setting.

In autonomous robot exploration tasks, a mobile robot needs to actively explore and map an unknown environment as fast as possible. Since the environment is being revealed during exploration, the robot needs to frequently re-plan its path online, as new information is acquired by onboard sensors and used to update its partial map. While state-of-the-art exploration planners are frontier- and sampling-based, encouraged by the recent development in deep reinforcement learning (DRL), we propose ARiADNE, an attention-based neural approach to obtain real-time, non-myopic path planning for autonomous exploration. ARiADNE is able to learn dependencies at multiple spatial scales between areas of the agent's partial map, and implicitly predict potential gains associated with exploring those areas. This allows the agent to sequence movement actions that balance the natural trade-off between exploitation/refinement of the map in known areas and exploration of new areas. We experimentally demonstrate that our method outperforms both learning and non-learning state-of-the-art baselines in terms of average trajectory length to complete exploration in hundreds of simplified 2D indoor scenarios. We further validate our approach in high-fidelity Robot Operating System (ROS) simulations, where we consider a real sensor model and a realistic low-level motion controller, toward deployment on real robots.

It was held on Sunday, 28 July 2002. The workshop papers are available as a technical report from AAAI Press. After a welcome and introductions, David Martin of SRI International started the day's presentations with an overview of the The objective of the language is to enable automated software agents to easily accomplish real-world planning tasks by discovering related services, selecting the most appropriate among them, composing them into effective plans, and invoking them to execute these plans and accomplish their tasks. The ServiceModel specification is aimed at supporting service invocation, composition, and monitoring and consists of a workflow model describing how the service is accomplished in terms of atomic and composite processes and their data and control dependencies. Finally, the ServiceGrounding specification specifies the implementation-specific details of service invocation, related to protocols, message formatting, and type serialization.

The operation of a human organization requires dozens of everyday tasks to ensure coherence in organizational activities, monitor the status of such activities, gather information relevant to the organization, keep everyone in the organization informed, and so on. Teams of software agents can aid humans in accomplishing these tasks, facilitating the organization's coherent functioning and rapid response to crises and reducing the burden on humans. These activities are often well suited for software agents, which can devote significant resources to perform these tasks, thus reducing the burden on humans. Indeed, teams of such software agents, including proxy agents that act on behalf of humans, would enable organizations to act coherently, attain their mission goals robustly, react to crises swiftly, and adapt to events dynamically. Such agent teams could assist all organizations, including the military, civilian disaster response, corporations, and universities and research institutions.

This chapter will discuss one example of how AI techniques are being integrated with, and extending, existing molecular biology sequence analysis methods. AI ideas of complex representations, pattern recognition, search, and machine learning have been applied to the task of inferring and recognizing structural patterns associated with molecular function. We wish to construct such patterns, and to recognize them in unknown molecules, based on information inferred solely from protein primary (amino acid) sequences.

We present a new approach to path planning, called the "Ariadne's clew algorithm". It is designed to find paths in high-dimensional continuous spaces and applies to robots with many degrees of freedom in static, as well as dynamic environments - ones where obstacles may move. The Ariadne's clew algorithm comprises two sub-algorithms, called Search and Explore, applied in an interleaved manner. Explore builds a representation of the accessible space while Search looks for the target. Both are posed as optimization problems. We describe a real implementation of the algorithm to plan paths for a six degrees of freedom arm in a dynamic environment where another six degrees of freedom arm is used as a moving obstacle. Experimental results show that a path is found in about one second without any pre-processing.

This paper advocates the use of a portfolio of representations for problem solving in complex domains. It describes an approach that decouples efficient storage mechanisms called descriptives from the decision-making procedures that employ them. An architecture that takes this approach can learn which representations are appropriate for a given problem class. Examples of search with a portfolio of representations are drawn from a broad set of domains.