Abstract-- In this work, we introduce MO-SeGMan, a Multi-Objective Sequential and Guided Manipulation planner for highly constrained rearrangement problems. MO-SeGMan generates object placement sequences that minimize both re-planning per object and robot travel distance while preserving critical dependency structures with a lazy evaluation method. T o address highly cluttered, non-monotone scenarios, we propose a Selective Guided Forward Search (SGFS) that efficiently relocates only critical obstacles and to feasible relocation points. Furthermore, we adopt a refinement method for adaptive subgoal selection to eliminate unnecessary pick-and-place actions, thereby improving overall solution quality. Extensive evaluations on nine benchmark rearrangement tasks demonstrate that MO-SeGMan generates feasible motion plans in all cases, consistently achieving faster solution times and superior solution quality compared to the baselines. These results highlight the robustness and scalability of the proposed framework for complex rearrangement planning problems. Supplementary videos and code are available at: https: //sites.google.com/view/mo-segman/. Rearrangement planning involves generating a feasible motion plan for a robot to move all goal objects to their designated locations.

Abstract--In this paper, we propose a non-myopic sensor management algorithm for multi-target tracking, with multiple sensors operating in the same surveillance area. The algorithm is based on multi-Bernoulli filtering and selects the actions that solve a non-myopic minimisation problem, where the cost function is the mean square generalised optimal sub-pattern assignment (GOSPA) error, over a future time window. For tractability, the sensor management algorithm actually uses an upper bound of the GOSPA error and is implemented via Monte Carlo Tree Search (MCTS). The sensors have the ability to jointly optimise and select their actions with the considerations of all other sensors in the surveillance area. The benefits of the proposed algorithm are analysed via simulations. ENSOR management can be defined as the dynamic re-tasking of agile sensors to achieve an operational objective [1]. Sensors can be agile in a multitude of ways, from physically repositioning, changing direction or selecting a sensing mode. Myopic sensor management, sometimes called greedy sensor management, optimises the sensor resources for the immediate benefit of the system, not considering the long term effects of the actions being selected now. Non-myopic sensor management operates on the policy of considering these long-term effects of the actions selected now. Whilst it has an increased computational demand, non-myopic planning often produces more desirable results [2], [3].

In Symbolic Regression (SR), Genetic Programming (GP) is a popular search algorithm that delivers state-of-the-art results in term of accuracy. Its success relies on the concept of neutrality, which induces large plateaus that the search can safely navigate to more promising regions. Navigating these plateaus, while necessary, requires the computation of redundant expressions, up to 60% of the total number of evaluation, as noted in a recent study. The equality graph (e-graph) structure can compactly store and group equivalent expressions enabling us to verify if a given expression and their variations were already visited by the search, thus enabling us to avoid unnecessary computation. We propose a new search algorithm for symbolic regression called SymRegg that revolves around the e-graph structure following simple steps: perturb solutions sampled from a selection of expressions stored in the e-graph, if it generates an unvisited expression, insert it into the e-graph and generates its equivalent forms. We show that SymRegg is capable of improving the efficiency of the search, maintaining consistently accurate results across different datasets while requiring a choice of a minimalist set of hyperparameters.

We study the $k$-Submodular Cover ($kSC$) problem, a natural generalization of the classical Submodular Cover problem that arises in artificial intelligence and combinatorial optimization tasks such as influence maximization, resource allocation, and sensor placement. Existing algorithms for $\kSC$ often provide weak approximation guarantees or incur prohibitively high query complexity. To overcome these limitations, we propose a \textit{Fast Stochastic Greedy} algorithm that achieves strong bicriteria approximation while substantially lowering query complexity compared to state-of-the-art methods. Our approach dramatically reduces the number of function evaluations, making it highly scalable and practical for large-scale real-world AI applications where efficiency is essential.

Large Reasoning Models (LRMs) demonstrate strong performance on complex reasoning tasks, yet they often suffer from overthinking, producing excessively long chain-of-thought (CoT) traces that increase inference cost and may degrade accuracy. Our analysis reveals a clear anti-correlation between reasoning length and accuracy, where across multiple stochastic decodes, the short reasoning paths consistently achieve the highest correctness, while longer ones accumulate errors and repetitions. These short optimal reasoning paths can be found ideally through full enumeration of the reasoning space. However, the tree-structured reasoning space grows exponentially with sequence length, rendering exhaustive exploration infeasible. To address this, we propose DTS, a model-agnostic decoding framework that sketches the reasoning space by selectively branching at high-entropy tokens and applies early stopping to select the shortest completed reasoning path. This approach approximates the optimal solution that enhances both efficiency and accuracy, without requiring additional training or supervision. Experiments on AIME2024 and AIME2025 datasets with DeepSeek-R1-Distill-Qwen-7B and 1.5B show that DTS improves accuracy by up to 8%, reduces average reasoning length by 23%, and decreases repetition frequency by 12%, demonstrating DTS's ability for scalable and efficient LRM reasoning.

We introduce Pareto-NRPA, a new Monte-Carlo algorithm designed for multi-objective optimization problems over discrete search spaces. Extending the Nested Rollout Policy Adaptation (NRPA) algorithm originally formulated for single-objective problems, Pareto-NRPA generalizes the nested search and policy update mechanism to multi-objective optimization. The algorithm uses a set of policies to concurrently explore different regions of the solution space and maintains non-dominated fronts at each level of search. Policy adaptation is performed with respect to the diversity and isolation of sequences within the Pareto front. We benchmark Pareto-NRPA on two classes of problems: a novel bi-objective variant of the Traveling Salesman Problem with Time Windows problem (MO-TSPTW), and a neural architecture search task on well-known benchmarks. Results demonstrate that Pareto-NRPA achieves competitive performance against state-of-the-art multi-objective algorithms, both in terms of convergence and diversity of solutions. Particularly, Pareto-NRPA strongly outperforms state-of-the-art evolutionary multi-objective algorithms on constrained search spaces. To our knowledge, this work constitutes the first adaptation of NRPA to the multi-objective setting.

Large language models (LLMs) have recently demonstrated the ability to act as function call agents by invoking external tools, enabling them to solve tasks beyond their static knowledge. However, existing agents typically call tools step by step at a time without a global view of task structure. As tools depend on each other, this leads to error accumulation and limited scalability, particularly when scaling to thousands of tools. To address these limitations, we propose NaviAgent, a novel bilevel architecture that decouples task planning from tool execution through graph-based modeling of the tool ecosystem. At the task-planning level, the LLM-based agent decides whether to respond directly, clarify user intent, invoke a toolchain, or execute tool outputs, ensuring broad coverage of interaction scenarios independent of inter-tool complexity. At the execution level, a continuously evolving Tool World Navigation Model (TWNM) encodes structural and behavioral relations among tools, guiding the agent to generate scalable and robust invocation sequences. By incorporating feedback from real tool interactions, NaviAgent supports closed-loop optimization of planning and execution, moving beyond tool calling toward adaptive navigation of large-scale tool ecosystems. Experiments show that NaviAgent achieves the best task success rates across models and tasks, and integrating TWMN further boosts performance by up to 17 points on complex tasks, underscoring its key role in toolchain orchestration.

Foundation models are increasingly becoming better autonomous programmers, raising the prospect that they could also automate dangerous offensive cyber-operations. Current frontier model audits probe the cybersecurity risks of such agents, but most fail to account for the degrees of freedom available to adversaries in the real world. In particular, with strong verifiers and financial incentives, agents for offensive cybersecurity are amenable to iterative improvement by would-be adversaries. We argue that assessments should take into account an expanded threat model in the context of cybersecurity, emphasizing the varying degrees of freedom that an adversary may possess in stateful and non-stateful environments within a fixed compute budget. We show that even with a relatively small compute budget (8 H100 GPU Hours in our study), adversaries can improve an agent's cybersecurity capability on InterCode CTF by more than 40\% relative to the baseline -- without any external assistance. These results highlight the need to evaluate agents' cybersecurity risk in a dynamic manner, painting a more representative picture of risk.

This paper proposes a neural architecture search space using ResNet as a framework, with search objectives including parameters for convolution, pooling, fully connected layers, and connectivity of the residual network. In addition to recognition accuracy, this paper uses the loss value on the validation set as a secondary objective for optimization. The experimental results demonstrate that the search space of this paper together with the optimisation approach can find competitive network architectures on the MNIST, Fashion-MNIST and CIFAR100 datasets.

Database Management Systems (DBMSs) are fundamental for managing large-scale and heterogeneous data, and their performance is critically influenced by configuration parameters. Effective tuning of these parameters is essential for adapting to diverse workloads and maximizing throughput while minimizing latency. Recent research has focused on automated configuration optimization using machine learning; however, existing approaches still exhibit several key limitations. Most tuning frameworks disregard the dependencies among parameters, assuming that each operates independently. This simplification prevents optimizers from leveraging relational effects across parameters, limiting their capacity to capture performancesensitive interactions. Moreover, to reduce the complexity of the high-dimensional search space, prior work often selects only the top few parameters for optimization, overlooking others that contribute meaningfully to performance. Bayesian Optimization (BO), the most common method for automatic tuning, is also constrained by its reliance on surrogate models, which can lead to unstable predictions and inefficient exploration. To overcome these limitations, we propose RelTune, a novel framework that represents parameter dependencies as a Relational Graph and learns GNN-based latent embeddings that encode performancerelevant semantics. RelTune further introduces Hybrid-Score-Guided Bayesian Optimization (HBO), which combines surrogate predictions with an Affinity Score measuring proximity to previously high-performing configurations. Experimental results on multiple DBMSs and workloads demonstrate that RelTune achieves faster convergence and higher optimization efficiency than conventional BO-based methods, achieving state-of-the-art performance across all evaluated scenarios.