The rapid advancement of GPU technology has unlocked powerful parallel processing capabilities, creating new opportunities to enhance classic search algorithms. This hardware has been exploited in best-first search algorithms with neural network-based heuristics by creating batched versions of A* and Weighted A* that delay heuristic evaluation until sufficiently many states can be evaluated in parallel on the GPU. But, research has not addressed how depth-first algorithms like IDA* or Budgeted Tree Search (BTS) can have their heuristic computations batched. This is more complicated in a tree search, because progress in the search tree is blocked until heuristic evaluations are complete. In this paper we show that GPU parallelization of heuristics can be effectively performed when the tree search is parallelized on the CPU while heuristic evaluations are parallelized on the GPU. We develop a parallelized cost-bounded depth-first search (CB-DFS) framework that can be applied to both IDA* and BTS, significantly improving their performance. We demonstrate the strength of the approach on the 3x3 Rubik's Cube and the 4x4 sliding tile puzzle (STP) with both classifier-based and regression-based heuristics.

Branch-and-Bound (B\&B) is the dominant exact solution method for Mixed Integer Linear Programs (MILP), yet its exponential time complexity poses significant challenges for large-scale instances. The growing capabilities of machine learning have spurred efforts to improve B\&B by learning data-driven branching policies. However, most existing approaches rely on Imitation Learning (IL), which tends to overfit to expert demonstrations and struggles to generalize to structurally diverse or unseen instances. In this work, we propose Tree-Gate Proximal Policy Optimization (TGPPO), a novel framework that employs Proximal Policy Optimization (PPO), a Reinforcement Learning (RL) algorithm, to train a branching policy aimed at improving generalization across heterogeneous MILP instances. Our approach builds on a parameterized state space representation that dynamically captures the evolving context of the search tree. Empirical evaluations show that TGPPO often outperforms existing learning-based policies in terms of reducing the number of nodes explored and improving p-Primal-Dual Integrals (PDI), particularly in out-of-distribution instances. These results highlight the potential of RL to develop robust and adaptable branching strategies for MILP solvers.

We study an efficient implementation of Multi-Armed Bandit (MAB)-based Monte-Carlo Tree Search (MCTS) for classical planning. One weakness of MCTS is that it spends a significant time deciding which node to expand next. While selecting a node from an OPEN list with $N$ nodes has $O(1)$ runtime complexity with traditional array-based priority-queues for dense integer keys, the tree-based OPEN list used by MCTS requires $O(\log N)$, which roughly corresponds to the search depth $d$. In classical planning, $d$ is arbitrarily large (e.g., $2^k-1$ in $k$-disk Tower-of-Hanoi) and the runtime for node selection is significant, unlike in game tree search, where the cost is negligible compared to the node evaluation (rollouts) because $d$ is inherently limited by the game (e.g., $d\leq 361$ in Go). To improve this bottleneck, we propose a bilevel modification to MCTS that runs a best-first search from each selected leaf node with an expansion budget proportional to $d$, which achieves amortized $O(1)$ runtime for node selection, equivalent to the traditional queue-based OPEN list. In addition, we introduce Tree Collapsing, an enhancement that reduces action selection steps and further improves the performance.

Open-domain question answering over datalakes requires retrieving and composing information from multiple tables, a challenging subtask that demands semantic relevance and structural coherence (e.g., joinability). While exact optimization methods like Mixed-Integer Programming (MIP) can ensure coherence, their computational complexity is often prohibitive. Conversely, simpler greedy heuristics that optimize for query coverage alone often fail to find these coherent, joinable sets. This paper frames multi-table retrieval as an iterative search process, arguing this approach offers advantages in scalability, interpretability, and flexibility. We propose a general framework and a concrete instantiation: a fast, effective Greedy Join-Aware Retrieval algorithm that holistically balances relevance, coverage, and joinability. Experiments across 5 NL2SQL benchmarks demonstrate that our iterative method achieves competitive retrieval performance compared to the MIP-based approach while being 4-400x faster depending on the benchmark and search space settings. This work highlights the potential of iterative heuristics for practical, scalable, and composition-aware retrieval.

Paths generated by A* and other graph-search-based planners are widely used in the robotic field. Due to the restricted node-expansion directions, the resulting paths are usually not the shortest. Besides, unnecessary heading changes, or zig-zag patterns, exist even when no obstacle is nearby, which is inconsistent with the human intuition that the path segments should be straight in wide-open space due to the absence of obstacles. This article puts forward a general and systematic post-processing algorithm for A* and other graph-search-based planners. The A* post-processing algorithm, called APP, is developed based on the costmap, which is widely used in commercial service robots. First, a bidirectional vertices reduction algorithm is proposed to tackle the asymm- etry of the path and the environments. During the forward and backward vertices reduction, a thorough shortcut strategy is put forward to improve the path-shortening performance and avoid unnecessary heading changes. Second, an iterative path perturbation algorithm is adopted to locally reduce the number of unnecessary heading changes and improve the path smooth- ness. Comparative experiments are then carried out to validate the superiority of the proposed method. Quantitative performance indexes show that APP outperforms the existing methods in planning time, path length as well as the number of unnecessary heading changes. Finally, field navigation experiments are carried out to verify the practicability of APP.

Text-attributed graphs (TAGs), which combine structural and textual node information, are ubiquitous across many domains. Recent work integrates Large Language Models (LLMs) with Graph Neural Networks (GNNs) to jointly model semantics and structure, resulting in more general and expressive models that achieve state-of-the-art performance on TAG benchmarks. However, this integration introduces dual vulnerabilities: GNNs are sensitive to structural perturbations, while LLM-derived features are vulnerable to prompt injection and adversarial phrasing. While existing adversarial attacks largely perturb structure or text independently, we find that uni-modal attacks cause only modest degradation in LLM-enhanced GNNs. Moreover, many existing attacks assume unrealistic capabilities, such as white-box access or direct modification of graph data. To address these gaps, we propose GRAPHTEXTACK, the first black-box, multi-modal{, poisoning} node injection attack for LLM-enhanced GNNs. GRAPHTEXTACK injects nodes with carefully crafted structure and semantics to degrade model performance, operating under a realistic threat model without relying on model internals or surrogate models. To navigate the combinatorial, non-differentiable search space of connectivity and feature assignments, GRAPHTEXTACK introduces a novel evolutionary optimization framework with a multi-objective fitness function that balances local prediction disruption and global graph influence. Extensive experiments on five datasets and two state-of-the-art LLM-enhanced GNN models show that GRAPHTEXTACK significantly outperforms 12 strong baselines.

What is reasoning? This question has driven centuries of philosophical inquiry, from Aristotle's syllogisms to modern computational complexity theory. In the age of large language models achieving superhuman performance on benchmarks like GSM8K (95\% accuracy) and HumanEval (90\% pass@1), we must ask: have these systems learned to \emph{reason}, or have they learned to \emph{pattern-match over reasoning traces}? This paper argues for a specific answer: \textbf{reasoning is iterative operator application in state spaces, converging to fixed points}. This definition is not merely philosophical -- it has concrete architectural implications that explain both the failures of current systems and the path to genuine reasoning capabilities. Our investigation begins with a puzzle (OpenXOR), progresses through theory (OpenOperator), and culminates in a working solution (OpenLM) that achieves 76\% accuracy where state-of-the-art LLMs achieve 0\%. This is not about criticizing existing systems, but about \emph{understanding what reasoning requires} and \emph{building architectures that provide it}.

Large Language Models (LLMs) often struggle with generating truly innovative ideas, typically defaulting to high-probability, familiar concepts within their training data's "gravity wells." While advanced search-based methods like Tree of Thoughts (ToT) attempt to mitigate this, they are fundamentally limited by their reliance on unprincipled, inconsistent self-evaluation heuristics to guide exploration. To address this gap, we introduce \textbf{Magellan}, a novel framework that reframes creative generation as a principled, guided exploration of an LLM's latent conceptual space. At its core, Magellan employs Monte Carlo Tree Search (MCTS) governed by a hierarchical guidance system. For long-range direction, a "semantic compass" vector, formulated via orthogonal projection, steers the search towards relevant novelty. For local, step-by-step decisions, a landscape-aware value function replaces flawed self-evaluation with an explicit reward structure that balances intrinsic coherence, extrinsic novelty, and narrative progress. Extensive experiments demonstrate that Magellan significantly outperforms strong baselines, including ReAct and ToT, in generating scientific ideas with superior plausibility and innovation. Our work shows that for creative discovery, a principled, guided search is more effective than unconstrained agency, paving the way for LLMs to become more capable partners in innovation.

The implicit hitting set (IHS) approach offers a general framework for solving computationally hard combinatorial optimization problems declaratively. IHS iterates between a decision oracle used for extracting sources of inconsistency and an optimizer for computing so-called hitting sets (HSs) over the accumulated sources of inconsistency. While the decision oracle is language-specific, the optimizers is usually instantiated through integer programming. We explore alternative algorithmic techniques for hitting set optimization based on different ways of employing pseudo-Boolean (PB) reasoning as well as stochastic local search. We extensively evaluate the practical feasibility of the alternatives in particular in the context of pseudo-Boolean (0-1 IP) optimization as one of the most recent instantiations of IHS. Highlighting a trade-off between efficiency and reliability, while a commercial IP solver turns out to remain the most effective way to instantiate HS computations, it can cause correctness issues due to numerical instability; in fact, we show that exact HS computations instantiated via PB reasoning can be made competitive with a numerically exact IP solver. Furthermore, the use of PB reasoning as a basis for HS computations allows for obtaining certificates for the correctness of IHS computations, generally applicable to any IHS instantiation in which reasoning in the declarative language at hand can be captured in the PB-based proof format we employ.

Real-world multimodal misinformation often arises from mixed forgery sources, requiring dynamic reasoning and adaptive verification. However, existing methods mainly rely on static pipelines and limited tool usage, limiting their ability to handle such complexity and diversity. To address this challenge, we propose \method, a novel misinformation detection agent that incorporates an extensible toolkit with Monte Carlo Tree Search (MCTS). The toolkit consists of modular tools such as web search, forgery detection, and consistency analysis. Each tool is described using standardized templates, enabling seamless integration and future expansion. To avoid inefficiency from using all tools simultaneously, a greedy search-based selector is proposed to identify a task-relevant subset. This subset then serves as the action space for MCTS to dynamically collect evidence and perform multi-source verification. To better align MCTS with the multi-source nature of misinformation detection, \method~ extends traditional MCTS with multi-source verification, which decomposes the task into coordinated subtasks targeting different forgery sources. A dual reward mechanism containing a reasoning trajectory score and a confidence score is further proposed to encourage a balance between exploration across mixed forgery sources and exploitation for more reliable evidence. We conduct ablation studies to confirm the effectiveness of the tree search mechanism and tool usage. Extensive experiments further show that \method~ consistently outperforms existing baselines on challenging mixed-source multimodal misinformation benchmarks, demonstrating its strong potential as a training-free detector.