Siyang Gao

Yingxu Wang, Xinwang Liu, Siyang Gao et al.

Source-free graph domain adaptation (SF-GDA) aims to adapt source-trained graph models to unlabeled target graphs when source graphs are no longer accessible. A central obstacle is pseudo-label reliability: under feature and topological shifts, source-induced predictions may become confidently wrong, and indiscriminate self-training can amplify systematic errors through graph message passing. This paper studies SF-GDA from a selective pseudo-labeling perspective. Instead of assuming globally bounded pseudo-label noise over the entire target domain, we identify a confidence-consistent safe subspace on which pseudo-label noise can be controlled under restricted posterior discrepancy, and derive a target-risk decomposition that separates safe-subspace fitting error, selected-label noise, and uncertain-set risk. Guided by this analysis, we propose SafeSubspace Pseudo-Label Refinement (S$^2$PLR), a source-free graph adaptation framework that applies hard pseudo-label supervision only to target graphs supported by both semantic and structural evidence. Specifically, S$^2$PLR estimates semantic reliability using source-committee confidence and disagreement, learns a targetintrinsic structural representation via graph contrastive learning, verifies pseudo-labels through neighborhood consistency, and exploits the remaining uncertain samples with noise-tolerant soft regularization rather than unreliable hard labels. Experiments on image and real-world graph benchmarks under different domain shifts demonstrate that S$^2$PLR achieves robust and competitive performance across diverse source-free transfer settings.

Yingxu Wang, Xinwang Liu, Mengzhu Wang et al.

Graph Domain Adaptation (GDA) aims to transfer graph classifiers across domains with both semantic and topological shifts. Existing Euclidean adversarial methods face two challenges: Structural Degeneration, where domain confusion entangles and suppresses label-relevant topology, and Optimization Instability, where minimax training induces oscillatory gradients under large structural shifts. We propose DisRFM, a geometry-aware GDA framework that addresses these challenges with Riemannian representation learning and flow-based transport. DisRFM embeds graph representations on a constant-curvature manifold and expresses them in geodesic polar coordinates. Polar endpoint regularization calibrates topologysensitive radial scales via univariate Wasserstein alignment and preserves scalenormalized class semantics through confidence-filtered angular alignment, with radial magnitude modulating pseudo-label reliability. DisRFM introduces topologyconditioned polar flow matching, which couples class-compatible source and target samples by a normalized polar transport cost and learns a metric-corrected vector field along geodesic interpolants. Theoretical analysis characterizes the structural risk of unconditional domain confusion and relates polar discrepancies and flow error to target risk. Extensive experiments under diverse domain shifts demonstrate that DisRFM consistently outperforms state-of-the-art methods.

Shiqi Chen, Yiran Zhao, Jinghan Zhang et al.

Assessing factuality of text generated by large language models (LLMs) is an emerging yet crucial research area, aimed at alerting users to potential errors and guiding the development of more reliable LLMs. Nonetheless, the evaluators assessing factuality necessitate suitable evaluation themselves to gauge progress and foster advancements. This direction remains under-explored, resulting in substantial impediments to the progress of factuality evaluators. To mitigate this issue, we introduce a benchmark for Factuality Evaluation of large Language Models, referred to as felm. In this benchmark, we collect responses generated from LLMs and annotate factuality labels in a fine-grained manner. Contrary to previous studies that primarily concentrate on the factuality of world knowledge (e.g.~information from Wikipedia), felm focuses on factuality across diverse domains, spanning from world knowledge to math and reasoning. Our annotation is based on text segments, which can help pinpoint specific factual errors. The factuality annotations are further supplemented by predefined error types and reference links that either support or contradict the statement. In our experiments, we investigate the performance of several LLM-based factuality evaluators on felm, including both vanilla LLMs and those augmented with retrieval mechanisms and chain-of-thought processes. Our findings reveal that while retrieval aids factuality evaluation, current LLMs are far from satisfactory to faithfully detect factual errors.

Zhongjian Qiao, Jiafei Lyu, Chenjia Bai et al.

Cross-domain offline reinforcement learning (RL) aims to learn a policy in the target domain with a limited target domain dataset and a source domain dataset that exhibits a dynamics shift. Training directly on the original source dataset typically leads to performance collapse. Recent studies perform data filtering from the perspective of dynamics alignment or value alignment to enable efficient policy transfer. However, these studies are typically validated on single-domain or single-behavior-policy source datasets. In this work, we explore a more general heterogeneous cross-domain offline RL setting, where the source datasets may be collected from multiple source domains by diverse behavior policies. We first uncover a critical yet overlooked issue in this setting: value misassignment. Empirically and theoretically, we demonstrate that value misassignment can undermine value alignment, mislead data filtering toward selecting suboptimal samples, and loosen the suboptimality gap, thereby degrading the agent's performance. To address this issue, we propose V2A, which integrates dynamics alignment, value alignment, and value assignment. V2A first employs temporally-consistent modality representation learning to extract dynamics modalities from the source dataset, followed by modality-aware advantage learning to rectify value alignment. Finally, it adopts a data filtering paradigm to selectively share source data for policy learning. Empirical results show that V2A significantly outperforms strong baseline methods under general heterogeneous cross-domain offline RL settings.

Yanwen Li, Siyang Gao

Ordinal optimization (OO) is a widely-studied technique for optimizing discrete-event dynamic systems (DEDS). It evaluates the performance of the system designs in a finite set by sampling and aims to correctly make ordinal comparison of the designs. A well-known method in OO is the optimal computing budget allocation (OCBA). It builds the optimality conditions for the number of samples allocated to each design, and the sample allocation that satisfies the optimality conditions is shown to asymptotically maximize the probability of correct selection for the best design. In this paper, we investigate two popular OCBA algorithms. With known variances for samples of each design, we characterize their convergence rates with respect to different performance measures. We first demonstrate that the two OCBA algorithms achieve the optimal convergence rate under measures of probability of correct selection and expected opportunity cost. It fills the void of convergence analysis for OCBA algorithms. Next, we extend our analysis to the measure of cumulative regret, a main measure studied in the field of machine learning. We show that with minor modification, the two OCBA algorithms can reach the optimal convergence rate under cumulative regret. It indicates the potential of broader use of algorithms designed based on the OCBA optimality conditions.

Ruicheng Ao, Hongyu Chen, Siyang Gao et al.

Designing service systems requires selecting among alternative configurations -- choosing the best chatbot variant, the optimal routing policy, or the most effective quality control procedure. In many service systems, the primary evidence of performance quality is textual -- customer support transcripts, complaint narratives, compliance review reports -- rather than the scalar measurements assumed by classical optimization methods. Large language models (LLMs) can read such textual evidence and produce standardized quality scores, but these automated judges exhibit systematic biases that vary across alternatives and evaluation instances. Human expert review remains accurate but costly. We study how to identify the best service configuration with high confidence while minimizing expensive human audits, given that automated evaluation is cheap but biased. We formalize this as a sequential decision problem where a biased proxy score is observed for every evaluation, and a verified outcome can be acquired selectively at additional cost. We prove that LLM-only selection fails under arm-dependent bias, and that naive selective-audit estimators can be asymptotically biased. We develop an estimator combining proxy scores with inverse-propensity-weighted residuals and construct anytime-valid confidence sequences. Our algorithm, PP-LUCB, jointly decides which alternatives to evaluate and whether to request human audits, concentrating reviews where the LLM judge is least reliable. We prove correctness and establish instance-dependent cost bounds showing near-optimal efficiency. On a customer support ticket classification task, our algorithm correctly identifies the best model in 40/40 trials while achieving 90\% audit cost reduction.

Yanwen Li, Siyang Gao

The knowledge gradient (KG) algorithm is a popular and effective algorithm for the best arm identification (BAI) problem. Due to the complex calculation of KG, theoretical analysis of this algorithm is difficult, and existing results are mostly about the asymptotic performance of it, e.g., consistency, asymptotic sample allocation, etc. In this research, we present new theoretical results about the finite-time performance of the KG algorithm. Under independent and normally distributed rewards, we derive bounds for the sample allocation of the algorithm. With these bounds, existing asymptotic results become simple corollaries. Furthermore, we derive upper and lower bounds for the probability of error and simple regret of the algorithm, and show the performance of the algorithm for the multi-armed bandit (MAB) problem. These developments not only extend the existing analysis of the KG algorithm, but can also be used to analyze other improvement-based algorithms. Last, we use numerical experiments to compare the bounds we derive and the performance of the KG algorithm.

Shiqi Chen, Tongyao Zhu, Ruochen Zhou et al. · deepmind, salesforce

Large Vision Language Models (VLMs) have long struggled with spatial reasoning tasks. Surprisingly, even simple spatial reasoning tasks, such as recognizing "under" or "behind" relationships between only two objects, pose significant challenges for current VLMs. In this work, we study the spatial reasoning challenge from the lens of mechanistic interpretability, diving into the model's internal states to examine the interactions between image and text tokens. By tracing attention distribution over the image through out intermediate layers, we observe that successful spatial reasoning correlates strongly with the model's ability to align its attention distribution with actual object locations, particularly differing between familiar and unfamiliar spatial relationships. Motivated by these findings, we propose ADAPTVIS based on inference-time confidence scores to sharpen the attention on highly relevant regions when confident, while smoothing and broadening the attention window to consider a wider context when confidence is lower. This training-free decoding method shows significant improvement (e.g., up to a 50 absolute point improvement) on spatial reasoning benchmarks such as WhatsUp and VSR with negligible cost. We make code and data publicly available for research purposes at https://github.com/shiqichen17/AdaptVis.

Yanwen Li, Siyang Gao, Zhongshun Shi

Ranking and selection (R&S) is a popular model for studying discrete-event dynamic systems. It aims to select the best design (the design with the largest mean performance) from a finite set, where the mean of each design is unknown and has to be learned by samples. Great research efforts have been devoted to this problem in the literature for developing procedures with superior empirical performance and showing their optimality. In these efforts, myopic procedures were popular. They select the best design using a 'naive' mechanism of iteratively and myopically improving an approximation of the objective measure. Although they are based on simple heuristics and lack theoretical support, they turned out highly effective, and often achieved competitive empirical performance compared to procedures that were proposed later and shown to be asymptotically optimal. In this paper, we theoretically analyze these myopic procedures and prove that they also satisfy the optimality conditions of R&S, just like some other popular R&S methods. It explains the good performance of myopic procedures in various numerical tests, and provides good insight into the structure and theoretical development of efficient R&S procedures.

Yunhe Li, Hao Shi, Bowen Deng et al.

Although most of the automated theorem-proving approaches depend on formal proof systems, informal theorem proving can align better with large language models' (LLMs) strength in natural language processing. In this work, we identify a primary bottleneck in informal theorem proving as a lack of insight, namely the difficulty of recognizing the core techniques required to solve complex problems. To address this, we propose a novel framework designed to cultivate this essential reasoning skill and enable LLMs to perform insightful reasoning. We propose $\mathtt{DeepInsightTheorem}$, a hierarchical dataset that structures informal proofs by explicitly extracting core techniques and proof sketches alongside the final proof. To fully exploit this dataset, we design a Progressive Multi-Stage SFT strategy that mimics the human learning process, guiding the model from basic proof writing to insightful thinking. Our experiments on challenging mathematical benchmarks demonstrate that this insight-aware generation strategy significantly outperforms baselines. These results demonstrate that teaching models to identify and apply core techniques can substantially improve their mathematical reasoning.

Zhongjian Qiao, Rui Yang, Jiafei Lyu et al.

Single-domain offline reinforcement learning (RL) often suffers from limited data coverage, while cross-domain offline RL handles this issue by leveraging additional data from other domains with dynamics shifts. However, existing studies primarily focus on train-time robustness (handling dynamics shifts from training data), neglecting the test-time robustness against dynamics perturbations when deployed in practical scenarios. In this paper, we investigate dual (both train-time and test-time) robustness against dynamics shifts in cross-domain offline RL. We first empirically show that the policy trained with cross-domain offline RL exhibits fragility under dynamics perturbations during evaluation, particularly when target domain data is limited. To address this, we introduce a novel robust cross-domain Bellman (RCB) operator, which enhances test-time robustness against dynamics perturbations while staying conservative to the out-of-distribution dynamics transitions, thus guaranteeing the train-time robustness. To further counteract potential value overestimation or underestimation caused by the RCB operator, we introduce two techniques, the dynamic value penalty and the Huber loss, into our framework, resulting in the practical \textbf{D}ual-\textbf{RO}bust \textbf{C}ross-domain \textbf{O}ffline RL (DROCO) algorithm. Extensive empirical results across various dynamics shift scenarios show that DROCO outperforms strong baselines and exhibits enhanced robustness to dynamics perturbations.

Zhongjian Qiao, Rui Yang, Jiafei Lyu et al.

Cross-Domain Offline Reinforcement Learning aims to train an agent deployed in the target environment, leveraging both a limited target domain dataset and a source domain dataset with (possibly) sufficient data coverage. Due to the underlying dynamics misalignment between the source and target domain, simply merging the data from two datasets may incur inferior performance. Recent advances address this issue by selectively sharing source domain samples that exhibit dynamics alignment with the target domain. However, these approaches focus solely on dynamics alignment and overlook \textit{value alignment}, i.e., selecting high-quality, high-value samples from the source domain. In this paper, we first demonstrate that both dynamics alignment and value alignment are essential for policy learning, by examining the limitations of the current theoretical framework for cross-domain RL and establishing a concrete sub-optimality gap of a policy trained on the source domain and evaluated on the target domain. Motivated by the theoretical insights, we propose to selectively share those source domain samples with both high dynamics and value alignment and present our \textbf{\underline{D}}ynamics- and \textbf{\underline{V}}alue-aligned \textbf{\underline{D}}ata \textbf{\underline{F}}iltering (DVDF) method. We design a range of dynamics shift settings, including kinematic and morphology shifts, and evaluate DVDF on various tasks and datasets, as well as in challenging extremely low-data settings where the target domain dataset contains only 5,000 transitions. Extensive experiments demonstrate that DVDF consistently outperforms prior strong baselines and delivers exceptional performance across multiple tasks and datasets.

Zhongjian Qiao, Jiafei Lyu, Boxiang Lyu et al.

Model-based offline reinforcement learning (RL) aims to enhance offline RL with a dynamics model that facilitates policy exploration. However, \textit{model exploitation} could occur due to inevitable model errors, degrading algorithm performance. Adversarial model learning offers a theoretical framework to mitigate model exploitation by solving a maximin formulation. Within such a paradigm, RAMBO~\citep{rigter2022rambo} has emerged as a representative and most popular method that provides a practical implementation with model gradient. However, we empirically reveal that severe Q-value underestimation and gradient explosion can occur in RAMBO with only slight hyperparameter tuning, suggesting that it tends to be overly conservative and suffers from unstable model updates. To address these issues, we propose \textbf{RO}bust value-aware \textbf{M}odel learning with \textbf{I}mplicitly differentiable adaptive weighting (ROMI). Instead of updating the dynamics model with model gradient, ROMI introduces a novel robust value-aware model learning approach. This approach requires the dynamics model to predict future states with values close to the minimum Q-value within a scale-adjustable state uncertainty set, enabling controllable conservatism and stable model updates. To further improve out-of-distribution (OOD) generalization during multi-step rollouts, we propose implicitly differentiable adaptive weighting, a bi-level optimization scheme that adaptively achieves dynamics- and value-aware model learning. Empirical results on D4RL and NeoRL datasets show that ROMI significantly outperforms RAMBO and achieves competitive or superior performance compared to other state-of-the-art methods on datasets where RAMBO typically underperforms. Code is available at https://github.com/zq2r/ROMI.git.

Ruicheng Ao, Siyang Gao, David Simchi-Levi

This technical note studies the reliability limits of LLM-based multi-agent planning as a delegated decision problem. We model the LLM-based multi-agent architecture as a finite acyclic decision network in which multiple stages process shared model-context information, communicate through language interfaces with limited capacity, and may invoke human review. We show that, without new exogenous signals, any delegated network is decision-theoretically dominated by a centralized Bayes decision maker with access to the same information. In the common-evidence regime, this implies that optimizing over multi-agent directed acyclic graphs under a finite communication budget can be recast as choosing a budget-constrained stochastic experiment on the shared signal. We also characterize the loss induced by communication and information compression. Under proper scoring rules, the gap between the centralized Bayes value and the value after communication admits an expected posterior divergence representation, which reduces to conditional mutual information under logarithmic loss and to expected squared posterior error under the Brier score. These results characterize the fundamental reliability limits of delegated LLM planning. Experiments with LLMs on a controlled problem set further demonstrate these characterizations.

Ruicheng Ao, Hongyu Chen, Siyang Gao et al.

We study fixed-confidence best-arm identification (BAI) where a cheap but potentially biased proxy (e.g., LLM judge) is available for every sample, while an expensive ground-truth label can only be acquired selectively when using a human for auditing. Unlike classical multi-fidelity BAI, the proxy is biased (arm- and context-dependent) and ground truth is selectively observed. Consequently, standard multi-fidelity methods can mis-select the best arm, and uniform auditing, though accurate, wastes scarce resources and is inefficient. We prove that without bias correction and propensity adjustment, mis-selection probability may not vanish (even with unlimited proxy data). We then develop an estimator for the mean of each arm that combines proxy scores with inverse-propensity-weighted residuals and form anytime-valid confidence sequences for that estimator. Based on the estimator and confidence sequence, we propose an algorithm that adaptively selects and audits arms. The algorithm concentrates audits on unreliable contexts and close arms and we prove that a plug-in Neyman rule achieves near-oracle audit efficiency. Numerical experiments confirm the theoretical guarantees and demonstrate the superior empirical performance of the proposed algorithm.

Mingjie Hu, Siyang Gao, Jian-qiang Hu et al.

Large language models (LLMs) have significant potential to improve operational efficiency in operations management. Deploying these models requires specifying a policy that governs response quality, shapes user experience, and influences operational value. In this research, we treat LLMs as stochastic simulators and propose a pairwise comparison-based adaptive simulation experiment framework for identifying the optimal policy from a finite set of candidates. We consider two policy spaces: an unstructured space with no parametric assumption, and a structured space in which the data are generated from a preference model. For both settings, we characterize the fundamental data requirements for identifying the optimal policy with high probability. In the unstructured case, we derive a closed-form expression for the optimal sampling proportions, together with a clear operational interpretation. In the structured case, we formulate a regularized convex program to compute the optimal proportions. We then develop an adaptive experimental procedure, termed LLM-PO, for both policy spaces, and prove that it identifies the optimal policy with the desired statistical guarantee while asymptotically attaining the fundamental data requirements. Numerical experiments demonstrate that LLM-PO consistently outperforms benchmark methods and improves LLM performance.

Yingxu Wang, Kunyu Zhang, Mengzhu Wang et al.

SF-GDA is pivotal for privacy-preserving knowledge transfer across graph datasets. Although recent works incorporate structural information, they implicitly condition adaptation on the smoothness priors of sourcetrained GNNs, thereby limiting their generalization to structurally distinct targets. This dependency becomes a critical bottleneck under significant topological shifts, where the source model misinterprets distinct topological patterns unseen in the source domain as noise, rendering pseudo-label-based adaptation unreliable. To overcome this limitation, we propose the Universal Structural Basis Distillation, a framework that shifts the paradigm from adapting a biased model to learning a universal structural basis for SF-GDA. Instead of adapting a biased source model to a specific target, our core idea is to construct a structure-agnostic basis that proactively covers the full spectrum of potential topological patterns. Specifically, USBD employs a bi-level optimization framework to distill the source dataset into a compact structural basis. By enforcing the prototypes to span the full Dirichlet energy spectrum, the learned basis explicitly captures diverse topological motifs, ranging from low-frequency clusters to high-frequency chains, beyond those present in the source. This ensures that the learned basis creates a comprehensive structural covering capable of handling targets with disparate structures. For inference, we introduce a spectral-aware ensemble mechanism that dynamically activates the optimal prototype combination based on the spectral fingerprint of the target graph. Extensive experiments on benchmarks demonstrate that USBD significantly outperforms state-of-the-art methods, particularly in scenarios with severe structural shifts, while achieving superior computational efficiency by decoupling the adaptation cost from the target data scale.

Yingxu Wang, Kunyu Zhang, Yanwu Yang et al.

Graph-based learning on functional magnetic resonance imaging (fMRI) has shown strong potential for brain network analysis. However, existing methods degrade under cross-site out-of-distribution (OOD) settings because site-conditioned confounders induce non-pathological shortcuts, while functional connectivity constructed by temporal averaging obscures transient neurodynamics, limiting generalization to unseen sites. In this paper, we propose Cross-site OOD Robust brain nEtwork (CORE), a unified framework for brain network learning across unseen sites. CORE first performs site-aware confounder decoupling to mitigate site-conditioned bias and extract a cross-site population scaffold of reproducible diagnostic connectivity edges. It then profiles transient pathway dynamics over this scaffold using lightweight temporal descriptors and organizes scaffold edges into a line graph for transferable pathway-level modeling. Finally, CORE introduces a prior-guided subject-adaptive gating mechanism that leverages scaffold-derived population priors while preserving subject-specific connectivity variability. Extensive experiments under leave-one-site-out evaluation on real-world datasets (ABIDE, REST-meta-MDD, SRPBS, and ABCD) show that CORE consistently outperforms state-of-the-art baselines, with up to 6.7% relative gain. Furthermore, CORE remains robust to atlas variations, maintaining performance gains across different brain parcellation schemes.

Qiji Zhou, Ruochen Zhou, Zike Hu et al.

Recent advancements in Chain-of-Thought (CoT) and related rationale-based works have significantly improved the performance of Large Language Models (LLMs) in complex reasoning tasks. With the evolution of Multimodal Large Language Models (MLLMs), enhancing their capability to tackle complex multimodal reasoning problems is a crucial frontier. However, incorporating multimodal rationales in CoT has yet to be thoroughly investigated. We propose the Image-of-Thought (IoT) prompting method, which helps MLLMs to extract visual rationales step-by-step. Specifically, IoT prompting can automatically design critical visual information extraction operations based on the input images and questions. Each step of visual information refinement identifies specific visual rationales that support answers to complex visual reasoning questions. Beyond the textual CoT, IoT simultaneously utilizes visual and textual rationales to help MLLMs understand complex multimodal information. IoT prompting has improved zero-shot visual reasoning performance across various visual understanding tasks in different MLLMs. Moreover, the step-by-step visual feature explanations generated by IoT prompting elucidate the visual reasoning process, aiding in analyzing the cognitive processes of large multimodal models

Shiqi Chen, Miao Xiong, Junteng Liu et al.

Large language models (LLMs) frequently hallucinate and produce factual errors, yet our understanding of why they make these errors remains limited. In this study, we delve into the underlying mechanisms of LLM hallucinations from the perspective of inner representations, and discover a salient pattern associated with hallucinations: correct generations tend to have sharper context activations in the hidden states of the in-context tokens, compared to the incorrect ones. Leveraging this insight, we propose an entropy-based metric to quantify the ``sharpness'' among the in-context hidden states and incorporate it into the decoding process to formulate a constrained decoding approach. Experiments on various knowledge-seeking and hallucination benchmarks demonstrate our approach's consistent effectiveness, for example, achieving up to an 8.6 point improvement on TruthfulQA. We believe this study can improve our understanding of hallucinations and serve as a practical solution for hallucination mitigation.

Shiqi Chen, Jinghan Zhang, Tongyao Zhu et al.

Vision-Language Models (VLMs) combine visual perception with the general capabilities, such as reasoning, of Large Language Models (LLMs). However, the mechanisms by which these two abilities can be combined and contribute remain poorly understood. In this work, we explore to compose perception and reasoning through model merging that connects parameters of different models. Unlike previous works that often focus on merging models of the same kind, we propose merging models across modalities, enabling the incorporation of the reasoning capabilities of LLMs into VLMs. Through extensive experiments, we demonstrate that model merging offers a successful pathway to transfer reasoning abilities from LLMs to VLMs in a training-free manner. Moreover, we utilize the merged models to understand the internal mechanism of perception and reasoning and how merging affects it. We find that perception capabilities are predominantly encoded in the early layers of the model, whereas reasoning is largely facilitated by the middle-to-late layers. After merging, we observe that all layers begin to contribute to reasoning, whereas the distribution of perception abilities across layers remains largely unchanged. These observations shed light on the potential of model merging as a tool for multimodal integration and interpretation.

Yingxu Wang, Kunyu Zhang, Jiaxin Huang et al.

Graph domain adaptation (GDA) aims to transfer knowledge from a labeled source graph to an unlabeled target graph under distribution shifts. However, existing methods are largely feature-centric and overlook structural discrepancies, which become particularly detrimental under significant topology shifts. Such discrepancies alter both geometric relationships and spectral properties, leading to unreliable transfer of graph neural networks (GNNs). To address this limitation, we propose Dual-Aligned Structural Basis Distillation (DSBD) for GDA, a novel framework that explicitly models and adapts cross-domain structural variation. DSBD constructs a differentiable structural basis by synthesizing continuous probabilistic prototype graphs, enabling gradient-based optimization over graph topology. The basis is learned under source-domain supervision to preserve semantic discriminability, while being explicitly aligned to the target domain through a dual-alignment objective. Specifically, geometric consistency is enforced via permutation-invariant topological moment matching, and spectral consistency is achieved through Dirichlet energy calibration, jointly capturing structural characteristics across domains. Furthermore, we introduce a decoupled inference paradigm that mitigates source-specific structural bias by training a new GNN on the distilled structural basis. Extensive experiments on graph and image benchmarks demonstrate that DSBD consistently outperforms state-of-the-art methods.

Shiqi Chen, Tongyao Zhu, Zian Wang et al.

Large Language Models (LLMs) as agents often struggle in out-of-distribution (OOD) scenarios. Real-world environments are complex and dynamic, governed by task-specific rules and stochasticity, which makes it difficult for LLMs to ground their internal knowledge in those dynamics. Under such OOD conditions, vanilla RL training often fails to scale; we observe Pass@k--the probability that at least one of (k) sampled trajectories succeeds--drops markedly across training steps, indicating brittle exploration and limited generalization. Inspired by model-based reinforcement learning, we hypothesize that equipping LLM agents with an internal world model can better align reasoning with environmental dynamics and improve decision-making. We show how to encode this world model by decomposing it into two components: state representation and transition modeling. Building on this, we introduce SPA, a simple reinforcement learning framework that cold-starts the policy via a Self-Play supervised finetuning (SFT) stage to learn the world model by interacting with the environment, then uses it to simulate future states prior to policy optimization. This simple initialization outperforms the online world-modeling baseline and greatly boosts the RL-based agent training performance. Experiments across diverse environments like Sokoban, FrozenLake, and Sudoku show that our approach significantly improves performance. For example, SPA boosts the Sokoban success rate from 25.6% to 59.8% and raises the FrozenLake score from 22.1% to 70.9% for the Qwen2.5-1.5B-Instruct model.

Yingxu Wang, Shiqi Fan, Mengzhu Wang et al.

Knowledge Graph Question Answering (KGQA) aims to interpret natural language queries and perform structured reasoning over knowledge graphs by leveraging their relational and semantic structures to retrieve accurate answers. Existing methods primarily follow either the retrieve-then-reason paradigm, which relies on Graph Neural Networks or heuristic rules to extract static candidate paths, or dynamic path generation strategies that employ LLMs with prompting to jointly perform retrieval and reasoning. However, the former lacks adaptability due to static path extraction and the absence of contextual refinement, while the latter suffers from high computational costs and limited evaluation accuracy because of their dependence on fixed scoring functions and repeated LLM calls. To address these issues, this paper proposes Dynamically Adaptive MCTS-based Reasoning (DAMR), a novel framework that integrates LLM-guided Monte Carlo Tree Search (MCTS) with adaptive path evaluation to enable efficient and context-aware KGQA. DAMR leverages MCTS as a backbone, where an LLM-based planner selects the top-$k$ semantically relevant relations at each expansion step to effectively reduce the search space. To enhance evaluation accuracy, we introduce a lightweight Transformer-based scorer that performs context-aware plausibility estimation by jointly encoding the question and relation sequence through cross-attention, thereby capturing fine-grained semantic shifts during multi-hop reasoning. Furthermore, to mitigate the scarcity of high-quality supervision, DAMR incorporates a dynamic pseudo-path refinement mechanism that periodically generates training signals from partial paths explored during search, enabling the scorer to continually adapt to the evolving distribution of reasoning trajectories. Extensive experiments on multiple KGQA benchmarks show that DAMR significantly outperforms SOTA methods.

Le Yang, Siyang Gao, Cheng Li et al.

We consider the problem of the best arm identification in the presence of stochastic constraints, where there is a finite number of arms associated with multiple performance measures. The goal is to identify the arm that optimizes the objective measure subject to constraints on the remaining measures. We will explore the popular idea of Thompson sampling (TS) as a means to solve it. To the best of our knowledge, it is the first attempt to extend TS to this problem. We will design a TS-based sampling algorithm, establish its asymptotic optimality in the rate of posterior convergence, and demonstrate its superior performance using numerical examples.

Shiqi Chen, Siyang Gao, Junxian He

Detecting factual errors in summaries has been an important and challenging subject in summarization research. Inspired by the emergent ability of large language models (LLMs), we explore evaluating factual consistency of summaries by directly prompting LLMs. We present a comprehensive empirical study to assess the ability of LLMs as factual consistency evaluators, which consists of (1) analyzing different LLMs such as the GPT model series and Flan-T5; (2) investigating a variety of prompting methods including vanilla prompting, chain-of-thought prompting, and a sentence-by-sentence prompting method to tackle long summaries; and (3) evaluating on diverse summaries generated by multiple summarization systems, ranging from pre-transformer methods to SOTA pretrained models. Our experiments demonstrate that prompting LLMs is able to outperform the previous best factuality systems in all settings, by up to 12.2 absolute points in terms of the binary classification accuracy on inconsistency detection.