Large language models have revolutionized agent planning by serving as the engine of heuristic guidance. However, LLM-based agents often struggle to generalize across complex environments and to adapt to stochastic feedback arising from environment–action interactions. We propose Counterfactual Planning—a method designed to improve the generalizability and adaptability of agents' actions by inferring causal representations of environmental confounders and performing counterfactual reasoning over planned actions. We formalize the agent planning process as a structural causal model, providing a mathematical formulation for causal analysis of how environmental states influence action generation and how actions affect future state transitions. To support generalizable action planning, we introduce the State Causality Evaluator (SCE), which dynamically infers task-conditioned causal representations from complex environment states; and to enhance adaptability under stochastic feedback, we propose the What-If-Not (WIN) reward, which performs counterfactual interventions to refine actions through causal evaluation. We validate our framework in an open-world environment, where experiments demonstrate improvements in both action generalization and planning adaptability.

Pengqi Li, Lizhong Ding, Zhehao Zhou, Chunhui Zhang, Jiarun Fu, Hao Li, Ye Yuan, Guoren Wang. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Kolmogorov-Arnold Networks (KANs) have demonstrated remarkable expressive capacity and predictive power in symbolic learning. However, existing generalization errors of KANs primarily focus on approximation errors while neglecting estimation errors, leading to a suboptimal bias-variance trade-off and poor generalization performance. Meanwhile, the unclear generalization mechanism hinders the design of more effective KANs variants. As the authors of KANs highlighted, they ``would like to explore ways to restrict KANs' hypothesis space so that they can achieve good performance''. To address these challenges, we explore the generalization mechanism of KANs and design more effective KANs with lower model complexity and better generalization. We define \textit{Lipschitz complexity} as the first structural measure for deep functions represented by KANs and derive novel generalization bounds based on \textit{Lipschitz complexity}, establishing a theoretical foundation for understanding their generalization behavior. To reduce \textit{Lipschitz complexity} and boost the generalization mechanism of KANs, we propose Lipschitz-Enhanced KANs ($\textbf{LipKANs}$) by integrating the Lip layer and pioneering the $L_{1.5}$-regularized loss, contributing to tighter generalization bounds. Empirical experiments validate that the proposed LipKANs enhance the generalization mechanism of KANs when modeling complex distributions. We hope our theoretical bounds and LipKANs lay a foundation for the future development of KANs.

Modeling users’ short-term dynamic and long-term static interests to enhance Point-of-Interests (POI) recommendation performance has shown lots of advantages. Since users’ check-in records can be viewed as a graph network, methods based on Graph Neural Networks (GNNs) have recently shown promising applicability for POI recommendation. However, existing GNN-based works have the following shortcomings: (1) ignoring the impact of complex higher-order relationships between user-POI dynamics over time; and (2) ignoring the difference in POI importance that cannot effectively capture the imbalances of geographical influence among POIs. To address these challenges, we propose a novel Self-supervised Long-and Short-term model (SLS-REC) for POI recommendation. Specifically, we first design a spatio-temporal Hawkes attention hypergraph neural network to capture the spatial dependence and temporal evolution in users’ short-term dynamic interests. Then we introduce a dynamic propagation mechanism of GNNs to learn the geographic influences underlying geographic imbalances among POIs. In addition, the contrastive learning framework over a fine-grained node dropout strategy is applied to maximize the mutual information of long and short-term interest representations. Finally, we adaptively unify the recommendation and self-supervised task with an attention-based mechanism to optimize the proposed SLS-REC model for POI recommendation. Experiments on real-world datasets show that the proposed model significantly outperforms state-of-the-art methods.

Abstract With the development of image recognition technology, face, body shape, and other factors have been widely used as identification labels, which provide a lot of convenience for our daily life. However, image recognition has much higher requirements for image conditions than traditional identification methods like a password. Therefore, image enhancement plays an important role in the process of image analysis for images with noise, among which the image of low-light is the top priority of our research. In this paper, a low-light image enhancement method based on the enhanced network module optimized Generative Adversarial Networks(GAN) is proposed. The proposed method first applied the enhancement network to input the image into the generator to generate a similar image in the new space, Then constructed a loss function and minimized it to train the discriminator, which is used to compare the image generated by the generator with the real image. We implemented the proposed method on two image datasets (DPED, LOL), and compared it with both the traditional image enhancement method and the deep learning approach. Experiments showed that our proposed network enhanced images have higher PNSR and SSIM, the overall perception of relatively good quality, demonstrating the effectiveness of the method in the aspect of low illumination image enhancement.