Singapore

With the advancements of large language models (LLMs), intelligent tutoring systems have witnessed significant progress. The extensive knowledge and reasoning capabilities of LLMs enable intelligent tutoring systems to generate more helpful tutoring dialogues with scaffolding instructions. However, these systems fail to provide scaffolds that align with the personalized needs of students due to the lack of attention to the long-term learning process of students. Meanwhile, the pursuit of more suitable scaffolds through complex reasoning may result in additional computational overhead. To address these issues, we propose LEAP, a Long-term Educational Adaptive Planning system that can model students&#39; long-term learning process. Specifically, LEAP plans for scaffolds through collaboration of direct planning and thoughtful reasoning to improve efficiency and captures students&#39; long-term learning progress through cognitive state extraction. Then we propose LEAD, a Long-term Educational Archive Dataset to alleviate the lack of data and validate the effectiveness of LEAP, which is constructed through real-world students&#39; reactions and simulation of the teacher-student interactions. Experiments on several datasets demonstrate the effectiveness of LEAP.

AAAI 2026

Learning from Long-Term Engagement: Adaptive Tutoring Dialogue Planning for Personalized Education

intelligent tutoring system

large language model

education

It is my great pleasure and honor to welcome you to the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026), held in San Diego, California, USA, July 2–7, 2026. ACL 2026 continues our fields tradition of excellence in scholarship, innovation, and inclusivity, and I am deeply grateful to the many volunteers who have worked tirelessly to bring this event to life.

It is exciting to see the many developments in the field reflected at our conference, such as the advancement of large language models (born out of our community) into many application directions. This is not without challenges, partly due to unsolved problems, and partly due to misuse of the technology. All this is reflected well at ACL 2026. The conference also reflects that the field is not only about advancing technology, but also the science of fundamentally understanding language and how it is use by many different speaker communities. 
[Full Message from General Chair Philipp Koehn](https://drive.google.com/file/d/1QiJFOmMjvDgsDo3i1XzlQnImxe3RU_Cy/view?usp=sharing) 
<html><button style="display: inline-flex; align-items: center; justify-content: center; white-space: nowrap; border-radius: 9999px; font-weight: bold; background: #7c3aed; color: white; font-family: 'Space Grotesk', sans-serif; height: 40px; font-size: 16px; padding: 0 20px; border: none; cursor: pointer" onclick="window.open('https://drive.google.com/file/d/1QiJFOmMjvDgsDo3i1XzlQnImxe3RU_Cy/view?usp=sharing')">Conference Handbook</button></html>

To access this event page, you need to log in with the **email address you registered with**. Access credentials will be sent to your email from Underline - subject line "Welcome to ACL 2026". Please be sure to check your spam email folder if you do not see an email confirmation right away.

To access this event page, you are required to register.
Please complete your registration to continue.

We recommend reading [**the registration information**](https://2026.aclweb.org/registration/) first.

Registration Required

ACL 2026

The 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026) will take place in San Diego, California, from July 2 - 7, 2026.

With the advancements of large language models (LLMs), intelligent tutoring systems have witnessed significant progress. The extensive knowledge and reasoning capabilities of LLMs enable intelligent tutoring systems to generate more helpful tutoring dialogues with scaffolding instructions. However, these systems fail to provide scaffolds that align with the personalized needs of students due to the lack of attention to the long-term learning process of students. Meanwhile, the pursuit of more suitable scaffolds through complex reasoning may result in additional computational overhead. To address these issues, we propose LEAP, a Long-term Educational Adaptive Planning system that can model students' long-term learning process. Specifically, LEAP plans for scaffolds through collaboration of direct planning and thoughtful reasoning to improve efficiency and captures students' long-term learning progress through cognitive state extraction. Then we propose LEAD, a Long-term Educational Archive Dataset to alleviate the lack of data and validate the effectiveness of LEAP, which is constructed through real-world students' reactions and simulation of the teacher-student interactions. Experiments on several datasets demonstrate the effectiveness of LEAP.

technical paper

We are pleased to announce the Fortieth AAAI Conference on Artificial Intelligence (AAAI-26), which will be held in Singapore EXPO from January 20 to January 27, 2026.

The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines. AAAI-26 will feature technical paper presentations, special tracks, invited speakers, workshops, tutorials, poster sessions, senior member presentations, competitions, and exhibit programs, and a range of other activities to be announced.

To access this event page, you need to log in with the **email address you registered with**. Access credentials will be sent to your email from Underline - subject line "Welcome to AAAI 2026". Please be sure to check your spam email folder if you do not see an email confirmation right away.

Please log in

To access this event page, you are required to register.
Please complete your registration to continue.

We recommend reading [**the registration information**](https://aaai.org/conference/aaai/aaai-26/registration/) first.

**Online Registration Form**: https://aaai.getregistered.net/conference-2026 

We are pleased to announce the Fortieth AAAI Conference on Artificial Intelligence (AAAI-26), which will be held in Singapore EXPO from January 20 to January 27, 2026.

Various complex water management decisions are made in snow-dominant watersheds with the knowledge of Snow-Water Equivalent (SWE)---a key measure widely used to estimate the water content of a snowpack. However, forecasting SWE is challenging because SWE is influenced by various factors including topography and an array of environmental conditions, and has therefore been observed to be spatio-temporally variable. Classical approaches to SWE forecasting have not adequately utilized these spatial/temporal correlations, nor do they provide uncertainty estimates --- which can be of significant value to the decision maker. In this paper, we present ForeSWE, a new probabilistic spatio-temporal forecasting model that integrates deep learning and classical probabilistic techniques. The resulting model features a combination of an attention mechanism to integrate spatiotemporal features and interactions, alongside a Gaussian process module that provides principled quantification of prediction uncertainty. We evaluate the model on data from 512 Snow Telemetry (SNOTEL) stations in the Western US. The results show significant improvements in both forecasting accuracy and prediction interval compared to state-of-the-art approaches. The results also serve to highlight the efficacy in uncertainty estimates between different approaches. Collectively, these findings have provided a platform for deployment and feedback by the water management community.

ForeSWE: Forecasting Snow-Water Equivalent with an Uncertainty-Aware Attention Model

Vision modeling has advanced rapidly with Transformers, whose attention mechanisms capture visual dependencies but lack a principled account of how semantic information propagates spatially. To address this, many physics-inspired models adopt heat conduction dynamics, where the temporal decay rate is proportional to the product of time and spatial frequency, inherently coupling them and causing high-frequency components to decay much faster than low-frequency ones. However, this preferential decay of high-frequency signals suppresses textures, edges, and other fine details that are crucial for preserving semantic richness in vision models. In this paper, we introduce WaveFormer, a novel physics‑inspired vision backbone that leverages frequency–time decoupled wave propagation. By decoupling frequency from temporal evolution through an underdamped wave equation, high‑frequency components oscillate rather than being rapidly damped, preserving fine‑grained details while maintaining low‑frequency stability. For efficient and interpretable modeling, we derive a closed-form solution of the underdamped wave equation that decouples frequency from temporal evolution. Leveraging this principle, we implement the Frequency–Time Decoupled Wave Propagation Operator (WPO), a lightweight module that models global interactions in $\mathcal{O}(N \log N)$ time—far lower than the $\mathcal{O}(N^2)$ cost of attention. We propose a family of WaveFormer models as drop-in replacements for standard ViTs and CNNs, achieving competitive accuracy across image classification, object detection, and semantic segmentation, while delivering up to $1.6\times$ higher throughput and 30\% fewer FLOPs than attention-based alternatives. Furthermore, our results demonstrate that wave propagation introduces a complementary modeling bias to heat-based approaches, effectively capturing both global coherence and high-frequency details essential for rich visual semantics.

WaveFormer: Frequency-Time Decoupled Vision Modeling with Wave Equation

Fake orders pose increasing threats to sequential recommender systems by misleading recommendation results through artificially manipulated interactions, including click farming, context-irrelevant substitutions, and sequential perturbations. 
Unlike injecting carefully designed fake users to influence recommendation performance, fake orders embedded within genuine user sequences aim to disrupt user preferences and mislead recommendation results, thereby manipulating exposure rates of specific items to gain competitive advantages. To protect users' authentic interest preferences and eliminate misleading information, this paper aims to perform precise and efficient rectification on compromised sequential recommender systems while avoiding the enormous computational and time costs of retraining existing models. Specifically, we identify that fake orders are not absolutely harmful—in certain cases, partial fake orders can even have a data augmentation effect. Based on this insight, we propose $\textit{Dual-view Identification}$ and $\textit{Targeted Rectification (DITaR)}$, which primarily identifies harmful samples to achieve unbiased rectification of the system. The core idea of this method is to obtain differentiated representations from collaborative and semantic views for precise detection, and then filters detected suspicious fake orders to select truly harmful ones for targeted rectification with gradient ascent. 
This ensures that useful information in fake orders is not removed while preventing bias residue. Moreover, it maintains the original data volume and sequence structure, thus protecting system performance and trustworthiness to achieve optimal unbiased rectification.
Extensive experiments on three datasets demonstrate that DITaR achieves superior performance compared to state-of-the-art methods in terms of recommendation quality, computational efficiency, and system robustness.

Unbiased Rectification for Sequential Recommender Systems Under Fake Orders

Cross-modal hashing (CMH) is an effective tool for large-scale retrieval due to its low storage cost and high efficiency. However, real-world multi-modal datasets often contain noisy annotations, which can significantly impair model performance. Many existing methods address this issue by using the small-loss criterion to select a likely clean subset of data to guide model training. Nonetheless, this clean subset is typically dominated by easy samples, and treating all samples within it equally can undermine the model’s generalization ability. In this paper, we propose a novel meta-learning-based framework, named Meta-Guided Sample Reweighting for Cross-Modal Hashing Retrieval (MGSH), which integrates meta-learning into robust cross-modal hashing. To address the above issues, we design a Meta-Similarity Weighting Network (MSWN) that dynamically assigns importance weights to samples during training. By employing a bi-level optimization strategy, the meta-importance weights are used to scale the loss of training samples during the main network update, encouraging the model to focus on more challenging examples. Additionally, to further distinguish between noisy and clean samples, we incorporate adaptive-margin and meta-guided center aggregation into a robust hashing loss, both guided by the learned meta-importance weights. Extensive experiments on three widely used benchmark datasets demonstrate that MGSH consistently outperforms state-of-the-art methods, validating its effectiveness.

Meta-Guided Sample Reweighting for Robust Cross-Modal Hashing Retrieval with Noisy Labels

The Information Bottleneck (IB) principle facilitates effective representation learning by preserving label-relevant information while compressing irrelevant information. However, its strong reliance on accurate labels makes it inherently vulnerable to label noise, prevalent in real-world scenarios, resulting in significant performance degradation and overfitting. To address this issue, we propose **LaT-IB**, a novel **La**bel-Noise Resistan**T** **I**nformation **B**ottleneck method which introduces a *"Minimal-Sufficient-Clean"* (MSC) criterion. Instantiated as a mutual information regularizer to retain task-relevant information while discarding noise, MSC addresses standard IB’s vulnerability to noisy label supervision. To achieve this, LaT-IB employs a noise-aware latent disentanglement that decomposes the latent representation into components aligned with to the clean label space and the noise space. Theoretically, we first derive mutual information bounds for each component of our objective including prediction, compression, and disentanglement, and moreover prove that optimizing it encourages representations invariant to input noise and separates clean and noisy label information.
Furthermore, we design a three-phase training framework: Warmup, Knowledge Injection and Robust Training, to progressively guide the model toward noise-resistant representations. Extensive experiments demonstrate that LaT-IB achieves superior robustness and efficiency under label noise, significantly enhancing robustness and applicability in real-world scenarios with label noise.

Is the Information Bottleneck Robust Enough? Towards Label-Noise Resistant Information Bottleneck Learning

Sound separation (SS) and target sound extraction (TSE) are fundamental techniques for addressing complex acoustic scenarios. While existing SS methods struggle with determining the unknown number of sound sources, TSE approaches require precisely specified clues to achieve optimal performance. This paper proposes a unified framework that synergistically combines SS and TSE to overcome their individual limitations. Our architecture employs two complementary components: 1) An Encoder-Decoder Attractor (EDA) network that automatically infers both the source count and corresponding acoustic clues for SS, and 2) A multi-modal fusion network that precisely interprets diverse user-provided clues (acoustic, semantic, or visual) for TSE. Through joint training with cross-task consistency constraints, we establish a unified latent space that bridges both paradigms. During inference, the system adaptively operates in either fully autonomous SS mode or clue-driven TSE mode. Experiments demonstrate remarkable performance in both tasks, with notable improvements of 1.4 dB SDR improvement in SS compared to baseline and 86% TSE accuracy.

USE: A Unified Model for Universal Sound Separation and Extraction

In recent years, constraint solvers show increasing use in solving various open combinatorial problems, e.g., from Ramsey theory or synthesis of combinatorial designs. The similar approach can be applied to some problems related to binary linear codes, which form one of the largest families of error correcting codes used both in coding theory and in various practical applications. Thanks to a simple algebraic structure of such codes it is possible to study them using a wide range of methods. Note that even codes with the same basic parameters (length $n$, dimension $k$, minimal code distance $d$) can show different error correction performance, i.e., the ability to correct errors which appear in a noisy channel. In the paper, we formulate the problem of finding binary linear codes with good error correction performance as a constraint optimization problem and explore the effectiveness of modern constraint solvers on it, including SAT, MaxSAT, and CP solvers. Using the respective solvers and parallel computing, for several values of $n$, $k$, $d$ we found the codes which are significantly better than the known in terms of their practical performance.

Using Constraint Solvers to Construct Binary Codes with Good Error Correction Performance

It is well understood that mental modeling forms the foundation of many everyday interactions between humans. This includes both collaborative and deceptive interactions. In fact, one could argue that the modeling and manipulation of mental states lies at the heart of effective deception. In this paper, we examine the security problem of insider threat attacks. In this case, an adversary has already infiltrated an organization. The primary challenge for this attacker is to avoid suspicion until their true goal can be achieved. We see how existing model-based explanatory methods can be leveraged to generate lies that explain away potentially suspicious activities. We also propose a novel planning formulation that generates plans that appear to achieve an assigned goal while getting close enough to achieve an alternative, covert goal. We evaluate the computational effectiveness of our formulation on multiple planning benchmarks.

Mental Model-based Generation of Lies for Insider Threat Modeling

We consider the problem of assigning items to platforms where each item has a utility associated with each of the platforms to which it can be assigned. Each platform has a soft constraint over the total number of items it serves, modeled via a convex cost function. Additionally, items are partitioned into groups, and each platform also incurs group-specific convex cost over the number of items from each group that can be assigned to the platform. These costs promote group fairness by penalizing imbalances, yielding a soft variation of fairness notions introduced in prior work, such as Restricted Dominance and Minority protection. Restricted Dominance enforces upper bounds on group representation, while Minority protection enforces lower bounds. Our approach replaces such hard constraints with cost-based penalties, allowing more flexible trade-offs. Our model also captures Nash Social Welfare kind of objective. 

The cost of an assignment is the sum of the values of all the cost functions across all the groups and platforms. The objective is to find an assignment that minimizes the cost while achieving a total utility that is at least a user-specified threshold. The main challenge lies in balancing the overall platform cost with group-specific costs, both governed by convex functions, while meeting the utility constraint. We present an efficient polynomial-time approximation algorithm, supported by theoretical guarantees and experimental evaluation. 

Our algorithm is based on techniques involving linear programming and network flows. We also provide an exact algorithm for a special case with uniform utilities and establish the hardness of the general problem when the groups can intersect arbitrarily. This work has applications in cloud computing, logistics, resource-constrained machine learning deployment, federated learning, and network design, where resources must be allocated across platforms with diverse cost structures and diminishing returns.

Group Fair Matchings Using Convex Cost Functions

Test-time scaling has significantly improved large language model (LLM) performance, enabling deeper reasoning to solve complex problems. However, this increased reasoning capability also leads to excessive token generation and unnecessary problem-solving attempts. We introduce ``Don't Reason Bench (DNR Bench)'', a new benchmark designed to evaluate LLMs’ ability to robustly understand the tricky reasoning triggers and avoiding unnecessary generation. DNR Bench consists of 150 adversarially designed prompts that are easy for humans to understand and respond to, but surprisingly not for many of the recent prominent LLMs. DNR Bench tests models' abilities across different capabilities, such as instruction adherence, hallucination avoidance, redundancy filtering, and unanswerable question recognition. We evaluate reasoning LLMs (RLMs), including DeepSeek-R1, OpenAI O3-mini, Claude-3.7-sonnet and compare them against a powerful non-reasoning model, e.g., GPT-4o. Our experiments reveal that RLMs generate up to 70$\times$ more tokens than necessary, often failing at tasks that simpler non-reasoning models handle efficiently with higher accuracy. Our findings underscore the need for more effective training and inference strategies in RLMs.

Downloads

Next from AAAI 2026

ForeSWE: Forecasting Snow-Water Equivalent with an Uncertainty-Aware Attention Model

Similar lecture

LongTutor: Benchmarking Large Language Models for Long-term Personalized Tutoring

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from AAAI 2026

ForeSWE: Forecasting Snow-Water Equivalent with an Uncertainty-Aware Attention Model

Similar lecture

LongTutor: Benchmarking Large Language Models for Long-term Personalized Tutoring

Downloads