United States

Multi-agent pathfinding (MAPF) is a challenging computational problem that generally asks to find collision-free paths for multiple agents in a shared environment. Solving MAPF optimally is NP-hard, yet efficient solutions are critical for numerous applications, including automated warehouses and transportation systems. Recently, learning-based approaches to MAPF have gained attention, particularly those leveraging deep reinforcement learning. Following current trends in machine learning, we have created a foundation model for the MAPF problems called MAPF-GPT. Using imitation learning, we have trained a policy on a set of pre-collected sub-optimal expert trajectories that can generate actions in conditions of partial observability without additional heuristics, reward functions or communication with other agents. The resulting MAPF-GPT model demonstrates zero-shot learning abilities when solving the MAPF problem instances that were not present in the training dataset. We show that MAPF-GPT notably overpasses the current best-performing learnable-MAPF solvers on a diverse range of problem instances and is efficient in terms of computation (in the inference mode).

AAAI 2025

MAPF-GPT: Imitation Learning for Multi-Agent Pathfinding at Scale

multiagent planning

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 

Registration Required

AAAI 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.

technical paper

We are pleased to announce the Thirty-Ninth AAAI Conference on Artificial Intelligence (AAAI-25), which will be held in Philadelphia, Pennsylvania at the Pennsylvania Convention Center from February 25 to March 4, 2025.

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-25 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.

### [Invited Speakers](https://aaai.org/conference/aaai/aaai-25/aaai-25-invited-speakers/)

Register [here](https://aaai.org/conference/aaai/aaai-25/registration/)

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-25 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.



In this paper, we augment online algorithms for the knapsack problem using the total weight information. The conventional optimal online algorithm achieves the $\ln (\frac{U}{L})+1$ competitive ratio where $L$ and $U$ are the upper and lower bounds of the value-to-weight ratio. However, it does not consider that decision makers can know the total weight information or obtain it through machine-learned predictions. To fill this gap, we first propose the Known Weight Algorithm (KWA) which uses the exact total weight information to achieve a competitive ratio of $\mathcal{W}(\frac{1}{e}\frac{U-L}{L})+1$, where $\mathcal{W}$ denotes the Lambert-W function. We prove that it is optimal and tight. After that, we extend KWA to the Predicted Weight Algorithm (PWA), a learning-augmented online algorithm that uses predicted total weight. We show the consistency and robustness of PWA, and prove that its competitive ratio degrades gracefully as the prediction error grows. Finally, we introduce the Limited Volume Algorithm (LWA), which achieves a better competitive ratio than $\ln \frac{U}{L}+1$ when the total weight is less than twice the capacity.

Augmenting Online Algorithms for Knapsack Problem with Total Weight Information

Recent advancements in proactive dialogues have garnered significant attention, particularly for more complex objectives (e.g. emotion support and persuasion). Unlike traditional task-oriented dialogues, proactive dialogues demand advanced policy planning and adaptability, requiring rich scenarios and comprehensive policy repositories to develop such systems. However, existing approaches tend to rely on Large Language Models (LLMs) for user simulation and online learning, leading to biases that diverge from realistic scenarios and result in suboptimal efficiency. Moreover, these methods depend on manually defined, context-independent, coarse-grained policies, which not only incur high expert costs but also raise concerns regarding their completeness. In our work, we highlight the potential for automatically discovering policies directly from raw, real-world dialogue records. To this end, we introduce a novel dialogue policy planning framework, LDPP. It fully automates the process from mining policies in dialogue records to learning policy planning. Specifically, we employ a variant of the Variational Autoencoder to discover fine-grained policies represented as latent vectors. After automatically annotating the data with these latent policy labels, we propose an Offline Hierarchical Reinforcement Learning (RL) algorithm in the latent space to develop effective policy planning capabilities. Our experiments demonstrate that LDPP outperforms existing methods on two proactive scenarios, even surpassing ChatGPT with only a 1.8-billion-parameter LLM. Our codes are available at xxx.

Simulation-Free Hierarchical Latent Policy Planning for Proactive Dialogues

Temporal pattern matching tasks require the detection of situations of interest based on streams of symbolic events. The Run-Time Event Calculus (RTEC) is a formal framework that represents situations of interest as time-varying properties called 'fluents'. Temporal patterns often express 'Boolean combinations' of situations; RTEC features two types of fluents that may model such patterns: 'simple' and 'statically determined'. A simple fluent representation, however, is exponentially larger and more expensive to reason with than the corresponding statically determined fluent one. We formally identify the class of simple fluent definitions that can be translated into statically determined fluent definitions. Moreover, we present a compiler for the translation, and a reproducible empirical evaluation on real applications.

Temporal Specification Optimisation for the Event Calculus

Prosody contains rich information beyond literal words, which is crucial for the intelligibility of speech. Current models still fall short in phrasing and intonation; they not only miss or misplace breaks when synthesizing long sentences with complex structures but also produce unnatural intonation. We propose ProsodyFM, a Prosody-aware text-to-speech synthesis (TTS) model with a flow-matching (FM) backbone that aims to enhance the phrasing and intonation aspects of prosody. ProsodyFM introduces two key components: a Phrase Break Encoder to capture initial phrase break cues, followed by a duration predictor to realize flexible adjustment of break durations; and a Terminal Intonation Encoder which integrates a set of intonation shape tokens combined with a novel pitch processor for more robust modeling of human-perceived intonation change. ProsodyFM is trained with no explicit prosodic labels and yet can uncover a broad spectrum of break duration and intonation patterns. Experimental results demonstrate that ProsodyFM can effectively improve the phrasing and intonation aspects of prosody, thereby enhancing the overall intelligibility compared to four state-of-the-art (SOTA) models. Out-of-distribution experiments show that this prosody improvement can further bring ProsodyFM superior generalizability for unseen complex sentences and speakers. Our case study intuitively illustrates the powerful and fine-grained controllability of ProsodyFM over phrasing and intonation. Our demo and code are available at {https://anonymous.4open.science/r/Demo-586C}.

ProsodyFM: Unsupervised Phrasing and Intonation Control for Intelligible Speech Synthesis

Image-goal navigation aims to steer an agent toward goal location specified by an image. Most prior methods tackle this task by learning a navigation policy, which extracts visual representation of goal and observation images, compares their similarity and predicts actions. However, if the agent is in different rooms or has large pose variation from the goal image, it is extremely challenging to identify their similarity, which may result in the agent wandering around. Intuitively, when humans carry out this task, they may first roughly compare the current observation with the goal image, having an approximate concept of whether they are in the same room. Inspired by this intuition, we try to imitate the human behaviour and propose a Room Expert Guided Image-Goal Navigation model (REGNav) to equip the agent with the ability of analyzing whether goal and observation images are taken in the same room. Specifically, we first pre-train a room expert with unsupervised learning technique on the self-collected unlabelled room images. The expert, composed of room style embedding network and room relation network, can extract the room style representation of image pairs and obtain their relationship about whether they belong to the same room. Two different fusion approaches are explored to efficiently guide the agent navigation with the room relation knowledge. As a result, our proposed REGNav can successfully navigate to the goal location in a more efficient way. Extensive experiments show that our REGNav surpasses prior state-of-the-art works on three popular benchmarks (e.g., Gibson, MP3D, and HM3D).

REGNav: Room Expert Guided Image-Goal Navigation

This paper studies continual learning (CL) of text classification tasks with a pre-trained language model (LM). In particular, it focuses on the class incremental learning (CIL) setting of CL. Many CIL methods have been proposed to leverage an LM via various types of fine-tuning or adaptation, but they are still prone to catastrophic forgetting (CF). This paper proposes a novel method, called Kernel Linear Discriminant Analysis (KLDA).  It only exploits the latent feature representations extracted from an LM for CIL. However, directly using LM features is sub-optimal. KLDA employs the Radial Basis Function (RBF) kernel to enhance the features from the LM to capture non-linear relationships in the features, resulting in improved accuracy. As the kernel matrix is impractical to build for CIL due to its huge size and the incremental learning nature of CIL, we approximate it using Random Fourier Features (RFF). When a new task arrives, KLDA computes the class mean of each class in the task and updates a shared covariance matrix for all classes learned so far based on the kernelized features. Linear Discriminant Analysis is employed for classification. Our experiments show that KLDA significantly outperforms existing methods. Remarkably, it achieves an accuracy level comparable to that of joint training all classes together, which is considered the upper bound for CIL performance, without using any replay data.

Continual Learning Using a Kernel-Based Method Over Foundation Models

Functional Magnetic Resonance Image (fMRI) is commonly employed to study human brain activity, since it offers insight into the relationship between functional fluctuations and human behavior. To enhance analysis and comprehension of brain activity, Graph Neural Networks (GNNs) have been widely applied to the analysis of functional connectivities (FC) derived from fMRI data, due to their ability to capture the synergistic interactions among brain regions. However, in the human brain, performing complex tasks typically involves the activation of certain \textit{pathways}, which could be represented as paths across graphs. As such, conventional GNNs struggle to learn from these pathways due to the long-range dependencies of multiple pathways. To address these challenges, we introduce a novel framework \textbf{BrainMAP} to learn multiple pathways in brain networks. BrainMAP leverages sequential models to identify long-range correlations among sequentialized brain regions and incorporates an aggregation module based on Mixture of Experts (MoE) to learn from multiple pathways. Our comprehensive experiments highlight BrainMAP's superior performance. Furthermore, our framework enables explanatory analyses of crucial brain regions involved in tasks.

BrainMAP: Learning Multiple Activation Pathways in Brain Networks

It is well known that numeric planning can be made decidable if the domain of all numeric state variables is finite, and that this bounded formulation can be polynomially compiled into classical planning with Boolean conditions and conditional effects, while preserving the plan size exactly. However, whether this compilation has any practical use remains unknown. To explore this aspect, this work revisits the theoretical compilation framework from a practical perspective, focusing on the fragment of simple numeric planning. Specifically, we introduce three different compilations. The first, called \emph{onehot}, aims to systematise the current practice among planning practitioners of modelling numeric planning through classical planning. The other two, termed \emph{binary} compilations, extend and specialise the logarithmic encoding presented in the literature. Our experimental analysis reveals that the supposedly overkill logarithmic encoding can, surprisingly, be made practical with some representational expedients; the use of axioms is particularly crucial. Furthermore, we identify a class of mild numeric planning problems where a classical planner, i.e., LAMA, when run on the compiled problem, is highly competitive with state-of-the-art numeric planners.

Towards Practical Classical Planning Compilations of Numeric Planning

Deep online cross-modal hashing has gained much attention from researchers recently, as its promising applications with low storage requirement, fast retrieval efficiency and cross modality adaptive, etc. However, there still exists some technical hurdles that hinder its applications, e.g., 1) how to extract the coexistent semantic relevance of cross-modal data, 2) how to achieve competitive performance when handling the real time data streams, 3) how to transfer the knowledge learned from offline to online training in a lightweight manner. To address these problems, this paper proposes a lightweight contrastive distilled hashing (LCDH) for cross-modal retrieval, by innovatively bridging the offline and online cross-modal hashing by similarity matrix approximation in a knowledge distillation framework. Specifically, in the teacher network, LCDH first extracts the cross-modal features by CLIP, which are further fed into an attention module for representation enhancement after feature fusion. Then, the output of the attention module is fed into a FC layer to obtain hash codes for aligning the sizes of similarity matrices for online and offline training. In the student network, LCDH extracts the visual and textual features by lightweight models, and then the features are fed into a FC layer to generate binary codes. Finally, by approximating the similarity matrices, the performance of online hashing in the lightweight student network can be enhanced by the supervision of coexistent semantic relevance that is distilled from the teacher network. Experimental results on three widely used datasets demonstrate that LCDH outperforms some state-of-the-art methods.

Lightweight Contrastive Distilled Hashing for Online Cross-modal Retrieval

We consider committee election of $k \geq 3$ (out of $m \geq k + 1$) candidates, where the voters and the candidates are associated with locations on the real line. Each voter’s cardinal preferences over candidates correspond to her distance to the candidate locations, and each voter’s cardinal preferences over committees is defined as her distance to the nearest candidate elected in the committee. We consider a setting where the true distances and the locations are unknown. We can nevertheless have access to degraded information which consists of an order of candidates for each voter. We investigate the best possible distortion (a worst-case performance criterion) wrt. the social cost achieved by deterministic committee election rules based on ordinal preferences submitted by $n$ voters and few additional distance queries. We show that for any $k \geq 3$, the best possible distortion of any deterministic rule that uses at most $k − 3$ distance queries cannot be bounded by any function of $n$, $m$ and $k$. We present deterministic rules for $k$-committee election with distortion of $O(n)$ with $O(k)$ distance queries and $O(1)$ with $O(k \log n)$ distance queries.

Downloads

Next from AAAI 2025

Augmenting Online Algorithms for Knapsack Problem with Total Weight Information

Similar lecture

Learning to Communicate Locally for Large-Scale Multi-Agent Pathfinding