Singapore

Web agents, like OpenAI&#39;s Operator and Google&#39;s Project Mariner, are powerful agentic systems pushing the boundaries of Large Language Models (LLM). They can autonomously interact with the internet at the user&#39;s behest, such as navigating websites, filling search masks, and comparing price lists. Though web agent research is thriving, induced sustainability issues remain largely unexplored. To highlight the urgency of this issue, we provide an initial exploration of the energy and CO₂ cost associated with web agents from both a theoretical —via estimation— and an empirical perspective —by benchmarking. Our results show how different philosophies in web agent creation can severely impact the associated expended energy, and that more energy consumed does not necessarily equate to better results. We highlight a lack of transparency regarding disclosing model parameters and processes used for some web agents as a limiting factor when estimating energy consumption. Our work contributes towards a change in thinking of how we evaluate web agents, advocating for dedicated metrics measuring energy consumption in benchmarks.

AAAI 2026

Promoting Sustainable Web Agents: Benchmarking and Estimating Energy Consumption Through Empirical and Theoretical Analysis

Web agents, like OpenAI's Operator and Google's Project Mariner, are powerful agentic systems pushing the boundaries of Large Language Models (LLM). They can autonomously interact with the internet at the user's behest, such as navigating websites, filling search masks, and comparing price lists. Though web agent research is thriving, induced sustainability issues remain largely unexplored. To highlight the urgency of this issue, we provide an initial exploration of the energy and CO₂ cost associated with web agents from both a theoretical —via estimation— and an empirical perspective —by benchmarking. Our results show how different philosophies in web agent creation can severely impact the associated expended energy, and that more energy consumed does not necessarily equate to better results. We highlight a lack of transparency regarding disclosing model parameters and processes used for some web agents as a limiting factor when estimating energy consumption. Our work contributes towards a change in thinking of how we evaluate web agents, advocating for dedicated metrics measuring energy consumption in benchmarks.

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.<br><br>

To access this event page, you need to log in with the **email address you registered with**. <br>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

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.

Music editing is an important step in music production, which has broad applications, including game development and film production. Most existing zero-shot text-guided editing methods rely on pretrained diffusion models by involving forward-backward diffusion processes. However, these methods often struggle to maintain the music content. Additionally, text instructions alone usually fail to accurately describe the desired music. In this paper, we propose two music editing methods that enhance the consistency between the original and edited music by leveraging score distillation. The first method, _SteerMusic_, is a coarse-grained zero-shot editing approach using delta denoising score. The second method, _SteerMusic+_, enables fine-grained personalized music editing by manipulating a concept token that represents a user-defined musical style. _SteerMusic+_ allows for the editing of music into any user-defined musical styles that cannot be achieved by the text instructions alone. Experimental results show that our methods outperform existing approaches in preserving both music content consistency and editing fidelity. User studies further validate that our methods achieve superior music editing quality. Demonstrations and implementation codes are available in our supplementary materials.

SteerMusic: Enhanced Musical Consistency for Zero-shot Text-Guided and Personalized Music Editing

Recent advances in medical multi-modal models focus on specialized image analysis like dermatology, pathology, or radiology. However, they do not fully capture the complexity of real-world clinical diagnostics, which involve heterogeneous inputs and require ongoing contextual understanding during patient-physician interactions.
To bridge this gap, we introduce PulseMind, a new family of multi-modal diagnostic models that integrates a systematically curated dataset, a comprehensive evaluation benchmark, and a tailored training framework. Specifically, we first construct a diagnostic dataset, MediScope, which comprises 98,000 real-world multi-turn consultations and 601,500 medical images, spanning over 10 major clinical departments and more than 200 sub-specialties. Then, to better reflect the requirements of real-world clinical diagnosis, we develop the PulseMind Benchmark, a multi-turn diagnostic consultation benchmark with a four-dimensional evaluation protocol comprising proactiveness, accuracy, usefulness, and language quality. Finally, we design a training framework tailored for multi-modal clinical diagnostics, centered around a core component named Comparison-based Reinforcement Policy Optimization (CRPO). Compared to absolute score rewards, CRPO uses relative preference signals from multi-dimensional comparisons to provide stable and human-aligned training guidance. Extensive experiments demonstrate that PulseMind achieves competitive performance on both the diagnostic consultation benchmark and public medical benchmarks.

PulseMind: A Multi-Modal Medical Model for Real-World Clinical Diagnosis

Recently, the River Method was introduced as novel refinement of the Split Cycle voting rule. The decision-making process of River is closely related to the well established Ranked Pairs Method. Both methods consider a margin graph computed from the voters' preferences and eliminate majority cycles in that graph to choose a winner. As ties can occur in the margin graph, a tiebreaker is required along with the preferences. While such a tiebreaker makes the computation efficient, it compromises the fundamental property of neutrality: the voting rule should not favor alternatives in advance.

One way to reintroduce neutrality is to use Parallel-Universe Tiebreaking (PUT), where each alternative is a winner if it wins according to any possible tiebreaker. Unfortunately, computing the winners selected by Ranked Pairs with PUT is NP-complete. Given the similarity of River to Ranked Pairs, one might expect River to suffer from the same complexity.

Surprisingly, we show the opposite: We present a polynomial-time algorithm for computing River winners with PUT, highlighting significant structural advantages of River over Ranked Pairs. Our Fused-Universe (FUN) algorithm simulates River for every possible tiebreaking in one pass. From the resulting FUN diagram one can then directly read off both the set of winners and, for each winner, a certificate that explains how this alternative dominates the others.

Cost-Free Neutrality for the River Method

Spatial representation learning is essential for GeoAI applications such as urban analytics, enabling the encoding of shapes, locations, and spatial relationships (topological and distance-based) of geo-entities like points, polylines, and polygons.
Existing methods either target a single geo-entity type or, like Poly2Vec, decompose entities into simpler components to enable Fourier transformation, introducing high computational cost. Moreover, since the transformed space lacks geometric alignment, these methods rely on uniform, non-adaptive sampling, which blurs fine-grained features like edges and boundaries.
To address these limitations, we introduce Geo2Vec, a novel method inspired by signed distance fields (SDF) that operates directly in the original space. Geo2Vec adaptively samples points and encodes their signed distances (positive outside, negative inside), capturing geometry without decomposition. A neural network trained to approximate the SDF produces compact, geometry-aware, and unified representations for all geo-entity types. Additionally, we propose a rotation-invariant positional encoding to model high-frequency spatial variations and construct a structured and robust embedding space for downstream GeoAI models. Empirical results show that Geo2Vec consistently outperforms existing methods in representing shape and location, capturing topological and distance relationships, and achieving greater efficiency in real-world GeoAI applications.

Geo2Vec: Shape- and Distance-Aware Neural Representation of Geospatial Entities

We tackle the challenge of generating the infinitely extendable 3D world -- large, continuous environments with coherent geometry and realistic appearance. Existing methods face key challenges: 2D-lifting approaches suffer from geometric and appearance inconsistencies across views, 3D implicit representations are hard to scale up, and current 3D foundation models are mostly object-centric, limiting their applicability to scene-level generation. Our key insight is leveraging strong generation priors from pre-trained 3D models for structured scene block generation. To this end, we propose WorldGrow, a hierarchical framework for unbounded 3D scene synthesis. Our method features three core components: (1) a data curation pipeline that extracts high-quality scene blocks for training, making the 3D structured latent representations suitable for scene generation; (2) a 3D block inpainting mechanism that enables context-aware scene extension; and (3) a coarse-to-fine generation strategy that ensures both global layout plausibility and local geometric/textural fidelity. Evaluated on the large-scale 3D-FRONT dataset, WorldGrow achieves SOTA performance in geometry reconstruction, while uniquely supporting infinite scene generation with photorealistic and structurally consistent outputs. These results highlight its capability for constructing large-scale virtual environments and potential for building future world models.

WorldGrow: Generating Infinite 3D World

Contribution evaluation is essential for incentivizing high-quality data sharing in federated learning (FL), yet existing Shapley-value-based methods are prohibitively expensive and overlook temporal influence propagation. In this paper, we propose Ripple Shapley, a novel attribution framework that enables accurate, real-time data valuation within a single federated training run. Our method decomposes each sample’s impact into an instantaneous drop term and a recursive ripple term, the latter capturing downstream influence via a Jacobian chain over global updates. To scale computation, we introduce a low-rank approximation of the Jacobian product and construct a shared subspace for efficient ripple accumulation. Extensive experiments on CIFAR-10 and MNIST show that Ripple Shapley achieves up to 62× speedup over existing Shapley-based FL methods while maintaining high attribution fidelity, significantly improving efficiency, robustness, and fairness in federated environments. We further demonstrate its effectiveness in dynamic federated learning scenarios and its potential for real-time data pricing.

Ripple Shapley: Data Influence Attribution in One Federated Training Run

The demand for long-context processing in large language models (LLMs) continues to escalate alongside rapid advancements in their capabilities. However, the intermediate attention keys and values (KV cache) employed to avoid re-computations, also grow linearly with sequence length, far exceeding the memory capacity of consumer-grade GPUs. Consequently, many studies have proposed KV cache compression methods that evict unimportant tokens based on variant attention scoring strategies. These methods typically retain the KV pairs of the top-k scoring tokens under a fixed memory budget. However, they still face several limitations. First, they disregard the activation frequency of tokens, specifically the count of times tokens achieve top-k scores in the attention distribution of following tokens. The methods based on variant attention scores may incorrectly evict some high-activation-frequency yet low final-scoring tokens. Second, the activation frequency exhibits different distribution patterns across layers and tasks. Neglecting these differences negatively impacts model performance and task adaptability. Our analysis of the actual token activation frequency and its unique characteristics across layers and task types reveals potential opportunities to address these issues. In this paper, we propose HitKV, which employs hit rates to directly characterize token activation frequencies, enabling adaptive layer-aware and task-aware KV cache eviction under the uniform memory allocation strategies. Also, HitKV can be easily integrated into layer-specific memory allocation methods. Experimental results demonstrate that HitKV maintains model performance with preserving only 3\% of the KV cache, achieves high-quality generation outputs in long-text generations tasks, and delivers $4\times$ throughput improvement over baselines.

HitKV: Activation Frequency Knows Which Tokens Are Important

Adversarial patch attacks pose a significant threat to visual systems. While current patch purification-based defense methods enhance core metrics of visual perception models, they overlook the critical issue of false positive patches, severely compromising image usability. This paper reveals the inadequacy of existing evaluations for adversarial patch defenses, and pioneers a multidimensional adversarial patch localization evaluation framework, which comprehensively quantifies false positives, recall capability, and overall localization accuracy, providing a novel perspective for comparative analysis within the field. Furthermore, building upon the observation that false positives stem from a lack of semantic understanding, we propose a Semantic-Aware Training-free Explainable Defense method (SATED). SATED achieves zero-shot patch localization, false detection correction, and decision explanation by constructing a patch reasoning chain, while simultaneously performing integrated text-guided patch inpainting. Extensive experiments across digital and physical scenarios, detection and segmentation tasks, and diverse adversarial patches, demonstrate that our method significantly reduces false positives and doubles the overall patch localization accuracy, boosting both the generalizability and explainability of the defense. Our code will be released upon acceptance.

False Positives Matter: Multidimensional Localization Evaluation and Training-Free Explainable Adversarial Patch Defense

Despite being successful in board games and reinforcement learning (RL),
Monte-Carlo Tree Search (MCTS) combined with Multi-Armed Bandit (MAB)
has seen limited success in domain-independent classical planning until recently.
Previous work [Wissow and Asai, 2024] showed that UCB1, designed for bounded rewards, does not perform well
as applied to cost-to-go estimates in classical planning, because cost-to-go estimates are unbounded,
and showed improved performance using a Gaussian reward MAB instead.
This paper further sharpens our understanding of ideal bandits for planning tasks.
Existing work has two issues:
first, Gaussian MABs under-specify the support of cost-to-go estimates as $(-\infty,\infty)$,
which we can narrow down.
Second, Full-Bellman backup [Schulte and Keller, 2014]
that backpropagates sample max/min lacks theoretical justification.
We use \emph{Peaks-Over-Threashold Extreme Value Theory} to resolve both issues at once,
propose a new bandit algorithm (UCB1-Uniform).
We formally prove its regret bound and
empirically demonstrate its performance in classical planning.

Extreme Value Monte Carlo Tree Search for Classical Planning

Recent breakthroughs in Large Language Models (LLMs) have positioned them as a promising paradigm for agents, with long-term planning and decision-making emerging as core general-purpose capabilities for adapting to diverse scenarios and tasks. Real-time strategy (RTS) games serve as an ideal testbed for evaluating these two capabilities, as their inherent gameplay requires both macro-level strategic planning and micro-level tactical adaptation and action execution. Existing RTS game-based environments either suffer from relatively high computational demands or lack support for textual observations, which has constrained the use of RTS games for LLM evaluation. Motivated by this, we present TowerMind, a novel environment grounded in the tower defense (TD) subgenre of RTS games. TowerMind preserves the key evaluation strengths of RTS games for assessing LLMs, while featuring low computational demands and a multimodal observation space, including pixel-based, textual, and structured game-state representations. In addition, TowerMind supports the evaluation of model hallucination and provides a high degree of customizability. We design five benchmark levels to evaluate several widely used LLMs under different multimodal input settings. The results reveal a clear performance gap between LLMs and human experts across both capability and hallucination dimensions. The experiments further highlight key limitations in LLM behavior, such as inadequate planning validation, a lack of multifinality in decision-making, and inefficient action use. We also evaluate two classic reinforcement learning algorithms: Ape-X DQN and PPO. By offering a lightweight and multimodal design, TowerMind complements the existing RTS game-based environment landscape and introduces a new benchmark for the AI agent field.

Downloads

Next from AAAI 2026

SteerMusic: Enhanced Musical Consistency for Zero-shot Text-Guided and Personalized Music Editing

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES