Singapore

The spatial reasoning task aims to reason about the spatial relationships in 2D and 3D space, which is a fundamental capability for Visual Question Answering (VQA) and robotics. Although vision language models (VLMs) have developed rapidly in recent years, they are still struggling with the spatial reasoning task. In this paper, we introduce a method that can enhance Spatial reasoning through Visual and Textual thinking Simultaneously (SpatialVTS). In the spatial visual thinking phase, our model is trained to generate location-related specific tokens of important targets automatically. Not only are the objects mentioned in the problem addressed, but also the potential objects related to the reasoning are considered. During the spatial textual thinking phase, our model conducts long-term thinking based on visual cues and dialogues and gradually inferences the answers to spatial reasoning problems. To effectively support the model&#39;s training, we made manual corrections to the existing spatial reasoning dataset, eliminating numerous incorrect labels resulting from automatic annotation, restructuring the data input format to enhance generalization, and developing a reasoning framework for model thinking. Without introducing any additional information (such as masks or depth), our model&#39;s overall average level in several spatial understanding tasks has significantly improved compared with other models.

AAAI 2026

Enhancing Spatial Reasoning Through Visual and Textual Thinking

chain-of-visual-thoughts

multimodal llm

visual language model

spatial reasoning

### Welcome!
The 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024) will take place in Bangkok, Thailand from August 11th to 16th, 2024. Our Virtual Poster Sessions will take place online Thursday, August 22, 2024.

You are required to register for this event. **Please register [here](https://2024.aclweb.org/registration). **

If you have already registered, please check your inbox for an email from Underline granting you access to ACL 2024 content.

Please register!

ACL 2024

The 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024) will take place in Bangkok, Thailand from August 11th to 16th, 2024. More information will be announced soon.

The spatial reasoning task aims to reason about the spatial relationships in 2D and 3D space, which is a fundamental capability for Visual Question Answering (VQA) and robotics. Although vision language models (VLMs) have developed rapidly in recent years, they are still struggling with the spatial reasoning task. In this paper, we introduce a method that can enhance Spatial reasoning through Visual and Textual thinking Simultaneously (SpatialVTS). In the spatial visual thinking phase, our model is trained to generate location-related specific tokens of important targets automatically. Not only are the objects mentioned in the problem addressed, but also the potential objects related to the reasoning are considered. During the spatial textual thinking phase, our model conducts long-term thinking based on visual cues and dialogues and gradually inferences the answers to spatial reasoning problems. To effectively support the model's training, we made manual corrections to the existing spatial reasoning dataset, eliminating numerous incorrect labels resulting from automatic annotation, restructuring the data input format to enhance generalization, and developing a reasoning framework for model thinking. Without introducing any additional information (such as masks or depth), our model's overall average level in several spatial understanding tasks has significantly improved compared with other models.

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 

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.

Large language models (LLMs) demonstrate strong reasoning
capabilities, yet the inference-time performance of
existing solutions remains limited by self-biases,
coordination inefficiencies, lack of robust error
detection, and dependency on high-quality verifiers. To
address these challenges, we propose Adaptive Coopetition
(AdCo), a lightweight, multi-agent multi-round
inference-time framework that enhances collective reasoning
through adaptive decision-making guided by coarse verifier
signals. Without relying on high-performance verifiers,
AdCo achieves a 20% relative accuracy improvement on math
reasoning benchmarks, with consistent performance on
different sample sizes and agent configurations. This
adaptive, signal-guided ‘coopetition’ framework (Tran et
al. 2025) enhances reasoning robustness by leveraging
diverse model knowledge and reasoning traces, while also
promoting uncertainty-driven exploration, especially when
participants have comparable capabilities.

Adaptive Coopetition: Leveraging Coarse Verifier Signals for Resilient Multi-Agent LLM Reasoning (Student Abstract)

This study presents a physics-informed neural network
framework to model droplet spreading dynamics on
unstructured rough surfaces, using training data generated
from high-fidelity lattice Boltzmann method simulations.
The droplet is represented by phase-field density field,
where interface evolution is governed by multiphase flow
physics, surface tension, and wall wettability effects.
Unlike conventional data-driven models, the PINN
incorporates the underlying physi-
cal laws such as mass and momentum conservation directly
into the loss function, enabling accurate prediction even
with the sparse data. The trained model successfully
captures the droplet dynamics over different time periods,
contact line evolution, and interfacial deformation across
time, showing high accuracy as compared with the CNNs. This
PINN-based surrogate offers a comutationally efficient,
mesh-free alternatives to traditional solvers, making it
ideal for rapid parametric studies and design optimized
microfluidic devices and wettability-controlled systems.

Learning Droplet Dynamics on Rough Unstructured Surfaces Using Physics-Informed Neural Networks (Student Abstract)

Agentic workflows, where multiple AI agents collaborate to
accomplish complex tasks like reasoning or planning, play a
substantial role in many cutting-edge commercial
applications. These workflows depend critically on the
prompts used to provide the roles models play in such
workflows. Poorly designed prompts that fail even slightly
to guide individual agents can lead to sub-optimal
performance that may snowball within a system of agents,
limiting their reliability and scalability. To address this
important problem of inference-time prompt optimization, we
introduce ProRefine, an innovative inference-time
optimization method that uses an agentic loop of LLMs to
generate and apply textual feedback. ProRefine dynamically
refines prompts for multi-step reasoning tasks without
additional training or ground truth labels. Evaluated on
five benchmark mathematical reasoning datasets, ProRefine
significantly surpasses zero-shot Chain-of-Thought
baselines by 3 to 37 percentage points. This approach not
only boosts accuracy but also allows smaller models to
approach the performance of their larger counterparts. This
highlights its potential for building cost-effective and
powerful hybrid AI systems, thereby democratizing access to
high-performing AI.

ProRefine: Inference-Time Prompt Refinement with Textual Feedback (Student Abstract)

Quantitative remote sensing estimation is critical for environmental monitoring, providing continuous measures of vegetation indices, canopy height, and carbon stock. Traditional radiative-transfer models and empirical regressions require expert knowledge and generalize poorly, while deep learning methods remain task-specific. We propose SatelliteCalculator+, a DINOv3-powered multi-task foundation model for continuous regression of spectral and structural variables. The framework combines prompt-driven cross-attentive adapters with lightweight MLP decoders, enabling efficient dense prediction from frozen features. To overcome limited supervision, we synthesize over one million paired samples from SPOT 6/7 imagery using physically defined formulas. On the Open-Canopy dataset, SatelliteCalculator+ achieves competitive accuracy across eight ecological variables while reducing inference cost, demonstrating the promise of self-supervised transformers and scalable multi-task learning for large-scale Earth observation.

DINOv3-Powered Multi-Task Foundation Model for Quantitative Remote Sensing Estimation (Student Abstract)

This paper bridges two perspectives: it studies the multi-secretary problem through the fairness lens of social choice, and examines multi-winner elections from the viewpoint of online decision making. After identifying the limitations of the prominent proportionality notion of Extended Justified Representation (EJR) in the online domain, the work proposes a set of mechanisms that merge techniques from online algorithms with rules from social choice---such as the Method of Equal Shares and the Nash Rule---and supports them through both theoretical analysis and extensive experimental evaluation.

Fairness in the Multi-Secretary Problem

Neural coupling is a fundamental mechanism in neuroscience that facilitates the emergence of cognitive functions through dynamic interactions and synchronization among distributed brain regions. Inspired by this principle, we pose the question: Might the biological mechanism of neural oscillatory synchronization inspire the feature representation learning for neuroscience? By addressing this question through the Kuramoto model, renowned for simulating oscillatory dynamics, we present a novel physics-informed deep model, `SyncBrain`, it models brain regions as interacting oscillatory units and simulates their temporal dynamics and synchronization patterns to distinguish cognitive states. Furthermore, inspired by the brain's inherent ability to dynamically attend to critical temporal information, we incorporate an adaptive control module that introduces an attention-like mechanism to guide information flow. We evaluate our model on multiple functional neuroimaging datasets, it demonstrates promising performance and enhanced interpretability in both cognitive state decoding and early disease diagnosis, outperforming existing computational methods. These results demonstrate the effectiveness of neural oscillatory mechanisms in shaping robust and interpretable machine learning models for neuroscience applications.

SyncBrain: Exploring Brain Functional Dynamics Through Neural Oscillatory Synchronization

Vietnamese exhibits extensive dialectal variation, posing challenges for NLP systems trained predominantly on standard Vietnamese. Such systems often underperform on dialectal inputs, especially from underrepresented Central and Southern regions. Previous work on dialect normalization has focused narrowly on Central-to-Northern dialect transfer using synthetic data and limited dialectal diversity. These efforts exclude Southern varieties and intra-regional variants within the North. We introduce ViDia2Std, the first manually annotated parallel corpus for dialect-to-standard Vietnamese translation covering all 63 provinces. Unlike prior datasets, ViDia2Std includes diverse dialects from Central, Southern, and non-standard Northern regions often absent from existing resources, making it the most dialectally inclusive corpus to date. The dataset consists of over 13,000 sentence pairs sourced from real-world Facebook comments and annotated by native speakers across all three dialect regions. To assess annotation consistency, we define a semantic mapping agreement metric that accounts for synonymous standard mappings across annotators. Based on this criterion, we report agreement rates of 86% (North), 82% (Central), and 85% (South). We benchmark several sequence-to-sequence models on ViDia2Std. mBART-large-50 achieves the best results (BLEU 0.7801, ROUGE-L 0.9285, METEOR 0.8689), while ViT5-base offers competitive performance with fewer parameters. ViDia2Std demonstrates that dialect normalization substantially improves downstream tasks, highlighting the need for dialect-aware resources in building robust Vietnamese NLP systems.

ViDia2Std: A Parallel Corpus and Methods for Low-Resource Vietnamese Dialect-to-Standard Translation

Alignment of large language models (LLMs) with human preferences typically relies on supervised reward models or external judges, which in turn require abundant preference data. We propose a generative preference modeling approach for low-resource and domain-specific scenarios, reframing preference learning as an inverse reinforcement learning problem. Instead of training a discriminative reward model, we train the LLM itself to infer and maximize an implicit reward function underlying high-quality reasoning. Specifically, we leverage Chain-of-Thought (CoT) sampling to generate diverse candidate solutions for each query and refine fine-grained preferences from these without additional human labels. We also introduce an entropy-guided token scoring mechanism to rank and weight the sampled CoTs, boosting the importance of high-confidence answers and strategically high-entropy tokens. Building on this, we train the model with our Self-Evaluated Group Advantage (SEGA) algorithm. Compared with other methods, this algorithm efficiently utilizes the fine-grained preference information in group candidate solutions to update the strategy. Our method eliminates dependence on external judges or reward classifiers, instead relying on the generative model’s own judgments. Experiments on general benchmarks and domain-specific tasks—such as mathematical reasoning and medical question answering—demonstrate that our generative preference model achieves significant improvements with limited data.

GEM: Generative Entropy-Guided Preference Modeling for Few-Shot Alignment of LLMs

Agents are rapidly advancing in automating digital work, but enterprises face a harder challenge: moving beyond prototypes to deployed systems that deliver measurable business value. This path is complicated by fragmented frameworks, slow development, and the absence of standardized evaluation practices. Generalist agents have emerged as a promising direction, excelling on academic benchmarks and offering flexibility across task types, applications, and modalities. Yet, evidence of their deployment in production enterprise settings is still limited. This paper reports IBM’s experience developing and deploying the \textbf{Computer Using Generalist Agent (CUGA)}. CUGA adopts a hierarchical planner--executor architecture with strong analytical foundations, achieving state-of-the-art performance on AppWorld and WebArena. Beyond benchmarks, it was deployed in the Business-Process-Outsourcing talent acquisition domain, meeting enterprise requirements for scalability, auditability, safety, and governance. To support evaluation, we introduce \textbf{BPO-TA}, a 26-task benchmark spanning 13 analytics endpoints. In deployment, CUGA matched the accuracy of specialized agents while reducing development time by 91.9\% and cost by 52.3\%. Our contribution is twofold: demonstrating generalist agents operating at enterprise scale, and distilling technical and organizational lessons from this deployment. We outline requirements and next steps for advancing research-grade architectures like CUGA into robust, enterprise-ready systems.

From Benchmarks to Business Impact: Deploying IBM Generalist Agent in Enterprise Production

Explanation generation frameworks aim to make AI systems’ decisions transparent and understandable to human users. However, generating explanations in uncertain environments characterized by incomplete information and probabilistic models remains a significant challenge. In this paper, we propose a novel framework for generating probabilistic monolithic explanations and model reconciling explanations. Monolithic explanations provide self-contained reasons for an explanandum without considering the agent receiving the explanation, while model reconciling explanations account for the knowledge of the agent receiving the explanation. For monolithic explanations, our approach integrates uncertainty by utilizing probabilistic logic to increase the probability of the explanandum. For model reconciling explanations, we propose a framework that extends the logic-based variant of the model reconciliation problem to account for probabilistic human models, where the goal is to find explanations that increase the probability of the explanandum while minimizing conflicts between the explanation and the probabilistic human model. We introduce explanatory gain and explanatory power as quantitative metrics to assess the quality of these explanations. Further, we present algorithms that exploit the duality between minimal correction sets and minimal unsatisfiable sets to efficiently compute both types of explanations in probabilistic contexts. Extensive experimental evaluations on various benchmarks demonstrate the effectiveness and scalability of our approach in generating explanations under uncertainty.

Downloads

Next from AAAI 2026

Adaptive Coopetition: Leveraging Coarse Verifier Signals for Resilient Multi-Agent LLM Reasoning (Student Abstract)

Similar lecture

SpaRC and SpaRP: Spatial Reasoning Characterization and Path Generation for Understanding Spatial Reasoning Capability of Large Language Models

.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

Adaptive Coopetition: Leveraging Coarse Verifier Signals for Resilient Multi-Agent LLM Reasoning (Student Abstract)

Similar lecture

SpaRC and SpaRP: Spatial Reasoning Characterization and Path Generation for Understanding Spatial Reasoning Capability of Large Language Models

Downloads