Singapore

Critical thinking is essential for building robust AI systems, preventing them from blindly accepting flawed data or biased reasoning.
However, prior work has primarily focused on passive critical thinking, where models simply reject problematic queries without taking constructive steps to address user requests.
In this work, we introduce proactive critical thinking, a paradigm where models actively seek missing or clarifying information from users to resolve their queries better.
To evaluate this capability, we present GSM-MC and GSM-MCE, two novel benchmarks based on GSM8K for assessing mathematical reasoning under incomplete or misleading conditions.
GSM-MC contains 1,368 math problems with a key variable deliberately removed, requiring models to identify and request the missing information.
GSM-MCE further increases the difficulty by introducing irrelevant details to test robustness against distractions.
Experiments on Qwen3 and Llama series models show that, while these models excel in traditional reasoning tasks due to extensive post-training and inference-time scaling, they struggle with proactive critical thinking, especially smaller ones.
However, we demonstrate that reinforcement learning (RL) can significantly improve this ability. Using our enhanced RL algorithm, we achieve substantial gains, boosting the Qwen3-1.7B&#39;s accuracy from 0.15\% to 73.98\% on GSM-MC.
Our data and code will be released upon acceptance. We hope this work advances models that collaborate more effectively with users in problem-solving through proactive critical thinking.

AAAI 2026

Beyond Passive Critical Thinking: Fostering Proactive Questioning to Enhance Human-AI Collaboration

(large) language models

human-ai collaboration

conversational ai

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/)

AAAI 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.



Critical thinking is essential for building robust AI systems, preventing them from blindly accepting flawed data or biased reasoning.
However, prior work has primarily focused on passive critical thinking, where models simply reject problematic queries without taking constructive steps to address user requests.
In this work, we introduce proactive critical thinking, a paradigm where models actively seek missing or clarifying information from users to resolve their queries better.
To evaluate this capability, we present GSM-MC and GSM-MCE, two novel benchmarks based on GSM8K for assessing mathematical reasoning under incomplete or misleading conditions.
GSM-MC contains 1,368 math problems with a key variable deliberately removed, requiring models to identify and request the missing information.
GSM-MCE further increases the difficulty by introducing irrelevant details to test robustness against distractions.
Experiments on Qwen3 and Llama series models show that, while these models excel in traditional reasoning tasks due to extensive post-training and inference-time scaling, they struggle with proactive critical thinking, especially smaller ones.
However, we demonstrate that reinforcement learning (RL) can significantly improve this ability. Using our enhanced RL algorithm, we achieve substantial gains, boosting the Qwen3-1.7B's accuracy from 0.15\% to 73.98\% on GSM-MC.
Our data and code will be released upon acceptance. We hope this work advances models that collaborate more effectively with users in problem-solving through proactive critical thinking.

poster

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.

We challenge the assumption that complex instruction-guided segmentation tasks necessitate equally complex and explicit supervision. This paper introduces RISE (Reasoning via Implicit Self-supervised Emergence), a framework that learns intricate compositional reasoning, spanning spatial relations to world knowledge, without a single ground-truth mask. To achieve this, RISE employs reinforcement learning with GRPO guided by a single, strikingly simple reward: the semantic alignment score between the textual instruction and the predicted image region. Our primary discovery is the implicit emergence of a high-quality chain-of-thought process from this minimalist signal. Within a structured format, the model autonomously learns to understand instructions by accessing its latent knowledge, inferring spatial relationships—capabilities inherent in its architecture but unlocked by our simple objective. Remarkably, our emergent reasoning yields highly competitive results: RISE achieves 58.7 gIoU on the ReasonSeg benchmark, on par with methods using geometric rewards. Furthermore, we show extreme data efficiency: a variant trained on only 2,000 ImageNet-label pairs establishes a new state-of-the-art for annotation-free referring segmentation with 73.7 cIoU on RefCOCO, drastically outperforming prior work (46.5).

Reasoning via Implicit Self-supervised Emergence for Instruction Segmentation

Monocular 3D Visual Grounding (Mono3DVG) is an emerging task that locates 3D objects in RGB images using text descriptions with geometric cues. However, existing methods face two key limitations. Firstly, they often over-rely on high-certainty keywords that explicitly identify the target object while neglecting critical spatial descriptions. Secondly, generalized textual features contain both 2D and 3D descriptive information, thereby capturing an additional dimension of details compared to singular 2D or 3D visual features. This characteristic leads to cross-dimensional interference when refining visual features under text guidance. To overcome these challenges, we propose Mono3DVG-EnSD, a novel framework that integrates two key components: the CLIP-Guided Lexical Certainty Adapter (CLIP-LCA) and the Dimension-Decoupled Module (D2M). The CLIP-LCA dynamically masks high-certainty keywords while retaining low-certainty implicit spatial descriptions, thereby forcing the model to develop a deeper understanding of spatial relationships in captions for object localization. Meanwhile, the D2M decouples dimension-specific (2D/3D) textual features from generalized textual features to guide corresponding visual features at same dimension, which mitigates cross-dimensional interference by ensuring dimensionally-consistent cross-modal interactions. Through comprehensive comparisons and ablation studies on the Mono3DRefer dataset, our method achieves state-of-the-art (SOTA) performance across all metrics. Notably, it improves the challenging Far(Acc@0.5) scenario by a significant +13.54\%.

Mono3DVG-EnSD: Enhanced Spatial-aware and Dimension-decoupled Text Encoding for Monocular 3D Visual Grounding

Federated Recommender Systems (FedRecs) leverage federated learning to protect user privacy by retaining data locally.
However, user embeddings in FedRecs often encode sensitive attribute information, rendering them vulnerable to attribute inference attacks. Attribute unlearning has emerged as a promising approach to mitigate this issue. In this paper, we focus on user-level FedRecs, which is a more practical yet challenging setting compared to group-level FedRecs. Adversarial training emerges as the most feasible approach within this context. We identify two key challenges in implementing adversarial training-based attribute unlearning for user-level
FedRecs: i) mitigating training instability caused by user data heterogeneity, and ii) preventing attribute information leakage through gradients. To address these challenges, we propose FedAU$^2$, an attribute unlearning method for user-level FedRecs. For CH1, we propose a adaptive adversarial training strategy, where the training dynamics are adjusted in response to local optimization behavior. For CH2, we propose a dual-stochastic variational autoencoder to perturb the adversarial model, effectively preventing gradient-based information leakage. Extensive experiments on three real-world datasets demonstrate that our proposed FedAU$^2$ achieves superior performance in unlearning effectiveness and recommendation performance compared to existing baselines.

FedAU2: Attribute Unlearning for User-Level Federated Recommender Systems with Adaptive and Robust Adversarial Training

Skill discovery has emerged as a popular route for unsupervised reinforcement learning (URL), offering agents a diverse, reusable set of behaviours learned before any task-specific reward is experienced. However, existing methodologies tend to favour either categorical codes or unimodal skill priors, which simplifies training at the cost of limiting the variety of behaviours they can represent. We introduce \emph{Discovery of Mixture Skills} (DiMS), a URL algorithm that learns a latent Gaussian mixture by training a Gaussian Mixture Variational Autoencoder (GMVAE) in tandem with the unsupervised policy. In DiMS, a hierarchical GMVAE simultaneously discovers clusters of skills, while an auxiliary macro-latent dynamically positions mixture components to prevent mode collapse. A joint loss term combining log-likelihood and curiosity rewards enables simultaneous updates of representation and policy while improving exploration. Experiments on the Unsupervised Reinforcement Learning Benchmark (URLB) show that DiMS consistently outperforms a wide range of state-of-the-art baselines. Ablation studies confirm that the mixture prior is critical to these gains, and that DiMS is robust to alternative exploration bonuses. Overall, our results suggest that Gaussian mixture skill priors offer a compelling foundation for future unsupervised RL.

Discovering Mixture Skills for Unsupervised Reinforcement Learning

Human-Centric Video Generation (HCVG) methods seek to synthesize human videos from multimodal inputs, including text, images, and audio. Existing methods struggle to effectively coordinate these heterogeneous modalities due to two challenges: the scarcity of modality-complete data and the difficulty of jointly modeling triplet conditions without performance degradation. In this work, we present
HuMo, a unified HCVG framework for collaborative multimodal control. For the first challenge, we construct an incomplete-yet-complementary dataset for improved data utilization efficiency and training scalability. For the second challenge, we propose a two-stage progressive multimodal training paradigm with task-specific strategies at each stage. In the first stage, to balance the text-following and subject-preservation abilities, we adopt the minimal-invasive image injection strategy. In the second stage, to enhance audio-visual sync, we propose a focus-by-predicting strategy that implicitly guides the model to associate audio with facial regions. For joint learning of controllabilities across multi-modal inputs, we progressively incorporate the audio-visual sync task, building on previously acquired capabilities. During inference, for flexible and fine-grained multimodal control, we design a stage-adaptive Classifier-Free Guidance
strategy that dynamically adjusts guidance weights across denoising steps. Extensive experimental results demonstrate that HuMo surpasses specialized state-of-the-art methods in sub-tasks, establishing a unified framework for collaborative multimodal-conditioned HCVG. Demo videos can be found in the supplementary materials.

Human-Centric Video Generation via Collaborative Multi-Modal Conditioning

Federated Learning (FL) enables privacy-preserving distributed training but remains vulnerable to backdoor attacks. Attackers can embed malicious trigger-label associations into the global model by participating in the aggregation process. Existing defense methods typically defend against backdoor attacks by detecting and filtering malicious updates that deviate from benign ones. However, we find that these defenses fail under domain skew, where differing feature distributions across clients increase update heterogeneity, making it harder to distinguish malicious updates from benign ones. To address this challenge, we propose $\textbf{DoBlock}$, a novel defense that utilizes an aggregatable domain infuser incapable of embedding malicious associations, through federated training to facilitate cross-domain knowledge sharing. Moreover, DoBlock prevents malicious association propagation by isolating local models from aggregation, as local models remain client-specific and rely solely on local data for training. Experiments on five domain skew datasets (Digits, PACS, VLCS, Office-Caltech10, and DomainNet) show that DoBlock maintains attack success rates below 2.5\%, while achieving the highest main task accuracy, demonstrating superior robustness without sacrificing benign performance.

DoBlock: Blocking Malicious Association Propagation for Backdoor-Robust Federated Learning Under Domain Skew

Unsupervised visible-infrared person re-identification (USVI-ReID) aims to match individuals across visible and infrared cameras without relying on any annotation. Given the significant gap across visible and infrared modality, estimating reliable cross-modality association becomes a major challenge in USVI-ReID. Existing methods usually adopt optimal transport to associate the intra-modality clusters, which is prone to propagating the local cluster errors, and also overlooks global instance-level relations. By mining and attending to the visible-infrared modality bias, this paper focuses on addressing cross-modality learning from two aspects: bias-mitigated global association and modality-invariant representation learning. Motivated by the camera-aware distance rectification in single-modality re-ID, we propose modality-aware Jaccard distance to mitigate the distance bias caused by modality discrepancy, so that more reliable cross-modality associations can be estimated through global clustering. To further improve cross-modality representation learning, a `split-and-contrast' strategy is designed to obtain modality-specific global prototypes. By explicitly aligning these prototypes under global association guidance, modality-invariant yet ID-discriminative representation learning can be achieved. While conceptually simple, our method obtains state-of-the-art performance on benchmark VI-ReID datasets and outperforms existing methods by a significant margin, validating its effectiveness. Code will be available on Github soon.

Modality-Aware Bias Mitigation and Invariance Learning for Unsupervised Visible-Infrared Person Re-Identification

Machine unlearning (MU) aims to remove the influence of specific data from trained models, addressing privacy concerns and ensuring compliance with regulations such as the "right to be forgotten." Evaluating strong unlearning, where the unlearned model is indistinguishable from one retrained without the forgetting data, remains a significant challenge in deep neural networks (DNNs). Common black-box metrics, such as variants of membership inference attacks and accuracy comparisons, primarily assess model outputs but often fail to capture residual information in intermediate layers. To bridge this gap, we introduce the Information Difference Index (IDI), a novel white-box metric inspired by information theory. IDI quantifies retained information in intermediate features by measuring mutual information between those features and the labels to be forgotten, offering a more comprehensive assessment of unlearning efficacy. Our experiments demonstrate that IDI effectively measures the degree of unlearning across various datasets and architectures, providing a reliable tool for evaluating strong unlearning in DNNs.

An Information Theoretic Evaluation Metric for Strong Unlearning

Tree search-based methods have made significant progress in enhancing the code generation capabilities of large language models. However, due to the difficulty in effectively evaluating intermediate algorithmic steps and the inability to locate and timely correct erroneous steps, these methods often generate incorrect code and incur increased computational costs. To tackle these problems, we propose RPM-MCTS, an effective method that utilizes Knowledge-Retrieval as Process Reward Model based on Monte Carlo Tree Search to evaluate intermediate algorithmic steps. By utilizing knowledge base retrieval probabilities, RPM-MCTS avoids the complex process of training process reward models. During the expansion phase, similarity filtering is employed to remove redundant nodes, ensuring diversity in reasoning paths. Furthermore, our method utilizes sandbox execution feedback to locate erroneous algorithmic steps during generation, enabling timely and targeted corrections. Extensive experiments on four public code generation benchmarks demonstrate that RPM-MCTS outperforms current state-of-the-art methods while achieving an approximately 15% reduction in token consumption. Furthermore, full fine-tuning the base model using data constructed by RPM-MCTS significantly enhances its code capabilities.

RPM-MCTS: Knowledge-Retrieval as Process Reward Model with Monte Carlo Tree Search for Code Generation

Efficient Multimodal Large Language Models (MLLMs) compress vision tokens to reduce resource consumption, but the loss of visual information can degrade comprehension capabilities.
While Knowledge Distillation could enhance student models through teacher guidance, existing methods overlook the fundamental differences in fine-grained vision comprehension caused by unbalanced vision tokens.
In this paper, we propose EM-KD, a novel paradigm that enhances the Efficient MLLM with Knowledge Distillation.
Firstly, we calculate the Mahattan distance between the vision logits of teacher and student, and align them in the spatial dimension with the Hungarian algorithm to solve the imbalance issue.
After alignment, EM-KD introduces two key designs: 1) Vision-Language Affinity Distillation and 2) Vision-Semantic Distillation.
Specifically, we calculate the affinity matrix between text tokens and aligned vision tokens, and minimize the smooth L1 distance of the student and the teacher affinity matrices.
Considering the semantic richness of vision logits in the final layer, we employ the reverse KL divergence to measure the discrete probability distributions of the aligned vision logits over the vocabulary space.
Comprehensive evaluation on diverse benchmarks demonstrates that EM-KD trained model outperforms prior Efficient MLLMs on accuracy and efficiency, validating its effectiveness.

Downloads

Next from AAAI 2026

Reasoning via Implicit Self-supervised Emergence for Instruction Segmentation

Similar lecture

AI Reasoning and System 2 Thinking