The rise of Large Language Models (LLMs) has redefined the AI landscape, particularly due to their ability to encode factual and commonsense knowledge, and their outstanding performance in tasks requiring reasoning. Despite these advances, hallucinations and reasoning errors remain a significant barrier to their deployment in high-stakes settings. In this work, we observe that even the most prominent LLMs, such as OpenAI-o1, suffer from high rates of reasoning errors and hallucinations on tasks requiring commonsense reasoning over obscure, long-tail entities. To investigate this limitation, we present a new dataset for Commonsense reasoning over Long-Tail entities (CoLoTa), that consists of 3,300 queries from question answering and claim verification tasks and covers a diverse range of commonsense reasoning skills. We remark that CoLoTa can also serve as a Knowledge Graph Question Answering (KGQA) dataset since the support of knowledge required to answer its queries is present in the Wikidata knowledge graph. However, as opposed to existing KGQA benchmarks that merely focus on factoid questions, our CoLoTa queries also require commonsense reasoning. Our experiments with strong LLM-based KGQA methodologies indicate their severe inability to answer queries involving commonsense reasoning. Hence, we propose CoLoTa as a novel benchmark for assessing both (i) LLM commonsense reasoning capabilities and their robustness to hallucinations on long-tail entities and (ii) the commonsense reasoning capabilities of KGQA methods.

Reasoning over Knowledge Graphs (KGs) plays a pivotal role in knowledge graph completion or question answering systems, providing richer and more accurate triples and attributes. As numerical attributes become increasingly essential in characterizing entities and relations in KGs, the ability to reason over these attributes has gained significant importance. Existing graph-based methods such as Graph Neural Networks (GNNs) and Knowledge Graph Embeddings (KGEs), primarily focus on aggregating homogeneous local neighbors and implicitly embedding diverse triples. However, these approaches often fail to fully leverage the potential of logical paths within the graph, limiting their effectiveness in exploiting the reasoning process. To address these limitations, we propose ChainsFormer, a novel chain-based framework designed to support numerical reasoning. Chainsformer not only explicitly constructs logical chains but also expands the reasoning depth to multiple hops. Specially, we introduces Relation-Attribute Chains (RA-Chains), a specialized logic chain, to model sequential reasoning patterns. ChainsFormer captures the step-by-step nature of multi-hop reasoning along RA-Chains by employing sequential in-context learning. To mitigate the impact of noisy chains, we propose a hyperbolic affinity scoring mechanism that selects relevant logic chains in a variable-resolution space. Furthermore, ChainsFormer incorporates an attention-based numerical reasoner to identify critical reasoning paths, enhancing both reasoning accuracy and transparency. Experimental results demonstrate that ChainsFormer significantly outperforms state-of-the-art methods, achieving up to a 20.0% improvement in performance. The implementations are available at https://github.com/zhaodazhuang2333/ChainsFormer.

Our work aims to advance the social reasoning of embodied artificial intelligence (AI) agents in real-world social interactions. Recently, language models (LMs) and foundational models (FMs) are being utilized as automatic evaluators of human-AI interactions with the goal of eventually being used to improve the policy of the AI agent. To enable further research in this direction, we introduce a large-scale real-world Human Robot Social Interaction (HSRI) Dataset to benchmark the capabilities of LMs and FMs to identify and reason about social interactions, specifically with regard to robot social errors and competencies . Our dataset consists of 400 real-world human social robot interaction videos and over 10K annotations, detailing the robot's social errors, competencies, rationale, and corrective actions, capturing unique aspects of human-AI interaction only present in real-world interactions. To further assess AI models' ability to reason about social interactions, we propose eight new benchmark tasks for evaluating centered around whether AI models can (1) evaluate social interactions via detecting social errors and competencies, (2) identify the explanatory factors associated to errors and competencies, (3) understand the flow of real-world social interactions, and (4) provide reasons and corrective actions for social errors. Human studies and experiments with modern LMs and FMs reveal that current models struggle with these tasks, demonstrating that our dataset and benchmark provides a step forward towards socially intelligent AI.

This work aligns deep learning (DL) with human reasoning capabilities and needs to enable more efficient, interpretable, and robust image classification. We approach this from three perspectives: explainability, causality, and biological vision. Introduction and background open this work before diving into operative chapters. First, we assess neural networks' visualization techniques for medical images and validate an explainable-by-design method for breast mass classification. A comprehensive review at the intersection of XAI and causality follows, where we introduce a general scaffold to organize past and future research, laying the groundwork for our second perspective. In the causality direction, we propose novel modules that exploit feature co-occurrence in medical images, leading to more effective and explainable predictions. We further introduce CROCODILE, a general framework that integrates causal concepts, contrastive learning, feature disentanglement, and prior knowledge to enhance generalization. Lastly, we explore biological vision, examining how humans recognize objects, and propose CoCoReco, a connectivity-inspired network with context-aware attention mechanisms. Overall, our key findings include: (i) simple activation maximization lacks insight for medical imaging DL models; (ii) prototypical-part learning is effective and radiologically aligned; (iii) XAI and causal ML are deeply connected; (iv) weak causal signals can be leveraged without a priori information to improve performance and interpretability; (v) our framework generalizes across medical domains and out-of-distribution data; (vi) incorporating biological circuit motifs improves human-aligned recognition. This work contributes toward human-aligned DL and highlights pathways to bridge the gap between research and clinical adoption, with implications for improved trust, diagnostic accuracy, and safe deployment.

Recent advancements in dialogue policy planning have emphasized optimizing system agent policies to achieve predefined goals, focusing on strategy design, trajectory acquisition, and efficient training paradigms. However, these approaches often overlook the critical role of user characteristics, which are essential in real-world scenarios like conversational search and recommendation, where interactions must adapt to individual user traits such as personality, preferences, and goals. To address this gap, we first conduct a comprehensive study utilizing task-specific user personas to systematically assess dialogue policy planning under diverse user behaviors. By leveraging realistic user profiles for different tasks, our study reveals significant limitations in existing approaches, highlighting the need for user-tailored dialogue policy planning. Building on this foundation, we present the User-Tailored Dialogue Policy Planning (UDP) framework, which incorporates an Intrinsic User World Model to model user traits and feedback. UDP operates in three stages: (1) User Persona Portraying, using a diffusion model to dynamically infer user profiles; (2) User Feedback Anticipating, leveraging a Brownian Bridge-inspired anticipator to predict user reactions; and (3) User-Tailored Policy Planning, integrating these insights to optimize response strategies. To ensure robust performance, we further propose an active learning approach that prioritizes challenging user personas during training. Comprehensive experiments on benchmarks, including collaborative and non-collaborative settings, demonstrate the effectiveness of UDP in learning user-specific dialogue strategies. Results validate the protocol's utility and highlight UDP's robustness, adaptability, and potential to advance user-centric dialogue systems.

In this paper, we introduce a new \emph{process prejudge} strategy in LLM reasoning to demonstrate that bootstrapping with process prejudge allows the LLM to adaptively anticipate the errors encountered when advancing the subsequent reasoning steps, similar to people sometimes pausing to think about what mistakes may occur and how to avoid them, rather than relying solely on trial and error. Specifically, we define a prejudge node in the rationale, which represents a reasoning step, with at least one step that follows the prejudge node that has no paths toward the correct answer. To synthesize the prejudge reasoning process, we present an automated reasoning framework with a dynamic tree-searching strategy. This framework requires only one LLM to perform answer judging, response critiquing, prejudge generation, and thought completion. Furthermore, we develop a two-phase training mechanism with supervised fine-tuning (SFT) and reinforcement learning (RL) to further enhance the reasoning capabilities of LLMs. Experimental results from competition-level complex reasoning demonstrate that our method can teach the model to prejudge before thinking and significantly enhance the reasoning ability of LLMs. Code and data is released at https://github.com/wjn1996/Prejudge-Before-Think.

Recent advances in Multimodal Large Language Models (MLLMs) have achieved remarkable progress in general domains and demonstrated promise in multimodal mathematical reasoning. However, applying MLLMs to geometry problem solving (GPS) remains challenging due to lack of accurate step-by-step solution data and severe hallucinations during reasoning. In this paper, we propose GeoGen, a pipeline that can automatically generates step-wise reasoning paths for geometry diagrams. By leveraging the precise symbolic reasoning, \textbf{GeoGen} produces large-scale, high-quality question-answer pairs. To further enhance the logical reasoning ability of MLLMs, we train \textbf{GeoLogic}, a Large Language Model (LLM) using synthetic data generated by GeoGen. Serving as a bridge between natural language and symbolic systems, GeoLogic enables symbolic tools to help verifying MLLM outputs, making the reasoning process more rigorous and alleviating hallucinations. Experimental results show that our approach consistently improves the performance of MLLMs, achieving remarkable results on benchmarks for geometric reasoning tasks. This improvement stems from our integration of the strengths of LLMs and symbolic systems, which enables a more reliable and interpretable approach for the GPS task. Codes are available at https://github.com/ycpNotFound/GeoGen.

Recent advances leverage post-training to enhance model reasoning performance, which typically requires costly training pipelines and still suffers from inefficient, overly lengthy outputs. We introduce Speculative Thinking, a training-free framework that enables large reasoning models to guide smaller ones during inference at the reasoning level, distinct from speculative decoding, which operates at the token level. Our approach is based on two observations: (1) reasoning-supportive tokens such as "wait" frequently appear after structural delimiters like "\n\n", serving as signals for reflection or continuation; and (2) larger models exhibit stronger control over reflective behavior, reducing unnecessary backtracking while improving reasoning quality. By strategically delegating reflective steps to a more capable model, our method significantly boosts the reasoning accuracy of reasoning models while shortening their output. With the assistance of the 32B reasoning model, the 1.5B model's accuracy on MATH500 increases from 83.2% to 89.4%, marking a substantial improvement of 6.2%. Simultaneously, the average output length is reduced from 5439 tokens to 4583 tokens, representing a 15.7% decrease. Moreover, when applied to a non-reasoning model (Qwen-2.5-7B-Instruct), our framework boosts its accuracy from 74.0% to 81.8% on the same benchmark, achieving a relative improvement of 7.8%.

It can have serious implications in critical application scenarios like that of Knowledge Graph-based multilingual data integration. In view of the above, the thesis argues that the current understanding of the problem of semantic heterogeneity as the'existence of variance', while being crucially necessary, is not sufficient and under-characterized. There can be no variance without a prior notion of a unifying reference taken as the basis for computing the variance itself. To that end, the thesis proposes the problem of representation heterogeneity to emphasize the fact that heterogeneity is an intrinsic property of any representation, wherein, different observers encode different representations of the same target reality in a stratified manner using different concepts, language and knowledge (as well as data). The thesis then advances a top-down solution approach to the above stratified problem of representation heterogeneity in terms of several solution components, namely: (i) a representation formalism stratified into concept level, language level, knowledge level and data level to accommodate representation heterogeneity, (ii) a top-down language representation using Universal Knowledge Core (UKC), UKC namespaces and domain languages to tackle the conceptual and language level heterogeneity, (iii) a top-down knowledge representation using the notions of language teleontology and knowledge teleontology to tackle the knowledge level heterogeneity, (iv) the usage and further development of the existing LiveKnowledge catalog for enforcing iterative reuse and sharing of language and knowledge representations, and, (v) the kTelos methodology integrating the solution components above to iteratively generate the language and knowledge representations absolving representation heterogeneity. The thesis also includes proof-of-concepts of the language and knowledge representations developed for two international research projects - DataScientia (data catalogs) and JIDEP (materials modelling). Finally, the thesis concludes with future lines of research.

This work revisits the dominant supervised fine-tuning (SFT) then reinforcement learning (RL) paradigm for training Large Vision-Language Models (LVLMs), and reveals a key finding: SFT can significantly undermine subsequent RL by inducing ``pseudo reasoning paths'' imitated from expert models. While these paths may resemble the native reasoning paths of RL models, they often involve prolonged, hesitant, less informative steps, and incorrect reasoning. To systematically study this effect, we introduce VLAA-Thinking, a new multimodal dataset designed to support reasoning in LVLMs. Constructed via a six-step pipeline involving captioning, reasoning distillation, answer rewrite and verification, VLAA-Thinking comprises high-quality, step-by-step visual reasoning traces for SFT, along with a more challenging RL split from the same data source. Using this dataset, we conduct extensive experiments comparing SFT, RL and their combinations. Results show that while SFT helps models learn reasoning formats, it often locks aligned models into imitative, rigid reasoning modes that impede further learning. In contrast, building on the Group Relative Policy Optimization (GRPO) with a novel mixed reward module integrating both perception and cognition signals, our RL approach fosters more genuine, adaptive reasoning behavior. Notably, our model VLAA-Thinker, based on Qwen2.5VL 3B, achieves top-1 performance on Open LMM Reasoning Leaderboard (https://huggingface.co/spaces/opencompass/Open_LMM_Reasoning_Leaderboard) among 4B scale LVLMs, surpassing the previous state-of-the-art by 1.8%. We hope our findings provide valuable insights in developing reasoning-capable LVLMs and can inform future research in this area.