arXiv subjects

Xing Xie

Publications and source records attributed to Xing Xie.

At least 19 recordsLinked to original sources

arXiv2026

Discrete Diffusion Bridges for Spatiotemporally Aligned Image Translation and Generation

We propose Discrete Diffusion Bridges (DDB), a novel framework designed to resolve the fundamental spatiotemporal misalignment of standard discrete diffusion in image translation and generation. By corrupting data into a pure mask state via a random schedule, the conventional forward process induces a twofold misalignment: spatially, this pure-mask destination entirely discards the rich structural priors of the source image; temporally, the random masking order inherently contradicts the ``easy-first, hard-last'' decoding mechanism used during inference. To address this, DDB constructs a direct and efficient trajectory between domains. Spatially, we introduce a hybrid absorption mechanism that redefines the absorbing state to a stochastic mixture of mask and source tokens, effectively injecting source prior as spatial anchors into the latent space. Temporally, we design an information-guided noise schedule that quantifies semantic variation to prioritize the corruption of high-information regions at earlier timesteps. This ensures the model learns to resolve difficult semantic changes using robust context from invariant regions. Extensive experiments validate the versatility and robustness of our framework across diverse generative paradigms. DDB effectively balances edit alignment with structural fidelity across both text-guided semantic manipulation and pure structural image translation, while inherently complementing text-to-image generation and guaranteeing robust high-quality decoding under extremely low sampling steps. Code and models are available at \href{https://github.com/HKU-HealthAI/DDB}{https://github.com/HKU-HealthAI/DDB}.

cs.CV↗

arXiv2026

CultureConverse: A Multilingual Multi-turn Simulation Harness for Culturally Grounded Assistance in East and Southeast Asia

Current cultural evaluations for large language models (LLMs) often reduce culture to single-turn factual recall via MCQs, failing to capture a common use case: users seeking practical help over multiple turns in culturally grounded scenarios. We introduce CultureConverse, a scalable, multilingual simulation and evaluation harness for culturally grounded assistant dialogue that covers 10 East and Southeast Asian regions, 58 subgroup identities, and 7 domains. Each simulated and evaluated episode produces a scored interaction where the assistant assists the user and infers cultural constraints from partial information. The resulting CultureConverse-DS dataset contains 14,610 benchmark (evaluation) episodes and 274,295 oracle-guided (gold-mode) dialogues. In our benchmark evaluation of 18 models, GPT-5 mini achieves the highest assistance quality. Human annotation experiments suggest that our evaluation framework is a sufficient proxy for human judgment. Performance gains from fine-tuning on 27,860 high-quality CultureConverse-DS samples improve in-domain assistance and transfer out-of-domain to cultural MCQ and safety classification benchmarks. We release the harness, both splits, and judge prompts to support interactive evaluation of cultural competency.

cs.CL↗

arXiv2026

Preference Data Selection for Mitigating the Alignment Tax in Large Language Models

Aligning large language models to human preferences is crucial for real-world deployment but frequently incurs an alignment tax, leading to the catastrophic forgetting of pre-trained general capabilities. While previous works primarily frame this problem as an optimization or architectural challenge, the inherent characteristics of preference data that drive this degradation remain largely underexplored. In this paper, we propose BALIGN, a balanced data selection strategy that explicitly mitigates catastrophic forgetting while optimizing alignment efficacy. Through theoretical and empirical analyses of the preference optimization gradient, we identify three key data-centric features that dictate parameter drift: the reference model's log-probability margin, the token length difference between chosen and rejected responses, and the TF-IDF similarity to general capability corpora. By aggregating these orthogonal features into a unified composite risk score, BALIGN systematically filters out high-risk preference samples that disrupt intrinsic model parameters or provide minimal alignment utility. Extensive experiments on standard human preference datasets demonstrate that BALIGN strongly preserves foundational capabilities without compromising alignment gains, consistently achieving the optimal Pareto frontier with minimal computational overhead.

cs.AI↗

arXiv2026

AI-AI co-creation outperforms human pairs in creative tasks

Prior research often finds that AI creativity is limited: single systems rarely outperform humans, and human-AI collaboration does not exceed human output. We argue these conclusions underestimate AI's potential because most studies do not allow iterative, multi-agent exchanges that mirror the social processes underpinning human creativity. We conducted an experiment comparing four conditions: (i) AI-AI co-creation with complementary generator-evaluator roles, (ii) AI-AI co-creation with identical roles, (iii) single-AI creation, and (iv) human-human co-creation. Across three open-ended tasks, 1,212 ideas were rated by trained judges on creativity, novelty, and usefulness. Both AI-AI co-creation conditions consistently outperformed single-AI creation and human pairs on creativity and novelty. Usefulness varied by task: complementary roles yielded the most useful solutions in the broadest and most socially complex task, suggesting role differentiation is advantageous when problems require both imaginative ideation and practical refinement. Human pairs performed worst, consistent with production losses in group creativity. These findings indicate that structured, iterative multi-agent AI co-creation can exceed single-AI and human-human ideation.

cs.CY↗

arXiv2026

$A^2E$ : An End-to-End Agent Auditing Engine

With the rapid advancement of large language models (LLMs), harnesses have become essential infrastructure for deploying agents across a wide range of domains. The fast-evolving harness ecosystem has also made rigorous capability evaluation increasingly important. However, efficiently building an end-to-end, systematic, and comprehensive evaluation pipeline remains a significant challenge. To address this challenge, we introduce $A^2E$ (Agent Auditing Engine), an end-to-end evaluation engine designed for agent harnesses. $A^2E$ leverages our newly proposed Agent Task Protocol (ATP) to enable the rapid integration of evaluation tasks with different harnesses. Through an automatically instrumented Monitor, it captures and generates standardized execution traces during experiments. In the Evaluation stage, $A^2E$ systematically assesses harness capabilities using a suite of multidimensional metrics. Compared with correctness alone, these metrics provide a more fine-grained characterization of differences among harnesses in execution efficiency, tool use, task planning, and error recovery. Experiments conducted with $A^2E$ further reveal that model-harness combinations exhibit substantial performance variation across different types of tasks, and that no single combination consistently outperforms all others across every task. These findings not only demonstrate the necessity of systematic evaluation but also provide useful guidance for the co-evolution of models and harnesses. Our code is available at https://github.com/datamllab/A2E.

cs.AI↗

arXiv2026

Informal Learning Emerges in Everyday Human-LLM Interaction

As LLMs become increasingly capable of completing tasks for users, a central concern is that everyday AI use may become primarily cognitive offloading, eroding the opportunities through which people develop their own capabilities. We analyse large-scale human-LLM conversations to ask whether informal learning behaviors also emerge in this setting: whether users engage in exchanges in ways that preserve opportunities to learn. Across 128,569 naturalistic conversations, we translated learning-science constructs into turn-level behavioural signatures. Cognitive engagement, users' cognitive effort as reflected in the exchange, appeared in 31.9% of 491,685 user turns, whereas constructive engagement, the deepest observable form of learning-oriented engagement, appeared in 4.9%, showing that deeper sense-making was recurrent but selective. Our study further identifies factors associated with these forms of engagement. Scaffolded assistant support consistently marked richer constructive participation, with associations varying by user framing, task ecology, support form, timing and prior user state. Together, these findings show that everyday human-LLM interaction is not only answer delivery or cognitive offloading; it also contains measurable, selective and conditionally organized behavioural signatures of informal learning. They shift AI evaluation from answer-delivery efficiency toward the preservation of cognitive opportunities for users to reason, test ideas and construct understanding in the course of everyday problem-solving.

cs.HC↗

arXiv2026

Learning behavior accounts for background-related advantage in AI-assisted education

Generative AI has been found, and will likely be found increasingly, useful in education. However, existing AI-for-education studies provide inconsistent evidence on its average effects. More broadly, research on prior educational technologies shows that average effects often mask substantial heterogeneity across student populations. Motivated by this evidence, this study examines heterogeneity in students' learning behavior with AI, which students benefit from AI assistance, and how learner profiles and learning behavior shape these patterns. To this end, we recruited 318 university students to participate in structured learning experiments lasting up to 125 minutes. Our findings indicate that students' learning behavior is strongly associated with learning outcomes, with behaviors characterized by proactive and critical engagement, rather than limited engagement, associated with significantly better performance. These behavioral differences are related to learner profiles, with students from higher-ranking universities and those with greater prior knowledge tending to benefit more, consistent with their greater likelihood of adopting proactive interaction strategies. Accounting for learning behavior substantially weakens or eliminates the associations between learner profiles and learning outcomes, suggesting that how students use AI is a key pathway through which background differences are linked to learning gains. Overall, this work provides a deeper understanding of AI assistance in education by showing how differences in learner profiles and learning behavior shape who benefits from AI-supported learning. These insights can help educators and students better navigate and integrate AI into educational practices.

cs.HC↗

arXiv2026

Multi-agent AI systems outperform human teams in creativity

Although artificial intelligence (AI) now matches or exceeds human performance across numerous cognitive tasks, creativity remains a highly contested frontier. As AI systems based on large language models (LLMs) are increasingly adopted in research and innovation, it is essential to understand and augment their creativity. Here we demonstrate that multi-agent LLM teams not only surpass single agents, but also substantially outperform human teams in creativity (Cohen's d=1.50) across 4,541 multi-agent LLM ideas and 341 human-team ideas on six diverse problem-solving tasks. This advantage is driven by novelty while maintaining comparable usefulness. To investigate the generative processes in both groups, we represent conversations as paths through semantic space using neural language model representations. Both LLM and human teams produce more creative ideas when conversations range widely rather than staying centered on a single theme (low global coherence). However, the additional patterns that predict creativity differ: LLM teams benefit from efficient exploration (high semantic spread, shorter paths), while human teams benefit from maintaining smooth conversational flow (high local coherence, frequent pivots). Additionally, we identify model choice and discussion structure as orthogonal design levers that together explain 26.8% of variance in LLM conversational dynamics, paving the way for systematic approaches to developing multi-agent systems with augmented creative capabilities.

cs.CL↗

arXiv2026

PersonaArena: Dynamic Simulation for Evaluating and Enhancing Persona-Level Role-Playing in Large Language Models

Large language models (LLMs) increasingly serve as interactive social agents, yet their ability to maintain coherent and authentic persona-level role-playing remains limited, particularly in realistic social scenarios. Existing research predominantly focuses on character-level settings and relies on static evaluation formats, failing to capture the complexity of everyday social interactions. In this work, we present PersonaArena, a dynamic simulation framework for evaluating and improving persona-level role-playing in LLMs. PersonaArena leverages a large, filtered corpus of user-generated social content to construct a nuanced persona bank, and elicits multi-turn, context-rich interactions within simulated social environments. Our framework features a multi-agent debating judge for holistic and unbiased assessment. Through extensive experiments, we demonstrate that PersonaArena enables rigorous evaluation and enhancement of LLMs' role-playing capabilities, advancing the development of more authentic and socially adept AI agents.

cs.AI↗

arXiv2026

Does Theory of Mind Improvement Really Benefit Human-AI Interactions? Empirical Findings from Interactive Evaluations

Improving the Theory of Mind (ToM) capability of Large Language Models (LLMs) is crucial for effective social interactions between these AI models and humans. However, the existing benchmarks often measure ToM capability improvement through story-reading, multiple-choice questions from a third-person perspective, while ignoring the first-person, dynamic, and open-ended nature of human-AI (HAI) interactions. To directly examine how ToM improvement techniques benefit HAI interactions, we first proposed the new paradigm of interactive ToM evaluation with both perspective and metric shifts. Next, following the paradigm, we conducted a systematic study of four representative ToM enhancement techniques using both four real-world datasets and a user study, covering both goal-oriented tasks (e.g., coding, math) and experience-oriented tasks (e.g., counseling). Our findings reveal that improvements on static benchmarks do not always translate to better performance in dynamic HAI interactions. This paper offers critical insights into ToM evaluation, showing the necessity of interaction-based assessments in developing next-generation, socially aware LLMs for HAI symbiosis.

cs.AI↗

arXiv2026

Can Persona-Prompted LLMs Emulate Subgroup Values? An Empirical Analysis of Generalisability and Fairness in Cultural Alignment

Despite their global prevalence, many Large Language Models (LLMs) are aligned to a monolithic, often Western-centric set of values. This paper investigates the more challenging task of fine-grained value alignment: examining whether LLMs can emulate the distinct cultural values of demographic subgroups. Using Singapore as a case study and the World Values Survey (WVS), we examine the value landscape and show that even state-of-the-art models like GPT-4.1 achieve only 57.4% accuracy in predicting subgroup modal preferences. We construct a dataset of over 20,000 samples to train and evaluate a range of models. We demonstrate that simple fine-tuning on structured numerical preferences yields substantial gains, improving accuracy on unseen, out-of-distribution subgroups by an average of 17.4%. These gains partially transfer to open-ended generation. However, we find significant pre-existing performance biases, where models better emulate young, male, Chinese, and Christian personas. Furthermore, while fine-tuning improves average performance, it widens the disparity between subgroups when measured by distance-aware metrics. Our work offers insights into the limits and fairness implications of subgroup-level cultural alignment.

cs.CY↗

arXiv2026

Human Values Matter: Investigating How Misalignment Shapes Collective Behaviors in LLM Agent Communities

As LLMs become increasingly integrated into human society, evaluating their orientations on human values from social science has drawn growing attention. Nevertheless, it is still unclear why human values matter for LLMs, especially in LLM-based multi-agent systems, where group-level failures may accumulate from individually misaligned actions. We ask whether misalignment with human values alters the collective behavior of LLM agents and what changes it induces? In this work, we introduce CIVA, a controlled multi-agent environment grounded in social science theories, where LLM agents form a community and autonomously communicate, explore, and compete for resources, enabling systematic manipulation of value prevalence and behavioral analysis. Through comprehensive simulation experiments, we reveal three key findings. (1) We identify several structurally critical values that substantially shape the community's collective dynamics, including those diverging from LLMs' original orientations. Triggered by the misspecification of these values, we (2) detect system failure modes, e.g., catastrophic collapse, at the macro level, and (3) observe emergent behaviors like deception and power-seeking at the micro level. These results offer quantitative evidence that human values are essential for collective outcomes in LLMs and motivate future multi-agent value alignment.

cs.CL↗

arXiv2026

Distributional Open-Ended Evaluation of LLM Cultural Value Alignment Based on Value Codebook

As LLMs are globally deployed, aligning their cultural value orientations is critical for safety and user engagement. However, existing benchmarks face the Construct-Composition-Context ($C^3$) challenge: relying on discriminative, multiple-choice formats that probe value knowledge rather than true orientations, overlook subcultural heterogeneity, and mismatch with real-world open-ended generation. We introduce DOVE, a distributional evaluation framework that directly compares human-written text distributions with LLM-generated outputs. DOVE utilizes a rate-distortion variational optimization objective to construct a compact value codebook from 10K documents, mapping text into a structured value space to filter semantic noise. Alignment is measured using unbalanced optimal transport, capturing intra-cultural distributional structures and subgroup diversity. Experiments across 12 LLMs show that DOVE achieves superior predictive validity, attaining a 31.56% correlation with downstream tasks, while maintaining high reliability with as few as 500 samples per culture.

cs.CL↗

arXiv2026

Does LLM Alignment Really Need Diversity? An Empirical Study of Adapting RLVR Methods for Moral Reasoning

Reinforcement learning with verifiable rewards (RLVR) has achieved remarkable success in logical reasoning tasks, yet whether large language model (LLM) alignment requires fundamentally different approaches remains unclear. Given the apparent tolerance for multiple valid responses in moral reasoning, a natural hypothesis is that alignment tasks inherently require diversity-seeking distribution-matching algorithms rather than reward-maximizing policy-based methods. We conduct the first comprehensive empirical study comparing both paradigms on MoReBench. To enable stable RLVR training, we build a rubric-grounded reward pipeline by training a Qwen3-1.7B judge model. Contrary to our hypothesis, we find that distribution-matching approaches do not demonstrate significant advantages over reward-maximizing methods as expected on alignment tasks. Through semantic visualization mapping high-reward responses to semantic space, we demonstrate that moral reasoning exhibits more concentrated high-reward distributions than mathematical reasoning, where diverse solution strategies yield similarly high rewards. This counter-intuitive finding explains why mode-seeking optimization proves equally or more effective for alignment tasks. Our results suggest that alignment tasks do not inherently require diversity-preserving algorithms, and standard reward-maximizing RLVR methods can effectively transfer to moral reasoning without explicit diversity mechanisms.

cs.AI↗

arXiv2026

Social-R1: Towards Human-like Social Reasoning in LLMs

While large language models demonstrate remarkable capabilities across numerous domains, social intelligence - the capacity to perceive social cues, infer mental states, and generate appropriate responses - remains a critical challenge, particularly for enabling effective human-AI collaboration and developing AI that truly serves human needs. Current models often rely on superficial patterns rather than genuine social reasoning. We argue that cultivating human-like social intelligence requires training with challenging cases that resist shortcut solutions. To this end, we introduce ToMBench-Hard, an adversarial benchmark designed to provide hard training examples for social reasoning. Building on this, we propose Social-R1, a reinforcement learning framework that aligns model reasoning with human cognition through multi-dimensional rewards. Unlike outcome-based RL, Social-R1 supervises the entire reasoning process, enforcing structural alignment, logical integrity, and information density. Results show that our approach enables a 4B parameter model to surpass much larger counterparts and generalize robustly across eight diverse benchmarks. These findings demonstrate that challenging training cases with trajectory-level alignment offer a path toward efficient and reliable social intelligence.

cs.AI↗

arXiv2026

From Passive Consumption to Active Interaction: Exploring Interactive LLM Scaffolding to Support Learning Engagement

Large Language Models (LLMs) are increasingly used as learning companions, providing scaffolded explanations, hints, or step-by-step guidance. However, in current LLM-based learning scenarios, scaffolded content is primarily consumed passively, offering limited support for active learner engagement. Learning science research suggests that effective educational scaffolding depends not only on what support is provided, but also on how learners engage with it. In this work, we explore whether embedding lightweight interactive components into LLM-generated scaffolding responses can promote learning-oriented engagement and improve short-term learning outcomes. We evaluated this approach through a within-subjects laboratory study (N=8). Results provide initial evidence that interactive scaffolding increases learners' perceived engagement and attentional focus, while supporting short-term learning performance. We conclude with design implications for integrating interaction into LLM-generated scaffolding to support active learning engagement.

cs.HC↗

arXiv2026

Visuospatial Perspective Taking in Multimodal Language Models

As multimodal language models (MLMs) are increasingly used in social and collaborative settings, it is crucial to evaluate their perspective-taking abilities. Existing benchmarks largely rely on text-based vignettes or static scene understanding, leaving visuospatial perspective-taking (VPT) underexplored. We adapt two evaluation tasks from human studies: the Director Task, assessing VPT in a referential communication paradigm, and the Rotating Figure Task, probing perspective-taking across angular disparities. Across tasks, MLMs show pronounced deficits in Level 2 VPT, which requires inhibiting one's own perspective to adopt another's. These results expose critical limitations in current MLMs' ability to represent and reason about alternative perspectives, with implications for their use in collaborative contexts.

cs.CL↗

arXiv2026

Contextualized Privacy Defense for LLM Agents

LLM agents increasingly act on users' personal information, yet existing privacy defenses remain limited in both design and adaptability. Most prior approaches rely on static or passive defenses, such as prompting and guarding. These paradigms are insufficient for supporting contextual, proactive privacy decisions in multi-step agent execution. We propose Contextualized Defense Instructing (CDI), a new privacy defense paradigm in which an instructor model generates step-specific, context-aware privacy guidance during execution, proactively shaping actions rather than merely constraining or vetoing them. Crucially, CDI is paired with an experience-driven optimization framework that trains the instructor via reinforcement learning (RL), where we convert failure trajectories with privacy violations into learning environments. We formalize baseline defenses and CDI as distinct intervention points in a canonical agent loop, and compare their privacy-helpfulness trade-offs within a unified simulation framework. Results show that our CDI consistently achieves a better balance between privacy preservation (94.2%) and helpfulness (80.6%) than baselines, with superior robustness to adversarial conditions and generalization.

cs.CR↗