arXiv subjects

Xing Xie

Publications and source records attributed to Xing Xie.

At least 37 records · Page 2Linked to original sources

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

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

CAReDiO: Cultural Alignment via Representativeness and Distinctiveness Guided Data Optimization

As Large Language Models (LLMs) are deployed across diverse regions, aligning them with pluralistic cultures is crucial for improving user engagement and mitigating cultural conflicts. Recent work has curated, either synthesized or manually annotated, culture-specific corpora for alignment. Nevertheless, inspired by cultural theories, we recognize they face two key challenges. (1) Representativeness: These corpora inadequately capture the target culture's core characteristics, causing insufficient cultural coverage and redundancy; (2) Distinctiveness: They fail to distinguish the unique nuances of the target culture from patterns shared across relevant ones, hindering precise culture modeling. To handle these challenges, we introduce CAReDiO, a novel data optimization framework that alternately optimizes culture-sensitive questions and responses according to two information-theoretic objectives in an in-context manner, enhancing both cultural representativeness and distinctiveness of constructed data. Extensive experiments on 15 cultures demonstrate that CAReDiO can create high-quality data with richer cultural information and enable efficient alignment of small open-source or large proprietary LLMs with as few as 200 training samples, consistently outperforming previous datasets in both multi-choice and open-ended benchmarks.

cs.CL↗

arXiv2026

AdAEM: An Adaptively and Automated Extensible Measurement of LLMs' Value Difference

Assessing Large Language Models'(LLMs) underlying value differences enables comprehensive comparison of their misalignment, cultural adaptability, and biases. Nevertheless, current value measurement methods face the informativeness challenge: with often outdated, contaminated, or generic test questions, they can only capture the orientations on comment safety values, e.g., HHH, shared among different LLMs, leading to indistinguishable and uninformative results. To address this problem, we introduce AdAEM, a novel, self-extensible evaluation algorithm for revealing LLMs' inclinations. Distinct from static benchmarks, AdAEM automatically and adaptively generates and extends its test questions. This is achieved by probing the internal value boundaries of a diverse set of LLMs developed across cultures and time periods in an in-context optimization manner. Such a process theoretically maximizes an information-theoretic objective to extract diverse controversial topics that can provide more distinguishable and informative insights about models' value differences. In this way, AdAEM is able to co-evolve with the development of LLMs, consistently tracking their value dynamics. We use AdAEM to generate novel questions and conduct an extensive analysis, demonstrating our method's validity and effectiveness, laying the groundwork for better interdisciplinary research on LLMs' values and alignment. Codes and the generated evaluation questions are released at https://github.com/ValueCompass/AdAEM.

cs.CY↗

arXiv2026

To Think or Not To Think, That is The Question for Large Reasoning Models in Theory of Mind Tasks

Theory of Mind (ToM) assesses whether models can infer hidden mental states such as beliefs, desires, and intentions, which is essential for natural social interaction. Although recent progress in Large Reasoning Models (LRMs) has boosted step-by-step inference in mathematics and coding, it is still underexplored whether this benefit transfers to socio-cognitive skills. We present a systematic study of nine advanced Large Language Models (LLMs), comparing reasoning models with non-reasoning models on three representative ToM benchmarks. The results show that reasoning models do not consistently outperform non-reasoning models and sometimes perform worse. A fine-grained analysis reveals three insights. First, slow thinking collapses: accuracy significantly drops as responses grow longer, and larger reasoning budgets hurt performance. Second, moderate and adaptive reasoning benefits performance: constraining reasoning length mitigates failure, while distinct success patterns demonstrate the necessity of dynamic adaptation. Third, option matching shortcut: when multiple choice options are removed, reasoning models improve markedly, indicating reliance on option matching rather than genuine deduction. We also design two intervention approaches: Slow-to-Fast (S2F) adaptive reasoning and Think-to-Match (T2M) shortcut prevention to further verify and mitigate the problems. With all results, our study highlights the advancement of LRMs in formal reasoning (e.g., math, code) cannot be fully transferred to ToM, a typical task in social reasoning. We conclude that achieving robust ToM requires developing unique capabilities beyond existing reasoning methods.

cs.AI↗

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↗

arXiv2026

Harnessing Temporal Databases for Systematic Evaluation of Factual Time-Sensitive Question-Answering in Large Language Models

Facts change over time, making it essential for Large Language Models (LLMs) to handle time-sensitive factual knowledge accurately and reliably. Although factual Time-Sensitive Question-Answering (TSQA) tasks have been widely developed, existing benchmarks often face manual bottlenecks that limit scalable and comprehensive TSQA evaluation. To address this issue, we propose TDBench, a new benchmark that systematically constructs TSQA pairs by harnessing temporal databases and database techniques, such as temporal functional dependencies, temporal SQL, and temporal joins. We also introduce a new evaluation metric called time accuracy, which assesses the validity of time references in model explanations alongside traditional answer accuracy for a more fine-grained TSQA evaluation. Extensive experiments on contemporary LLMs show how TDBench enables scalable and comprehensive TSQA evaluation while reducing the reliance on human labor, complementing current TSQA evaluation approaches that largely center on Wikipedia/Wikidata by enabling LLM evaluation on application-specific data.

cs.CL↗

arXiv2026

Interaction-Augmented Instruction: Modeling the Synergy of Prompts and Interactions in Human-GenAI Collaboration

Text prompt is the most common way for human-generative AI (GenAI) communication. Though convenient, it is challenging to convey fine-grained and referential intent. One promising solution is to combine text prompts with precise GUI interactions, like brushing and clicking. However, there lacks a formal model to capture synergistic designs between prompts and interactions, hindering their comparison and innovation. To fill this gap, via an iterative and deductive process, we develop the Interaction-Augmented Instruction (IAI) model, a compact entity-relation graph formalizing how the combination of interactions and text prompts enhances human-GenAI communication. With the model, we distill twelve recurring and composable atomic interaction paradigms from prior tools, verifying our model's capability to facilitate systematic design characterization and comparison. Four usage scenarios further demonstrate the model's utility in applying, refining, and innovating these paradigms. These results illustrate the IAI model's descriptive, discriminative, and generative power for shaping future GenAI systems.

cs.HC↗

arXiv2026

Research Superalignment Should Advance Now with Alternating Competence and Conformity Optimization

The recent leap in AI capabilities, driven by big generative models, has sparked the possibility of achieving Artificial General Intelligence (AGI) and further triggered discussions on Artificial Superintelligence (ASI)-a system surpassing all humans across measured domains. This gives rise to the critical research question of: As we approach ASI, how do we align it with human values, ensuring it benefits rather than harms human society, a.k.a., the Superalignment problem. Despite ASI being regarded by many as a hypothetical concept, in this position paper, we argue that superalignment is achievable and research on it should advance immediately, through simultaneous and alternating optimization of task competence and value conformity. We posit that superalignment is not merely a safeguard for ASI but also necessary for its responsible realization. To support this position, we first provide a formal definition of superalignment rooted in the gap between capability and capacity, delve into its perceived infeasibility by analyzing the limitations of existing paradigms, and then illustrate a conceptual path of superalignment to support its achievability, centered on two fundamental principles. This work frames a potential initiative for developing value-aligned next-generation AI in the future, which will garner greater benefits and reduce potential harm to humanity.

cs.AI↗

arXiv2026

How Do Human Creators Embrace Human-AI Co-Creation? A Perspective on Human Agency of Screenwriters

Generative AI has greatly transformed creative work in various domains, such as screenwriting. To understand this transformation, prior research often focused on capturing a snapshot of human-AI co-creation practice at a specific moment, with less attention to how humans mobilize, regulate, and reflect to form the practice gradually. Motivated by Bandura's theory of human agency, we conducted a two-week study with 19 professional screenwriters to investigate how they embraced AI in their creation process. Our findings revealed that screenwriters not only mindfully planned, foresaw, and responded to AI usage, but, more importantly, through reflections on practice, they developed themselves and human-AI co-creation paradigms, such as cognition, strategies, and workflows. They also expressed various expectations for how future AI should better support their agency. Based on our findings, we conclude this paper with extensive discussion and actionable suggestions to screenwriters, tool developers, and researchers for sustainable human-AI co-creation.

cs.HC↗

arXiv2026

DuoDrama: Supporting Screenplay Refinement Through LLM-Assisted Human Reflection

AI has been increasingly integrated into screenwriting practice. In refinement, screenwriters expect AI to provide feedback that supports reflection across the internal perspective of characters and the external perspective of the overall story. However, existing AI tools cannot sufficiently coordinate the two perspectives to meet screenwriters' needs. To address this gap, we present DuoDrama, an AI system that generates feedback to assist screenwriters' reflection in refinement. To enable DuoDrama, based on performance theories and a formative study with nine professional screenwriters, we design the Experience-Grounded Feedback Generation Workflow for Human Reflection (ExReflect). In ExReflect, an AI agent adopts an experience role to generate experience and then shifts to an evaluation role to generate feedback based on the experience. A study with fourteen professional screenwriters shows that DuoDrama improves feedback quality and alignment and enhances the effectiveness, depth, and richness of reflection. We conclude by discussing broader implications and future directions.

cs.HC↗