Zhicong Lu

Yangbin Yu, Mingyu Yang, Junyou Li et al.

Existing Large Language Model (LLM) agents struggle in interactive environments requiring long-horizon planning, primarily due to compounding errors when simulating future states. To address this, we propose ProAct, a framework that enables agents to internalize accurate lookahead reasoning through a two-stage training paradigm. First, we introduce Grounded LookAhead Distillation (GLAD), where the agent undergoes supervised fine-tuning on trajectories derived from environment-based search. By compressing complex search trees into concise, causal reasoning chains, the agent learns the logic of foresight without the computational overhead of inference-time search. Second, to further refine decision accuracy, we propose the Monte-Carlo Critic (MC-Critic), a plug-and-play auxiliary value estimator designed to enhance policy-gradient algorithms like PPO and GRPO. By leveraging lightweight environment rollouts to calibrate value estimates, MC-Critic provides a low-variance signal that facilitates stable policy optimization without relying on expensive model-based value approximation. Experiments on both stochastic (e.g., 2048) and deterministic (e.g., Sokoban) environments demonstrate that ProAct significantly improves planning accuracy. Notably, a 4B parameter model trained with ProAct outperforms all open-source baselines and rivals state-of-the-art closed-source models, while demonstrating robust generalization to unseen environments. The codes and models are available at https://github.com/GreatX3/ProAct

Qian Wan, Siying Hu, Yu Zhang et al.

Prewriting is the process of discovering and developing ideas before a first draft, which requires divergent thinking and often implies unstructured strategies such as diagramming, outlining, free-writing, etc. Although large language models (LLMs) have been demonstrated to be useful for a variety of tasks including creative writing, little is known about how users would collaborate with LLMs to support prewriting. The preferred collaborative role and initiative of LLMs during such a creativity process is also unclear. To investigate human-LLM collaboration patterns and dynamics during prewriting, we conducted a three-session qualitative study with 15 participants in two creative tasks: story writing and slogan writing. The findings indicated that during collaborative prewriting, there appears to be a three-stage iterative Human-AI Co-creativity process that includes Ideation, Illumination, and Implementation stages. This collaborative process champions the human in a dominant role, in addition to mixed and shifting levels of initiative that exist between humans and LLMs. This research also reports on collaboration breakdowns that occur during this process, user perceptions of using existing LLMs during Human-AI Co-creativity, and discusses design implications to support this co-creativity process.

Lingyao Li, Junjie Xiong, Changjia Zhu et al.

Large language models (LLMs) are increasingly used in academic peer review, yet their reliability, alignment with human judgment, and robustness to adversarial attacks remain poorly understood. We present a systematic benchmark of LLM-as-a-Reviewer on 898 papers stratified from NeurIPS and ICLR, evaluating 12 LLMs along three axes: rating calibration, divergence from human reviewers, and resistance to prompt injection embedded via an invisible font-mapping attack. We find that LLMs systematically overrate weaker submissions and diverge from humans in topical emphasis, under-flagging Clarity and over-flagging Reproducibility, while producing reviews two to three times longer with lower lexical diversity and a more standardized vocabulary. Prompt injection remains highly effective. Simple hidden instructions can promote low-scoring papers to acceptance-level ratings in a substantial fraction of cases, with effectiveness varying sharply across model families. While LLMs offer utility in structuring evaluations, their integration into peer review requires safeguards against both intrinsic biases and adversarial risks.

Zichuan Lin, Feiyu Liu, Yijun Yang et al.

Autonomous mobile GUI agents have attracted increasing attention along with the advancement of Multimodal Large Language Models (MLLMs). However, existing methods still suffer from inefficient learning from failed trajectories and ambiguous credit assignment under sparse rewards for long-horizon GUI tasks. To that end, we propose UI-Voyager, a novel two-stage self-evolving mobile GUI agent. In the first stage, we employ Rejection Fine-Tuning (RFT), which enables the continuous co-evolution of data and models in a fully autonomous loop. The second stage introduces Group Relative Self-Distillation (GRSD), which identifies critical fork points in group rollouts and constructs dense step-level supervision from successful trajectories to correct failed ones. Extensive experiments on AndroidWorld show that our 4B model achieves an 81.0% Pass@1 success rate, outperforming numerous recent baselines and exceeding human-level performance. Ablation and case studies further verify the effectiveness of GRSD. Our method represents a significant leap toward efficient, self-evolving, and high-performance mobile GUI automation without expensive manual data annotation.

Zhicong Lu, Zichuan Lin, Wei Jia et al.

While large language models excel in diverse domains, their performance on complex longhorizon agentic decision-making tasks remains limited. Most existing methods concentrate on designing effective reward models (RMs) to advance performance via multi-turn reinforcement learning. However, they suffer from delayed propagation in sparse outcome rewards and unreliable credit assignment with potentially overly fine-grained and unfocused turnlevel process rewards. In this paper, we propose (HISR) exploiting Hindsight Information to modulate Segmental process Rewards, which closely aligns rewards with sub-goals and underscores significant segments to enhance the reliability of credit assignment. Specifically, a segment-level process RM is presented to assign rewards for each sub-goal in the task, avoiding excessively granular allocation to turns. To emphasize significant segments in the trajectory, a hindsight model is devised to reflect the preference of performing a certain action after knowing the trajectory outcome. With this characteristic, we design the ratios of sequence likelihoods between hindsight and policy model to measure action importance. The ratios are subsequently employed to aggregate segment importance scores, which in turn modulate segmental process rewards, enhancing credit assignment reliability. Extensive experimental results on three publicly benchmarks demonstrate the validity of our method.

Changyuan Tian, Zhicong Lu, Huaxing Liu et al.

Reinforcement learning with verifiable rewards (RLVR) has emerged as a promising paradigm for advancing complex reasoning in large language models, and recent work extends RLVR to multimodal large language models (MLLMs). This transfer, however, surfaces a faithfulness challenge: faithful perception of task-relevant visual evidence and faithful use of that evidence during reasoning, leading to unsatisfactory gains on multimodal benchmarks. Specifically, existing perception supervision often operates on textual descriptions rather than natively on image regions, and faithful use is largely overlooked, exposing the perception-reasoning disconnect where correctly perceived evidence is dropped or contradicted during reasoning. To close these gaps, we propose Faithful-MR1, a training framework that anchors and reinforces visual attention to address both halves of faithful multimodal reasoning. The Anchoring stage turns perception into an explicit pre-reasoning subtask, supervising a dedicated <Focus> token's attention directly against image regions rather than through textual descriptions. The Reinforcing stage exposes faithful use through counterfactual image intervention, rewarding answer-correct trajectories that concentrate visual attention where vision causally matters. Extensive experiments demonstrate that Faithful-MR1 outperforms recent multimodal reasoning baselines on both Qwen2.5-VL-Instruct 3B and 7B backbones while using substantially less training data.

Changyuan Tian, Zhicong Lu, Shuang Qian et al.

To improve Multi-step Mathematical Reasoning (MsMR) of Large Language Models (LLMs), it is crucial to obtain scalable supervision from the corpus by automatically critiquing mistakes in the reasoning process of MsMR and rendering a final verdict of the problem-solution. Most existing methods rely on crafting high-quality supervised fine-tuning demonstrations for critiquing capability enhancement and pay little attention to delving into the underlying reason for the poor critiquing performance of LLMs. In this paper, we orthogonally quantify and investigate the potential reason -- imbalanced evaluation preference, and conduct a statistical preference analysis. Motivated by the analysis of the reason, a novel perplexity-aware reinforcement learning algorithm is proposed to rectify the evaluation preference, elevating the critiquing capability. Specifically, to probe into LLMs' critiquing characteristics, a One-to-many Problem-Solution (OPS) benchmark is meticulously constructed to quantify the behavior difference of LLMs when evaluating the problem solutions generated by itself and others. Then, to investigate the behavior difference in depth, we conduct a statistical preference analysis oriented on perplexity and find an intriguing phenomenon -- ``LLMs incline to judge solutions with lower perplexity as correct'', which is dubbed as \textit{imbalanced evaluation preference}. To rectify this preference, we regard perplexity as the baton in the algorithm of Group Relative Policy Optimization, supporting the LLMs to explore trajectories that judge lower perplexity as wrong and higher perplexity as correct. Extensive experimental results on our built OPS and existing available critic benchmarks demonstrate the validity of our method.

Shiwei Hong, Lingyao Li, Ethan Z. Rong et al.

Prior work has explored multi-turn interaction and feedback for LLM writing, but evaluations still largely center on prompts and localized feedback, leaving persistent public reception in online communities underexamined. We test whether broadcast community discussion improves stand-up comedy writing in a controlled multi-agent sandbox: in the discussion condition, critic and audience threads are recorded, filtered, stored as social memory, and later retrieved to condition subsequent generations, whereas the baseline omits discussion. Across 50 rounds (250 paired monologues) judged by five expert annotators using A/B preference and a 15-item rubric, discussion wins 75.6% of instances and improves Craft/Clarity (Δ = 0.440) and Social Response (Δ = 0.422), with occasional increases in aggressive humor.

Rongyi Chen, Ziyan Xin, Qing Xiao et al.

The digital transformation of religious practice has reshaped how billions of people engage with spiritual content, with video-sharing platforms becoming central to contemporary religious communication. Yet HCI research lacks systematic understanding of how narrative and visual elements create meaningful spiritual experiences and foster viewer engagement. We present a mixed-methods study of religious videos on YouTube across major religions, developing taxonomies of narrative frameworks, visual elements, and viewer interaction. Using LLM-assisted analysis, we studied relationships between content characteristics and viewer responses. Religious videos predominantly adopt lecture-style formats with authority-based persuasion strategies, using salvation narratives for guidance. All prefer bright lighting, with Buddhism favoring warm tones and prominent symbols, Judaism preferring indoor settings, and Hinduism emphasizing sacred objects. We identified differentiated patterns of emotional sharing among religious viewers while revealing significant correlations between content characteristics and engagement, particularly regarding AI-generated content. We provide evidence-based guidance for creating inclusive and engaging spiritual media.

Zhiyang Wu, Junliang Chen, Qian Wan et al.

Equipping laypeople with the capabilities to seek legal information has been an important goal for Legal Empowerment in modern society. However, unlike general information-seeking behaviors, legal information seeking is characterized by high stakes, urgency, and a critical need for emotional support, which traditional text-based searching platforms struggle to satisfy. In recent years, people have been increasingly turning to Video-Sharing Platforms (VSPs) for access to legal information and to fulfill their legal needs. Despite the importance of this shift, such VSP-mediated legal information-seeking practices remain underexplored. Through an observational analysis of legal content on two VSPs (Douyin and Bilibili) and interviews with 20 Chinese information seekers, this study examined the practices and challenges associated with seeking, comprehending, and evaluating legal information on VSPs. We further revealed the formation of trust and engagement on the VSP-based legal knowledge-sharing community, highlighting how VSP affordances helped mitigate seekers' epistemic discomfort and satisfy their needs for emotional support. In the discussion, we provided insights on balancing heuristic and systematic processing to encourage information cross-validation, and offered implications for designing trustworthy civic information systems and fostering an accessible, safe, and efficient information-seeking environment in digital space.

Shihao Yang, Zhicong Lu, Yong Yang et al.

Multi-character role-playing aims to equip models with the capability to simulate diverse roles. Existing methods either use one shared parameterized module across all roles or assign a separate parameterized module to each role. However, the role-shared module may ignore distinct traits of each role, weakening personality learning, while the role-specific module may overlook shared traits across multiple roles, hindering commonality modeling. In this paper, we propose a novel HyCoRA: Hyper-Contrastive Role-Adaptive learning framework, which efficiently improves multi-character role-playing ability by balancing the learning of distinct and shared traits. Specifically, we propose a Hyper-Half Low-Rank Adaptation structure, where one half is a role-specific module generated by a lightweight hyper-network, and the other half is a trainable role-shared module. The role-specific module is devised to represent distinct persona signatures, while the role-shared module serves to capture common traits. Moreover, to better reflect distinct personalities across different roles, we design a hyper-contrastive learning mechanism to help the hyper-network distinguish their unique characteristics. Extensive experimental results on both English and Chinese available benchmarks demonstrate the superiority of our framework. Further GPT-4 evaluations and visual analyses also verify the capability of HyCoRA to capture role characteristics.

Emma Jiren Wang, Siying Hu, Zhicong Lu

As a primary channel for sustaining modern intimate relationships, instant messaging facilitates frequent connection across distances. However, today's tools often dilute care; they favor single tap reactions and vague emojis that do not support two way action responses, do not preserve the feeling that the exchange keeps going without breaking, and are weakly tied to who we are and what we share. To address this challenge, we present PuppetChat, a dyadic messaging prototype that restores this expressive depth through embodied interaction. PuppetChat uses a reciprocity aware recommender to encourage responsive actions and generates personalized micronarratives from user stories to ground interactions in personal history. Our 10-day field study with 11 dyads of close partners or friends revealed that this approach enhanced social presence, supported more expressive self disclosure, and sustained continuity and shared memories.

Qian Wan, Xin Feng, Yining Bei et al.

Human emotions are essentially molded by lived experiences, from which we construct personalised meaning. The engagement in such meaning-making process has been practiced as an intervention in various psychotherapies to promote wellness. Nevertheless, to support recollecting and recounting lived experiences in everyday life remains under explored in HCI. It also remains unknown how technologies such as generative AI models can facilitate the meaning making process, and ultimately support affective mindfulness. In this paper we present Metamorpheus, an affective interface that engages users in a creative visual storytelling of emotional experiences during dreams. Metamorpheus arranges the storyline based on a dream's emotional arc, and provokes self-reflection through the creation of metaphorical images and text depictions. The system provides metaphor suggestions, and generates visual metaphors and text depictions using generative AI models, while users can apply generations to recolour and re-arrange the interface to be visually affective. Our experience-centred evaluation manifests that, by interacting with Metamorpheus, users can recall their dreams in vivid detail, through which they relive and reflect upon their experiences in a meaningful way.

Zihe Ran, Xiyu Li, Qing Xiao et al.

As blind and low-vision (BLV) players engage more deeply with games, accessibility features have become essential. While some research has explored tools and strategies to enhance game accessibility, the specific experiences of these players with mobile games remain underexamined. This study addresses this gap by investigating how BLV users experience mobile games with varying accessibility levels. Through interviews with 32 experienced BLV mobile players, we explore their perceptions, challenges, and strategies for engaging with mobile games. Our findings reveal that BLV players turn to mobile games to alleviate boredom, achieve a sense of accomplishment, and build social connections, but face barriers depending on the game's accessibility level. We also compare mobile games to other forms of gaming, highlighting the relative advantages of mobile games, such as the inherent accessibility of smartphones. This study contributes to understanding BLV mobile gaming experiences and provides insights for enhancing accessible mobile game design.

Haichang Li, Qinshi Zhang, Piaohong Wang et al.

In the human-AI collaboration area, the context formed naturally through multi-turn interactions is typically flattened into a chronological sequence and treated as a fixed whole in subsequent reasoning, with no mechanism for dynamic organization and management along the collaboration workflow. Yet these contexts differ substantially in lifecycle, structural hierarchy, and relevance. For instance, temporary or abandoned exchanges and parallel topic threads persist in the limited context window, causing interference and even conflict. Meanwhile, users are largely limited to influencing context indirectly through input modifications (e.g., corrections, references, or ignoring), leaving their control neither explicit nor verifiable. To address this, we propose Mixed-Initiative Context, which reconceptualizes the context formed across multi-turn interactions as an explicit, structured, and manipulable interactive object. Under this concept, the structure, scope, and content of context can be dynamically organized and adjusted according to task needs, enabling both humans and AI to actively participate in context construction and regulation. To explore this concept, we implement Contextify as a probe system and conduct a user study examining users' context management behaviors, attitudes toward AI initiative, and overall collaboration experience. We conclude by discussing the implications of this concept for the HCI community.

Xianzhe Fan, Qing Xiao, Xuhui Zhou et al. · allen-ai, cmu

AI companions based on large language models can role-play and converse very naturally. When value conflicts arise between the AI companion and the user, it may offend or upset the user. Yet, little research has examined such conflicts. We first conducted a formative study that analyzed 151 user complaints about conflicts with AI companions, providing design implications for our study. Based on these, we created Minion, a technology probe to help users resolve human-AI value conflicts. Minion applies a user-empowerment intervention method that provides suggestions by combining expert-driven and user-driven conflict resolution strategies. We conducted a technology probe study, creating 40 value conflict scenarios on Character.AI and Talkie. 22 participants completed 274 tasks and successfully resolved conflicts 94.16% of the time. We summarize user responses, preferences, and needs in resolving value conflicts, and propose design implications to reduce conflicts and empower users to resolve them more effectively.

Piaohong Wang, Motong Tian, Jiaxian Li et al.

Recent advancements in LLM-powered agents have demonstrated significant potential in generating human-like responses; however, they continue to face challenges in maintaining long-term interactions within complex environments, primarily due to limitations in contextual consistency and dynamic personalization. Existing memory systems often depend on semantic grouping prior to retrieval, which can overlook semantically irrelevant yet critical user information and introduce retrieval noise. In this report, we propose the initial design of O-Mem, a novel memory framework based on active user profiling that dynamically extracts and updates user characteristics and event records from their proactive interactions with agents. O-Mem supports hierarchical retrieval of persona attributes and topic-related context, enabling more adaptive and coherent personalized responses. O-Mem achieves 51.67% on the public LoCoMo benchmark, a nearly 3% improvement upon LangMem,the previous state-of-the-art, and it achieves 62.99% on PERSONAMEM, a 3.5% improvement upon A-Mem,the previous state-of-the-art. O-Mem also boosts token and interaction response time efficiency compared to previous memory frameworks. Our work opens up promising directions for developing efficient and human-like personalized AI assistants in the future.

Siying Hu, Yaxing Yao, Zhicong Lu

Large Language Models are profoundly changing work patterns in high-risk professional domains, yet their application also introduces severe and underexplored compliance risks. To investigate this issue, we conducted semi-structured interviews with 24 highly-skilled knowledge workers from industries such as law, healthcare, and finance. The study found that these experts are commonly concerned about sensitive information leakage, intellectual property infringement, and uncertainty regarding the quality of model outputs. In response, they spontaneously adopt various mitigation strategies, such as actively distorting input data and limiting the details in their prompts. However, the effectiveness of these spontaneous efforts is limited due to a lack of specific compliance guidance and training for Large Language Models. Our research reveals a significant gap between current NLP tools and the actual compliance needs of experts. This paper positions these valuable empirical findings as foundational work for building the next generation of Human-Centered, Compliance-Driven Natural Language Processing for Regulatory Technology (RegTech), providing a critical human-centered perspective and design requirements for engineering NLP systems that can proactively support expert compliance workflows.

Huanchen Wang, Wencheng Zhang, Zhiqiang Wang et al.

Vision-language (VL) models have shown transformative potential across various critical domains due to their capability to comprehend multi-modal information. However, their performance frequently degrades under distribution shifts, making it crucial to assess and improve robustness against real-world data corruption encountered in practical applications. While advancements in VL benchmark datasets and data augmentation (DA) have contributed to robustness evaluation and improvement, there remain challenges due to a lack of in-depth comprehension of model behavior as well as the need for expertise and iterative efforts to explore data patterns. Given the achievement of visualization in explaining complex models and exploring large-scale data, understanding the impact of various data corruption on VL models aligns naturally with a visual analytics approach. To address these challenges, we introduce VisMoDAl, a visual analytics framework designed to evaluate VL model robustness against various corruption types and identify underperformed samples to guide the development of effective DA strategies. Grounded in the literature review and expert discussions, VisMoDAl supports multi-level analysis, ranging from examining performance under specific corruptions to task-driven inspection of model behavior and corresponding data slice. Unlike conventional works, VisMoDAl enables users to reason about the effects of corruption on VL models, facilitating both model behavior understanding and DA strategy formulation. The utility of our system is demonstrated through case studies and quantitative evaluations focused on corruption robustness in the image captioning task.

Franklin Mingzhe Li, Cheng Lu, Zhicong Lu et al.

Deaf and Hard-of-Hearing (DHH) audiences have long complained about caption qualities for many online videos created by individual content creators on video-sharing platforms (e.g., YouTube). However, there lack explorations of practices, challenges, and perceptions of online video captions from the perspectives of both individual content creators and DHH audiences. In this work, we first explore DHH audiences' feedback on and reactions to YouTube video captions through interviews with 13 DHH individuals, and uncover DHH audiences' experiences, challenges, and perceptions on watching videos created by individual content creators (e.g., manually added caption tags could create additional confidence and trust in caption qualities for DHH audiences). We then discover individual content creators' practices, challenges, and perceptions on captioning their videos (e.g., back-captioning problems) by conducting a YouTube video analysis with 189 captioning-related YouTube videos, followed by a survey with 62 individual content creators. Overall, our findings provide an in-depth understanding of captions generated by individual content creators and bridge the knowledge gap mutually between content creators and DHH audiences on captions.

Qunfang Wu, Yisi Sang, Dakuo Wang et al.

Due to the limitations imposed by the COVID-19 pandemic, many users have shifted their shopping patterns from offline to online. Livestream shopping has become popular as one of the online shopping media. However, many streamers' malicious selling behaviors have been reported. In this research, we sought to explore streamers' malicious selling strategies and understand how viewers perceive these strategies. First, we recorded 40 livestream shopping sessions from two popular livestream platforms in China -- Taobao and TikTok (or "Douyin" in Chinese). We identified 16 malicious selling strategies and found that platform designs enhanced these malicious selling strategies. Second, through an interview study with 13 viewers, we provide a rich description of viewers' awareness of malicious selling strategies and the challenges they encountered while trying to overcome malicious selling. We conclude by discussing the policy and design implications of countering malicious selling.

Junshan Wang, Zhicong Lu, Guojie Song et al.

Network embedding is a method to learn low-dimensional representation vectors for nodes in complex networks. In real networks, nodes may have multiple tags but existing methods ignore the abundant semantic and hierarchical information of tags. This information is useful to many network applications and usually very stable. In this paper, we propose a tag representation learning model, Tag2Vec, which mixes nodes and tags into a hybrid network. Firstly, for tag networks, we define semantic distance as the proximity between tags and design a novel strategy, parameterized random walk, to generate context with semantic and hierarchical information of tags adaptively. Then, we propose hyperbolic Skip-gram model to express the complex hierarchical structure better with lower output dimensions. We evaluate our model on the NBER U.S. patent dataset and WordNet dataset. The results show that our model can learn tag representations with rich semantic information and it outperforms other baselines.

Zhicong Lu, Haijun Xia, Seongkook Heo et al.

Despite gaining traction in North America, live streaming has not reached the popularity it has in China, where livestreaming has a tremendous impact on the social behaviors of users. To better understand this socio-technological phenomenon, we conducted a mixed methods study of live streaming practices in China. We present the results of an online survey of 527 live streaming users, focusing on their broadcasting or viewing practices and the experiences they find most engaging. We also interviewed 14 active users to explore their motivations and experiences. Our data revealed the different categories of content that was broadcasted and how varying aspects of this content engaged viewers. We also gained insight into the role reward systems and fan group-chat play in engaging users, while also finding evidence that both viewers and streamers desire deeper channels and mechanisms for interaction in addition to the commenting, gifting, and fan groups that are available today.