arXiv subjects

Juho Kim

Publications and source records attributed to Juho Kim.

At least 19 recordsLinked to original sources

arXiv2026

From Simulated Citizens to Simulated Deliberation: Challenges in Representation and Interaction

Multi-agent LLM deliberation has been explored as a scalable way to simulate public deliberation. For such simulations to be informative, persona agents should reflect population opinion patterns and interaction should shape their conclusions. We evaluate whether LLM-based deliberation can meet these two conditions using census-grounded Korean personas debating real policy questions benchmarked against national surveys. Persona agents do not reliably reproduce population opinion patterns: responses are often far more concentrated and frequently reverse demographic differences in the human data. Deliberations nonetheless produce reasoned, reciprocal, and varied arguments alongside substantial stance movement. Yet much of this movement does not require peer exchange: sealed-monologue agents change position at similar rates and reach nearly the same final balance as full debates, while groups initialized with very different positions often converge to similar endpoints. Anchoring population-informed starting positions, meanwhile, sharply suppresses updating. Thus, population representation, argument generation, and interaction-driven opinion change do not necessarily go together. The simulations readily surface arguments on both sides, though whether they capture the diversity of human perspectives remains untested, leaving open a promising role for argument surfacing even as population simulation requires further validation.

cs.AI↗

arXiv2026

Investigating Assistant Bias in LLM User Simulators Using a Role Vector

LLM-based user simulators are increasingly used to evaluate autonomous agents at scale, in place of costly human evaluations. Despite this promise, these simulators exhibit "assistant bias," a tendency to cooperate and pursue task goals. They rarely reproduce the frustration or disengagement that real users exhibit, compromising evaluation validity. Prior work outlines that this bias is baked in during model training, which role-playing prompts fail to override. We analyze this bias from model activations, extracting a user role vector by contrasting how the model represents user versus assistant perspectives on the same dialogue. We observe two findings: (i) the user direction is identifiable in activations, elicits user-like behaviors, and captures characteristics distinct from assistant traits; and (ii) although user-role activation associates with simulation realism and steering strengthens it, it can exaggerate user behaviors and override individual user profiles. Together, our findings provide a representation-level analysis of LLM user simulators, confirming that assistant bias is structurally identifiable and that user behavior can be directionally analyzed.

cs.CL↗

arXiv2026

Maru: Information Architecture as a Shared Language for Generating Aligned and Persistent User Interfaces

Generative user interfaces (GenUIs) promise on-demand components tailored to users' needs. As users iterate on information tasks, they construct personal structures over information they encounter---how items are grouped, what gets prioritized, and what terms mean in their context. Yet, current systems leave these structural decisions to the model at each generation, ignoring the structural logic users have established. Without a persistent representational structure shared between user and system, GenUIs have no basis to remain aligned with what users have established. We draw on Information Architecture (IA), a design practice for organizing and structuring information, as a shared language to bridge user-constructed structure and system generation. We present a framework identifying four IA elements---partition, hierarchy, order, and vocabulary---and characterize how each maps to concrete UI generation decisions. We instantiate this framework in Maru, a conversational system that captures user prompts and interactions as IA preferences, persisting as rules both user and system draw on across generations. A user study revealed that IA persistence kept generated UIs aligned as sessions progressed, while alignment without it degraded, with diverse patterns emerging across users and contexts, pointing to the value of IA persistence in aligning GenUI to individual needs.

cs.HC↗

arXiv2026

When AI "Works," When Does Help Begin?: Intergenerational Support Around Older Adults' LLM Usage

LLMs are becoming part of everyday life, including for older adults (OAs). OAs often learn digital technologies with younger family members, who have traditionally served as "warm experts" providing trusted and personalized operational help. LLMs expand this role: family supporters may also help OAs judge appropriate uses, consider what information to disclose, assess the credibility of outputs, and decide when AI-generated advice is safe to act on. We conducted a formative qualitative study with six OAs and seven younger adults (YAs), using semi-structured interviews and scenario-based think-aloud activities. OA participants described using LLMs to lighten their recurring reliance on family, while preserving family as a selectively invoked support channel. However, because LLMs rarely produced visible operational breakdowns, YAs had limited signals for when support was actually needed. Instead, YAs relied on OAs' partial disclosures and negotiated intervention through general warnings and self-imposed action boundaries. As a result, family support often solved an immediate problem without leaving reusable calibration knowledge for future use. Based on these findings, we propose design implications for intergenerational LLM support (e.g., consentful help requests, learning-oriented family support that preserves OA task ownership).

cs.HC↗

arXiv2026

New lower bounds on domination--packing ratios in connected subcubic and cubic graphs

For a graph \(G\), let \(\gamma(G)\) and \(\rho(G)\) denote its domination number and packing number, respectively. Let \(c_{\mathrm{sub}}\) and \(c_{\mathrm{cub}}\) denote the respective limsups of \(\gamma(G)/\rho(G)\) over connected subcubic and connected cubic graphs as \(\rho(G)\to\infty\). We prove \[ c_{\mathrm{sub}}\geq\frac{13}{6}, \qquad c_{\mathrm{cub}}\geq\frac{17}{8}, \] by constructing two explicit binary branching families. The connected noncubic subcubic graphs \(\widehat B_t^\star\) satisfy \[ |V(\widehat B_t^\star)|=76\cdot2^t-12,\qquad \gamma(\widehat B_t^\star)=26\cdot2^t-4,\qquad \rho(\widehat B_t^\star)=12\cdot2^t-2, \] whereas the connected cubic graphs \(\widehat B_t^\bullet\) satisfy \[ |V(\widehat B_t^\bullet)|=108\cdot2^t-14,\qquad \gamma(\widehat B_t^\bullet)=34\cdot2^t-4,\qquad \rho(\widehat B_t^\bullet)=16\cdot2^t-2. \] The constructions use the same binary connector composition and closing lemma, with different connectors and initial assemblies. As a consequence, both families give unbounded additive violations of \(\gamma(G)\leq2\rho(G)+1\), disproving the proposed inequality even for connected cubic graphs.

math.CO↗

arXiv2026

Watermarked Game Solving via Perturbed Regret Minimization

Many real-world interactions among self-interested parties can be modeled by game theory, and the rapid advancements in AI have raised concerns about the possible misuse---accidental or deliberate---of superhuman or human-level game-playing agents by bad actors. While AI watermarking has mainly been applied to LLM-generated texts, a recent line of work proposes developing watermarking techniques for agents in game-theoretic settings. However, existing watermarking techniques for game-theoretic agents are not readily applicable due to their limited scope or capabilities---they are tailored to perfect-information games and are thus inapplicable to richer game types. We propose a new approach to watermarking game-playing agents, which a) can be applied to imperfect-information settings; b) is directly integrated into the learning process itself; and c) incurs only a bounded cost in exploitability. For this purpose, we introduce perturbed regret minimization, which adds perturbations to the utilities prior to observation so as to encourage the learning algorithm to embed the watermark. Our experiments show that the watermark incurs only a small exploitability cost and can be detected within just a couple of hours of gameplay at human speed.

cs.GT↗

arXiv2026

TIDES: A Longitudinal Bilingual Dataset for Modeling Multi-Party Social Dynamics

Group conversations are fundamental to human collaboration, yet standard large language models (LLMs) still struggle with the complexities of multi-party interaction. This challenge persists in part because existing group conversation datasets are often limited to short-term lab settings with contrived tasks, failing to capture the long-term social dynamics of real-world teams. To bridge this gap, we introduce TIDES, a high-resolution longitudinal dataset tracking 12 university project teams over a full semester. Comprising 75,971 utterances in both English and Korean from in-person meetings, TIDES provides a naturalistic record of teams working on self-managed projects. Our socio-structural annotations-covering interaction types, emergent roles, and development stages-allow for modeling of team evolution over months. Experiments show that fine-tuning on TIDES improves next-speaker prediction by 13.8 percentage points over a bigram baseline (64.53%) and yields performance comparable to strong proprietary zero-shot models. The model also comes within 2.1 percentage points of the published state of the art on the AMI Meeting Corpus while using approximately 42% less training data. However, human evaluations suggest that better next-speaker prediction does not necessarily yield more natural or coherent utterances, as fine-tuned models were generally less preferred than vanilla models. This potential mismatch motivates further study of how structural modeling can support natural multi-party generation.

cs.CL↗

arXiv2026

Student-ChatGPT Interaction Visible: Designing a Teacher Dashboard for EFL Writing Education

We present a Prompt Analytics Dashboard (PAD) for teachers that can traces student-LLM interactions from EFL writing classes. PAD can show student prompt-response exchanges with LLM chatbot and English essay writing revision histories to support data-informed instruction and visibility in classes. Through two iterative co-design sessions with six EFL instructors, we distilled a compact trace taxonomy (misuse signals, goal-alignment cues, revision effort) and instantiated three interface views (overview, week/outcome filter, drill-down with evidence snippets). This pipeline summarizes potential misuse and alignment at class/cohort levels and attaches micro-explanations to reduce over-surveillance. Instructors reported reduced scanning burden and clearer timing for interventions.

cs.HC↗

arXiv2026

Supporting Tutors in the Gig Economy with Automated Feedback: A Case Study on Ringle

The rise of online tutoring platforms in the gig economy has made education more scalable, flexible, and on-demand. These platforms rely on learner evaluations as the primary feedback for tutors and platforms. However, such feedback offers limited guidance for tutors' improvement and makes it difficult to monitor tutor quality at scale. To this end, we explored AI-powered automated feedback and how tutors perceive and respond to it. We deployed a research probe on Ringle, a popular online English tutoring platform, that analyzed tutors' lessons and provided automated feedback. We then surveyed 36 tutors about their experience. Our findings reveal that while tutors perceived automated feedback more negatively than learner feedback, they found it useful for self-monitoring and understanding platform expectations, though discrepancies between them often caused confusion. Based on these insights, we propose design considerations for feedback systems for online educational gig platforms.

cs.HC↗

arXiv2026

Domain-Independent Game Abstraction using Word Embedding Techniques

Many games of interest in the real world are often intractably large, thereby necessitating the use of game abstraction to shrink them in size, typically by many magnitudes. Over the last two decades, there have been significant advances in game abstraction; however, the domain-specific nature (usually poker) of much of the prior work prevents those techniques from being easily generalized to other settings without extensively analyzing the game at hand. In this paper, we propose a domain-independent approach to game abstraction, which applies word embedding techniques from the field of natural language processing. Treating each action as a word and gameplay data as a corpus, word vectors can be trained to represent each action as a real-valued vector, which can then be clustered to facilitate game abstraction. We also explore the use of foundational embedding models and show that action embeddings obtained this way can capture a surprising amount of information about the underlying game. Experimental results demonstrate that our proposed game abstraction technique is effective, although it does not outperform specialized algorithms tailored to specific games.

cs.GT↗

arXiv2026

Heuristic Pathologies and Further Variance Reduction via Uncertainty Propagation in the AIVAT Family of Techniques

How should an agent's performance in a multiagent environment be evaluated when there is a limited sample size or a high cost of running a trial? The AIVAT family of variance reduction techniques was proposed to address this challenge by introducing unbiased low-variance estimators of agents' expected payoffs. An important component of AIVAT is a heuristic value function that discriminates between potentially low- and high-value counterfactual histories. A notable gap in the literature is that there is little to no constraint or guideline on how the heuristic value function should be chosen or how uncertainty in its output should be handled. In our first contribution, we parameterize the heuristic value function to highlight AIVAT's potential vulnerabilities: a) the sample variance can be set pathologically low by directly applying gradient descent on the sample variance, and b) one can p-hack to draw a desired statistical conclusion via gradient descent/ascent on the test statistic. The main takeaway is that the heuristic value function should be fixed prior to observing the evaluation data! In our second contribution, we show how the heuristic uncertainty can be propagated to quantify the uncertainty of AIVAT estimates. It is then possible to further reduce the variance using inverse-variance weighted averaging, but AIVAT's unbiasedness guarantee may have to be sacrificed. In our experiments, we use a dataset of 10,000 poker hands to demonstrate our heuristic pathology and uncertainty results, with the latter yielding a 43.0% reduction in the number of samples (poker hands) needed to draw statistical conclusions.

cs.AI↗

arXiv2026

Parallelizing Counterfactual Regret Minimization

Parallelization has played an instrumental role in the field of artificial intelligence (AI), drastically reducing the time taken to train and evaluate large AI models. In contrast to its impact in the broader field of AI, applying parallelization to computational game solving is relatively unexplored, despite its great potential. In this paper, we parallelize the family of counterfactual regret minimization (CFR) algorithms, which were central to important breakthroughs for solving large imperfect-information games. We present a generalized parallelization framework, reframing CFR as a series of linear algebra operations. Then, existing techniques for parallelizing linear algebra operations can be applied to accelerate CFR. We also describe how our technique can be applied to other tabular members of the CFR family of algorithms, including the state-of-the-art, such as CFR+, discounted CFR, and predictive variants of CFR. Experimentally, we show that our CFR implementation on a GPU is up to four orders of magnitude faster than Google DeepMind OpenSpiel's CFR implementations on a CPU.

cs.AI↗

arXiv2026

Watermarking Game-Playing Agents in Perfect-Information Extensive-Form Games

Watermarking techniques for large language models (LLMs), which encode hidden information in the output so its source can be verified, have gained significant attention in recent days, thanks to their potential capability to detect accidental or deliberate misuse. Similar challenges involving model misuse also exist in the context of game-playing, such as when detecting the unauthorized use of AI tools in gaming platforms (e.g., cheating in online chess). In this paper, we initiate the study of how game-playing strategies can be watermarked. We show how the KGW watermark for LLMs can be adapted to watermark game-playing agents in perfect-information extensive-form games. The watermark can then be detected using a statistical test. We show that the degradation in the quality of the watermarked strategy profile, quantified by the expected utility, can be bounded, but there is a tradeoff between detectability and quality. In our experiments, we bootstrap the watermarking framework to various chess engines and demonstrate that a) the impact of the watermark on the quality of the strategy is negligible and b) the watermark can be detected with just a handful of games.

cs.GT↗

arXiv2026

Personalizing Cancer Models under Data Scarcity via Parameter Decomposition

Personalized cancer modeling for clinical applications requires robust and efficient parameter calibration, particularly in settings with limited patient data. This need is especially critical for medical digital twins (MDTs), which are virtual representations of disease continuously updated using longitudinal patient measurements. In this work, we propose a novel parameter personalization framework for dynamical cancer models under data scarcity. Our approach decomposes selected model parameters into a common component, shared across patients, and a personalized component, which is patient-specific and can be updated as new data become available. The common component captures population-level structure and is estimated once, providing an informed prior that enables rapid and accurate personalization. We demonstrate the effectiveness of this framework using synthetic data generated from canonical dynamical systems, such as logistic growth models with optimized treatment interventions. Our results show that parameter decomposition significantly improves calibration performance in limited-data regimes, facilitating fast and reliable personalization and supporting the development of patient-specific cancer models and MDTs.

q-bio.OT↗

arXiv2026

Hint-Writing with Deferred AI Assistance: Fostering Critical Engagement in Data Science Education

Generating hints for incorrect code is a cognitively demanding task that fosters learning and metacognitive development. This study investigates three designs for personalized, scalable, and reflective hint-writing activities within a data science course: (i) writing a hint independently, (ii) writing a hint with on-demand AI assistance, and (iii) deferred AI assistance, in which students first write a hint independently and then revise it with the help of an AI-generated one. We examine how AI support can scaffold the learning process without diminishing students' productive cognitive effort. Through a randomized controlled experiment with graduate-level students (N=97), we found that deferring AI assistance leads to the highest-quality hints. Further, this design helps students identify a wide range of mistakes they otherwise struggle to identify without any AI assistance. Students valued these activities as opportunities to practice debugging and critically engage with AI outputs--skills that are now critical for learners to acquire as programming becomes increasingly automated and the use of AI for learning grows. Our findings also highlight key considerations for designing student-AI collaborative learning experiences to sustain student engagement, maintain appropriate cognitive load, and mitigate negative effects of AI, such as introducing redundancies and extraneous information into student work.

cs.HC↗

arXiv2026

Contexty: Capturing and Organizing In-situ Thoughts for Context-Aware AI Support

During complex knowledge work, people engage in iterative sensemaking: interpreting information, connecting ideas, and refining their understanding. Yet in current human-AI collaboration, these cognitive processes are difficult to share and organize for AI. They arise in situ and are rarely captured without interrupting the task, and even when expressed, remain scattered or reduced to system-generated summaries that fail to reflect users' cognitive processes. We address this challenge by enabling AI context that is grounded in users' cognitive traces and can be directly inspected and revised by the user. We first explore this through a probe system that supports in-situ snippet memoing, allowing users to easily share their cognitive moves. Our study (N=10) highlights the value of capturing such context and the challenge of organizing it once accumulated. We then present Contexty, which supports users in inspecting and refining these contexts to better reflect their understanding of the task. Our evaluation (N=12) showed that Contexty improved task awareness, thought structuring, and users' sense of authorship and control, with participants preferring snippet-grounded AI responses over non-grounded ones (78.1%). We discuss how capturing and organizing users' cognitive context enables AI as a context-aware collaborator while preserving user agency.

cs.HC↗

arXiv2026

GUIDE: A Benchmark for Understanding and Assisting Users in Open-Ended GUI Tasks

Graphical User Interface (GUI) agents have the potential to assist users in interacting with complex software (e.g., PowerPoint, Photoshop). While prior research has primarily focused on automating user actions through clicks and keystrokes, this paradigm overlooks human intention, where users value the ability to explore, iterate, and refine their ideas while maintaining agency. To move beyond automation and toward collaboration, GUI agents must understand what users are doing and why. We introduce GUIDE (GUI User Intent Detection Evaluation), a benchmark that evaluates AI models on their ability to perceive user behavior, infer intent, and provide assistance in open-ended GUI tasks. GUIDE consists of 67.5 hours of screen recordings from 120 novice user demonstrations with think-aloud narrations, across 10 software. GUIDE defines three tasks - (i) Behavior State Detection, (ii) Intent Prediction, and (iii) Help Prediction that test a model's ability to recognize behavior state, reason about goals, and decide when and how to help. Evaluations across eight state-of-the-art multimodal models reveal that all models struggled, achieving only 44.6% and 55.0% accuracy on behavior state and help prediction. However, providing user context significantly improved the performance, raising help prediction by up to 50.2pp, highlighting the critical role of structured user understanding in effective assistance. Our dataset is available at https://guide-bench.github.io.

cs.CV↗

arXiv2026

"When to Hand Off, When to Work Together": Expanding Human-Agent Co-Creative Collaboration through Concurrent Interaction

As agents move into shared workspaces and their execution becomes visible, human-agent collaboration faces a fundamental shift from sequential delegation to concurrent co-creation. This raises a new coordination problem: what interaction patterns emerge, and what agent capabilities are required to support them? Study 1 (N=10) revealed that process visibility naturally prompted concurrent intervention, but exposed a critical capability gap: agents lacked the collaborative context awareness needed to distinguish user feedback from independent parallel work. This motivated CLEO, a design probe that embodies this capability, interpreting concurrent user actions as feedback or independent work and adapting execution accordingly. Study 2 (N=10) analyzed 214 turn-level interactions, identifying a taxonomy of five action patterns and ten codes, along with six triggers and four enabling factors explaining when and why users shift between collaboration modes. Concurrent interaction appeared in 31.8% of turns. We present a decision model, design implications, and an annotated dataset, positioning concurrent interaction as what makes delegation work better.

cs.HC↗