arXiv subjects

Yubin Kim

Publications and source records attributed to Yubin Kim.

At least 19 recordsLinked to original sources

arXiv2026

Measuring AI Agents as Teammates with Collaborative Intelligence

Progress in AI is often measured by what a single model can do on its own. Yet teams of AI agents are starting to make breakthroughs and discoveries in science, medicine, mathematics and software engineering. As AI begins to work in teams of agents and people, the ability to collaborate becomes a core part of their intelligence. Research on human teams has measured this ability for decades. Inspired by this, we introduce the Collaborative Intelligence Benchmark, which measures how well an AI agent works as a teammate. It contains 240 tasks across 8 dimensions of teamwork, from refusing an unsafe shortcut to checking the work that a weaker model leaves behind. Each task comes from a real record or an existing benchmark, from aviation accident reports and clinical cases to coding tasks and negotiations, and has a programmatically verifiable outcome. To isolate teamwork from individual capability, models are scored only on tasks that they can solve by themselves when they have full information. We evaluate 18 closed- and open-weight models and find that every model, across sizes and families, has clear weaknesses as a teammate, with the best model scoring only 82.2 out of 100. Frontier models almost always refuse unsafe shortcuts and report misconduct, yet they cave under interpersonal pressure, reaching the best overall deal in only 14% of conflicts, and their pass rate drops from 97% to 81% when they take over a task in which a weaker model has cheated. Crucially, general capability does not guarantee good teamwork, as models with nearly the same capability score differ by up to 11 points as teammates. The benchmark includes 160 public tasks with code and data, along with 80 held-out tasks for evaluation. As AI agents increasingly work alongside other agents and people, the ability to collaborate effectively is becoming a crucial capability to measure and develop.

cs.AI↗

arXiv2026

StretchTime: Adaptive Time Series Forecasting via Symplectic Attention

Transformer architectures have established strong baselines in time series forecasting, yet they typically rely on positional encodings that assume uniform, index-based temporal progression. However, real-world systems, from shifting financial cycles to elastic biological rhythms, frequently exhibit "time-warped" dynamics where the effective flow of time decouples from the sampling index. In this work, we first formalize this misalignment and prove that rotary position embedding (RoPE) is mathematically incapable of representing non-affine temporal warping. To address this, we propose Symplectic Positional Embeddings (SyPE), a learnable encoding framework derived from Hamiltonian mechanics. SyPE strictly generalizes RoPE by extending the rotation group $\mathrm{SO}(2)$ to the symplectic group $\mathrm{Sp}(2,\mathbb{R})$, modulated by a novel input-dependent adaptive warp module. By allowing the attention mechanism to adaptively dilate or contract temporal coordinates end-to-end, our approach captures locally varying periodicities without requiring pre-defined warping functions. We implement this mechanism in StretchTime, a multivariate forecasting architecture that achieves state-of-the-art performance on standard benchmarks, demonstrating superior robustness on datasets exhibiting non-stationary temporal dynamics.

cs.LG↗

arXiv2026

Training language models in simulation for psychiatric intake

In psychiatric practice, the clinical intake interview remains a primary diagnostic instrument, requiring the clinician to establish rapport while disentangling complex, overlapping presentations. Here, we show that multi-turn reinforcement learning (RL) in simulation environments improves language model performance on structured text-based psychiatric intake, spanning history-taking, differential diagnosis, and initial management planning. In a randomized, double-blind crossover study ($N = 60$ matched scenario pairs, 120 encounters) comparing the RL-trained agent against its identically prompted base model, 32 board-certified psychiatrists role-played standardized patients while a separate panel of 15 independent, board-certified psychiatrists scored the de-identified transcripts. The trained agent outperformed the base model in 76.7% of matched scenario pairs ($p < 0.0001$), with gains on an adapted clinical-examination rubric ($d_z = 0.77$, $p < 0.0001$), patient-centered communication (82.0% vs. 65.2%, $p < 0.001$), and differential diagnosis appropriateness (68.3% vs. 33.3%, $p < 0.001$). Across 127 psychiatrist-validated simulated intake scenarios, the trained agent nearly doubled its base model's clinical rubric score (0.706 vs. 0.379; composite reward 0.564 vs. 0.294, $p < 0.0001$). To systematically probe conversational safety, we established two Delphi-consensus taxonomies, of clinical safety risks and relational competencies, from which 256 challenging adversarial presentations were derived; we find that training in simulation environments more than halved under-triage of acute safety risks (12.9% vs. 30.5%, $p < 0.0001$). Simulation environments thus provide a controlled testbed for training and stress-testing psychiatric conversational agents, with gains that transferred to psychiatrist-enacted encounters, though residual gaps require safeguards and clinician oversight.

cs.AI↗

arXiv2026

TeamGym: A Gym for Team Decision-Making by AI Agents with Distributed Information

Many real-world decisions require teams to integrate information distributed across participants. Yet AI agents are still primarily trained and benchmarked in isolation. We introduce TeamGym, an environment for evaluating and training language model-based agents on team decision-making problems constructed from real-world legal, finance, medical, and software engineering corpora. TeamGym introduces a method to identify a minimal set of facts, each element of which is necessary and all of which are collectively sufficient for a correct final decision, which we call pivotal information. This enables TeamGym to both control the distribution of pivotal information and track how well agents identify and integrate pivotal information when making team decisions. Examining 8 language models on 12 source corpora, we find that current AI agents often fail to effectively share information: Distributing pivotal information across participants lowers success rate by 22.9 percentage points on average relative to giving the same information to a single model (a communication gap). We also document that participants do not effectively retrieve decision-relevant information on their own: A team's success rate is lowered by a further 19.9 points when participants must identify and extract pivotal information from source material rather than receiving it directly (a retrieval gap). To help remedy these deficits, we use TeamGym to train policies through reinforcement learning on team decision loss. Across two policy-training experiments, we find that training improves final-decision quality and induces emergent coordination in participation, speaker selection, and communication, even though the reward evaluates only the final decision.

cs.AI↗

arXiv2026

Persistent Partners Raise Prices Among Learning Agents

When pricing agents meet repeatedly on a platform, the platform decides who faces whom. We ask whether that choice moves the prices the agents learn, and whether a rise comes with learned punishment. In a pre-registered randomised experiment in the Bertrand duopoly of Calvano et al., each agent's price is set by a tabular Q-learning module, not by the small language model attached to it, and we randomise whether each agent keeps its partner, sees its rival's prices and can send messages. Keeping the same partner raises the level of profits, averaged over training, by 0.27 of the gap between competitive and monopoly profit (95% CI 0.20 to 0.35, all twenty paired runs positive), our registered primary result, and the resting price by 0.17 of the Nash-to-monopoly range (post hoc). A plain tabular learner reproduces the effect in all 25 further blocks, and there one permanent partner raises the level more than about three do (+0.23 against +0.05, exploratory). Where rival prices are hidden, the price-setting module cannot see a cut, so cannot punish it, yet the resting price rises as much and the rise lasts to the end of training, while with visible rivals it shrinks with longer training (post hoc). Where the rival is visible, a static best responder accounts for a third to a half of what a forced-deviation probe reads as punishment, on the starts where the rival can see the cut, and net of it the registered test of learned punishment is inconclusive. A test that looks only for punishment would thus miss the rise where the rival is hidden, while a check for profitable deviations flags most of those prices (post hoc). In an exploratory extension, untrained Qwen2.5 7B and 14B models under one prompt show the effect when the rival's price is left out of the prompt and inconsistently when it is shown, the 7B result replicating on fresh blocks, while two other model families show none.

cs.LG↗

arXiv2026

Locating Hidden Failures Makes Long-Horizon Agents More Reliable

As AI agents take on long, autonomous tasks, we increasingly oversee rather than perform the work, yet we still judge them almost entirely by whether they finally succeed. An outcome cannot reveal where a run went wrong, whether the agent recovered, or the irreversible harm it caused along the way, and where long-horizon agents fail remains unmapped. We study $2518$ agent trajectories across software engineering, computer use, and science, close to real deployment, and classify $6967$ mistakes into $78$ failure types. Failure follows a recurring signature: after its first mistake an agent often fails to recover and rarely catches the error itself, so the run continues unchecked while still looking correct; whether an agent recovers depends on the task and the environment's feedback, not on the agent framework running it. Long-horizon agents can do real harm on the way to a passing result: even runs scored as solved delete data, corrupt systems, or fabricate success rather than earning it. We release these human-verified annotations as Traverse, a benchmark on which six frontier judges struggle to locate failure regardless of scale: even the strongest correctly identifies the first mistake in fewer than a third of runs. Yet Scout, a $4$B verifier we trained, locates failure far better than these judges and transfers to domains it never saw. Used at test time to select among an agent's candidate runs, it raises task success above the agent's own single-attempt performance, without retraining the agent. By making failure cheap to locate and correct, this work is a foundation for more trustworthy long-horizon agents that learn from their own mistakes, and a practical path to overseeing increasingly autonomous AI.

cs.LG↗

arXiv2026

Unsupervised Deep Learning Method for Clustering KAGRA O3GK Transient Noise Data

The advent of ground-based gravitational wave detectors has significantly improved the detection of faint gravitational wave signals. However, these detectors are affected by various types of transient noise, known as glitches, which can mimic true gravitational wave signals and limit detector sensitivity. Classifying glitches according to their time-frequency characteristics not only facilitates a deeper understanding of their origins, but also supports their mitigation on data to maintain data quality. While supervised machine learning methods are commonly employed for glitch classification, they require the labelling of training datasets obtained through manual annotation, a process which is costly and not scalable for evolving detectors. In order to address this challenge, the present study investigates unsupervised deep learning methods for dimensionality reduction and clustering of glitch spectrogram images. In this study, three distinct approaches are applied and compared using data from the KAGRA detector's O3GK run. The findings of this study demonstrate that deep learning-based feature extraction significantly enhances the clustering performance compared to traditional machine learning methods. This study presents an initial analysis of the KAGRA glitch dataset using unsupervised deep learning, highlighting the potential of this approach for efficient and scalable glitch classification in future observation runs.

gr-qc↗

arXiv2026

Safety-Critical Bilateral Teleoperation for Omnidirectional Aerial Manipulation Using Force-Sensorless Haptic Feedback

This paper presents a safety-critical bilateral teleoperation framework for omnidirectional aerial manipulators that integrates visual and force-sensorless haptic wrench feedback. Unlike existing approaches that either rely on onboard force/torque sensors or use model-dependent wrench estimates, which may become unreliable under model uncertainties or induce unintended feedback during free-flight, our method implements a hierarchical safety filter based on control barrier functions to avoid such limitations. The safety filter, being the key contribution, explicitly accounts for tracking errors arising from physical interaction between the aerial manipulator and its surroundings while enforcing thrust limits, a factor overlooked despite its critical importance for flight safety. This safety filter adjusts the command from the operator to ensure safe and stable aerial manipulation and avoid motor saturation. The adjustment made by the filter is mapped to haptic feedback, which is intuitive to the operator and conveys information on physical interaction and impending motor saturation. By actual experiments with a hexarotor-based omnidirectional aerial manipulator, we demonstrate that the proposed method avoids haptic feedback during free-flight, provides directionally consistent feedback under physical interaction, and can be operated for diverse manipulative tasks. Moreover, an ablation study further shows that the saturation filter improves interaction stability by explicitly preventing motor saturation and informing the operator of corrective actions.

cs.RO↗

arXiv2026

MatrAIx: Simulating the World with 8.3 Billion Persona Agents

Human evaluation of AI systems and digital products is costly, slow, and difficult to scale. Offline evaluations are more scalable but often abstract away human diversity and interactive behavior. We therefore introduce MatrAIx, a population-scale simulated-user evaluation infrastructure for testing AI systems and digital products with heterogeneous users. MatrAIx has three core components: First, Persona 8B contains 8.3 billion persona records represented by 1,290 categorical dimensions. Records are either sampled from a dependency graph that preserves correlated attributes or derived from human-authored profiles. We release a quality-filtered coreset of approximately 1 million personas, comprising 599,847 human-grounded and 400,000 synthetic records. Second, the MatrAIx Playground provides four environments in which diverse users evaluate and interact with digital products: Survey, AI Chatbot, Web, and App. Third, MatrAIx provides 1,010 application tasks spanning more than 25 domains, including Commerce, Software, Finance, and Healthcare. We conducted 18,189 evaluation trials across eight representative tasks. Persona agents were powered by three LLMs: Claude Opus 4.8, GPT 5.5, and Claude Haiku 4.5. The resulting feedback captures how decisions and preferences vary across persona backgrounds, including hesitation after a price increase, willingness to continue after an AI assistant fails, and latency tolerance. We conducted two main validation studies: First, a 400-trial controlled study evaluated persona adherence across ten behavioral attributes and all four environments. The declared behavior was expressed or correctly suppressed in 366 trials (91.5%). Second, human and LLM judges evaluated the extraction quality of human-grounded personas. Overall, MatrAIx provides an end-to-end infrastructure for evaluating AI systems and digital products with diverse simulated human users.

cs.AI↗

arXiv2026

Towards a General Intelligence and Interface for Wearable Health Data

While ubiquitous wearable sensors capture a wealth of behavioral and physiological information, effectively transforming these signals into personalized health insights is challenging. Specifically, converting low-level sensor data into representations capable of characterizing higher-level states is difficult due to high phenotypic diversity and variation in individual baseline health, physiology, and lifestyle factors. Moreover, collecting wearable data paired with health outcome annotations is laborious and expensive, and retrospective annotation remains practically unfeasible, contributing to a scarcity of data with high-quality labels. To overcome these limitations, we propose a foundation model for wearable health that is pretrained on more than one trillion minutes of unlabeled sensor signals drawn from a large cohort of five million participants. We demonstrate that the joint scaling of model capacity and pretraining data volume leads to systematic improvements in performance, as evaluated on a diverse set of 35 health prediction tasks, spanning cardiovascular, metabolic, sleep, and mental health, as well as lifestyle choices and demographic factors. We find that this population scale representation unlocks label-efficient few-shot learning and generative capabilities for robust daily metric estimation. To further leverage this learned representation, we deploy a classroom of LLM agents to autonomously search the space of downstream predictive heads built on the model embeddings, showing broad performance improvements that increase with LLM model capacity. Finally, we show how integrating these downstream predictors into a Personal Health Agent can support model responses that are more relevant, contextually aware, and safe, and we validate this via 1,860 ratings from a cohort of clinicians.

cs.AI↗

arXiv2026

An AI Co-Data-Scientist for Prioritizing Candidate Biomarkers from Wearable Sensor Data

Wearable devices generate continuous physiological and behavioral data, but converting these signals into clinically reviewable biomarker hypotheses remains labor-intensive. We introduce CoDaS, an AI co-data-scientist that integrates multi-agent hypothesis generation, deterministic statistical analysis, adversarial validation and literature-grounded interpretation under human oversight. Across three wearable cohorts comprising 9,279 participant-observations, CoDaS prioritized candidate associations for mental-health and metabolic endpoints after internal checks for replication, stability, robustness and leakage. The system identified related circadian-instability signals associated with depression, including sleep-duration variability in DWB ($ρ$ = 0.252, $p$ < 0.001) and sleep-onset variability in GLOBEM ($ρ$ = 0.126, $p$ < 0.001), and derived a wearable cardiovascular-fitness index associated with insulin resistance (steps/resting heart rate; $ρ$ = -0.374, $p$ < 0.001). Adding these features to demographic models produced modest gains ($ΔR^2$ = 0.040 for depression, 0.021 for insulin resistance). In a 12-clinician review totaling approximately 25 active hours, clinician validity judgments aligned with CoDaS confidence tiers ($ρ$ = 0.67, $p$ = 0.005), whereas added clinical value and confidence to act were rated lower. CoDaS supports traceable, hypothesis-generating prioritization of wearable candidate biomarkers.

cs.AI↗

arXiv2026

Beyond Similarity: Temporal Operator Attention for Time Series Analysis

A persistent paradox in time-series forecasting is that structurally simple MLP and linear models often outperform high-capacity Transformers. We argue that this gap arises from a mismatch in the sequence-modeling primitive: while many time-series dynamics are governed by global temporal operators (e.g., filtering and harmonic structure), standard attention forms each output as a convex combination of inputs. This restricts its ability to represent signed and oscillatory transformations that are fundamental to temporal signal processing. We formalize this limitation as a simplex-constrained mixing bottleneck in softmax attention, which becomes especially restrictive for operator-driven time-series tasks. To address this, we propose $\textbf{Temporal Operator Attention (TOA)}$, a framework that augments attention with explicit, learnable sequence-space operators, enabling direct signed mixing across time while preserving input-dependent adaptivity. To make dense $N \times N$ operators practical, we introduce Stochastic Operator Regularization, a high-variance dropout mechanism that stabilizes training and prevents trivial memorization. Across forecasting, anomaly detection, and classification benchmarks, TOA consistently improves performance when integrated into standard backbones such as PatchTST and iTransformer, with particularly strong gains in reconstruction-heavy tasks. These results suggest that explicit operator learning is a key ingredient for effective time-series modeling.

cs.LG↗

arXiv2026

Social Human Robot Embodied Conversation (SHREC) Dataset: Benchmarking Foundational Models' Social Reasoning

Our work focuses on the social reasoning capabilities of foundation models for real-world human-robot interactions. We introduce the Social Human Robot Embodied Conversation (SHREC) Dataset, a benchmark of $\sim$400 real-world human-robot interaction videos and over 10K annotations, capturing robot social errors, competencies, underlying rationales, and corrections. Unlike prior datasets focused on human-human interactions, the SHREC Dataset uniquely highlights the social challenges faced by real-world social robots such as emotion understanding, intention tracking, and conversational mechanics. Moreover, current foundation models struggle to recognize these deficits, which manifest as subtle, socially situated failures. To evaluate AI models' capacity for social reasoning, we define eight benchmark tasks targeting critical areas such as (1) detection of social errors and competencies, (2) identification of underlying social attributes, (3) comprehension of interaction flow, and (4) providing rationale and alternative correct actions. Experiments with state-of-the-art foundation models, alongside human evaluations, reveal substantial performance gaps -- underscoring the difficulty and providing directions in developing socially intelligent AI.

cs.HC↗

arXiv2026

InvThink: Premortem Reasoning for Safer Language Models

We present InvThink, a training and prompting framework that requires the model to enumerate, analyze, and constrain potential failures before generating its final response. Unlike existing safety alignment methods that optimize only for safe final responses, InvThink structures generation into three steps: (1) enumerate potential harms, (2) analyze their consequences, (3) generate the response under explicit mitigation constraints. We observe three findings: (i) InvThink shows higher safety scores at larger model sizes, compared to existing safety prompting and alignment baselines. (ii) InvThink mitigates the safety tax. Models trained with INVTHINK preserve their reasoning capability on standard benchmarks. (iii) beyond general safety tasks, InvThink also reduces harmful behavior in professional ethics domains (medicine, finance, law) and in agentic misalignment scenarios, achieving up to 32% reduction in harmfulness over zero-shot baselines and 16% over SafetyPrompt. We extend InvThink with supervised fine-tuning, and GRPO-based reinforcement learning across three LLM families.

cs.AI↗

arXiv2026

TeamBench: Evaluating Agent Coordination under Enforced Role Separation

Agent systems often decompose a task across multiple roles, but these roles are typically specified by prompts rather than enforced by access controls. Without enforcement, a team pass rate can mask whether agents actually coordinated or whether one role effectively did another role's work. We present TeamBench, a benchmark with 851 task templates and 931 seeded instances for evaluating agent coordination under operating system-enforced role separation. TeamBench separates specification access, workspace editing, and final certification across Planner, Executor, and Verifier roles, so that no role can read the full requirements, modify the workspace, and certify the final answer. Prompt-only and sandbox-enforced teams reach statistically indistinguishable pass rates, but prompt-only runs produce 3.6 times more cases where the verifier attempts to edit the executor's code. Verifiers approve 49% of submissions that fail the deterministic grader, and removing the verifier improves mean partial score in the ablation. Team value is also conditional. Teams benefit when single agents struggle, but hurt when single agents already perform well. A 40-session human study under the same role separation shows that our benchmark exposes interaction patterns that pass rate misses. Solo participants work through the task directly, human participants paired with agents often collapse into quick approval, and human teams spend more effort coordinating missing information across roles.

cs.AI↗

arXiv2026

Towards a Science of Scaling Agent Systems

Agents, language model-based systems capable of reasoning, planning, and acting are widely adopted in real-world tasks, yet how their performance changes as these systems scale across key dimensions remains underexplored. We introduce quantitative scaling principles for agent systems as a predictive model, capturing how performance varies with coordination, model capability, and measurable system and task factors. Across 260 configurations spanning six agentic benchmarks, five canonical architectures (Single-Agent and four Multi-Agent: Independent, Centralized, Decentralized, Hybrid), and three LLM families, we perform controlled evaluations, standardizing tools, prompts, and compute to isolate architectural effects. The resulting model achieves a cross-validated R^2=0.373 across all six benchmarks (R^2=0.413 with a task-grounded capability metric). We identify a robust capability-saturation effect and additional patterns: (1) a coordination yields diminishing returns once single-agent baselines exceed certain performance; (2) tool-heavy tasks appear to incur multi-agent overhead; and (3) architectures without centralized verification tend to propagate errors more than those with centralized coordination. Relative performance change compared to single-agent baseline ranges from +80.8% on decomposable financial reasoning to -70.0% on sequential planning, demonstrating that architecture-task alignment determines collaborative success. The framework identifies the best-performing architecture for 87% of held-out configurations and shows consistent relative architecture preferences on unseen frontier models. Agent effectiveness depends on alignment between coordination and task structure, and that mismatched coordination degrades the performance.

cs.AI↗

arXiv2026

ZeroS: Zero-Sum Linear Attention for Efficient Transformers

Linear attention methods offer Transformers $O(N)$ complexity but typically underperform standard softmax attention. We identify two fundamental limitations affecting these approaches: the restriction to convex combinations that only permits additive information blending, and uniform accumulated weight bias that dilutes attention in long contexts. We propose Zero-Sum Linear Attention (ZeroS), which addresses these limitations by removing the constant zero-order term $1/t$ and reweighting the remaining zero-sum softmax residuals. This modification creates mathematically stable weights, enabling both positive and negative values and allowing a single attention layer to perform contrastive operations. While maintaining $O(N)$ complexity, ZeroS theoretically expands the set of representable functions compared to convex combinations. Empirically, it matches or exceeds standard softmax attention across various sequence modeling benchmarks.

cs.LG↗

arXiv2026

CAPS: Unifying Attention, Recurrence, and Alignment in Transformer-based Time Series Forecasting

This paper presents $\textbf{CAPS}$ (Clock-weighted Aggregation with Prefix-products and Softmax), a structured attention mechanism for time series forecasting that decouples three distinct temporal structures: global trends, local shocks, and seasonal patterns. Standard softmax attention entangles these through global normalization, while recent recurrent models sacrifice long-term, order-independent selection for order-dependent causal structure. CAPS combines SO(2) rotations for phase alignment with three additive gating paths -- Riemann softmax, prefix-product gates, and a Clock baseline -- within a single attention layer. We introduce the Clock mechanism, a learned temporal weighting that modulates these paths through a shared notion of temporal importance. Experiments on long- and short-term forecasting benchmarks surpass vanilla softmax and linear attention mechanisms and demonstrate competitive performance against seven strong baselines with linear complexity. Our code implementation is available at https://github.com/vireshpati/CAPS-Attention.

cs.LG↗