arXiv subjects

Xiaoshan Huang

Publications and source records attributed to Xiaoshan Huang.

At least 19 recordsLinked to original sources

arXiv2026

Unlocking the QPE Mystery: Star-Disk Collisions in Realistic AGN Disks

Quasi-periodic eruptions (QPEs) are luminous, recurring soft X-ray outbursts observed in the nuclei of low-mass galaxies. They display two remarkable trends: outburst durations are $\sim$10-20% of the recurrence timescale, and longer bursts are more luminous. A promising theory that naturally explains the quasi-periodicity invokes collisions between a star on an extreme mass-ratio inspiral (EMRI) orbit and the accretion disk around the supermassive black hole. However, it remains unclear how this model reproduces the observed trends. We therefore carry out two-dimensional, multi-frequency radiation hydrodynamic (RH) simulations of star--disk collisions. Crucially, we adopt a more realistic circumnuclear disk structure from previous Radiation MHD simulations of sub-Eddington accretion disks. We find that the thick, puffed-up disk atmosphere, extending to $z/r\sim1$, causes different portions of the bow shock to break out at different times, producing prolonged thermal emission as the shock emerges through the breakout surface at $z/r\sim0.7$. The X-ray flare duration is set by the shock propagation time through the optically thick disk--a $\sim$10% of the orbital timescale, reproducing the observed duty cycle. A more oblique star-disk interaction yields a longer, more luminous flare. The realistic AGN disk models also exhibit a surface density $Σ\propto r^2$, giving a collisional energy $E\propto P^{2/3}$ that may explain the luminosity--period trend, especially for the weaker QPEs. Overall, we suggest that a more realistic circumnuclear disk structure can explain several observed QPE trends-and QPEs may, in turn, constrain the disk structure.

astro-ph.HE↗

arXiv2026

X-ray Variability and Photosphere Evolution during Accretion Disk Formation in Tidal Disruption Events

The early time emission in tidal disruption events (TDEs) originates from both accretion and shocks, producing photons that eventually emerge from an inhomogeneous photosphere. We model disk formation following debris stream self-intersection in a TDE using three-dimensional, frequency-integrated and multi-group radiation hydrodynamic simulations. We find a more circularized disk forms about 24 days following the stream-stream collision, once the mass fallback rate passes its peak and the debris stream density decreases. Despite the absence of a circularized disk at early times, various shocks and the asymmetric photosphere are sufficient to drive a wide range of x-ray-to-optical ratios and soft-X-ray variability. We find that with strong apsidal precession, the first light is from the stream-stream collision. It launches an optically-thick outflow, but only produces modest prompt emission. The subsequent optical and ultraviolet (UV) light curve rise is mainly powered by shocks in the turbulent accretion flow close to the black hole. The optical-UV luminosity peaks roughly when the disk forms and shock-driven outflows subside. Radiation pressure clears the polar region and creates optically-thin channels. We obtain the broadband spectral energy distribution (SED) by post-processing multi-group simulations with 16-20 frequency groups. The SED has a black body component that peaks in the extreme UV. The soft X-ray component either resembles a thermal tail, or can be described by a power law associated with bulk Compton scattering. The blackbody parameters are broadly consistent with observed optical TDEs and vary weakly with viewing angle, but the soft X-ray emission is highly angle-dependent.

astro-ph.HE↗

arXiv2026

Stellar mergers and chemical element mixing: implications for the metamorphic stellar evolution in AGN disks

Chemical mixing during stellar mergers can significantly influence the subsequent evolution of the merger remnant. We perform a suite of three-dimensional hydrodynamical simulations of stellar mergers, each evolved for $\sim100$ stellar dynamical times until the remnant reaches a quasi-hydrostatic equilibrium. The simulations incorporate subgrid-scale diffusion models to capture the turbulent mixing of chemical elements. Starting with an idealized polytropic equation of state (EOS), we first identify the dominant mixing mechanisms and investigate how the merger outcome depends on the mass ratio, relative velocity, impact parameter, and stellar structure. We then extend our simulations to the context of stars embedded in active galactic nucleus (AGN) disks, using a realistic, composition-dependent EOS and AGN stellar models generated with the stellar evolution code MESA. We find that mergers with both younger metamorphic stars and H-rich accreting AGN stars can substantially rejuvenate old metamorphic stars through efficient core mixing after thermal relaxation. The merger remnants are nitrogen-enriched, with ${\rm N/O}\sim1$--3 and ${\rm N/C}\gtrsim5$, comparable to the abundances observed in the nebula surrounding SN 1987A. During subsequent stellar evolution, the remnants may converge onto the main sequence of isolated metamorphic AGN stars once they reach accretion--wind equilibrium. They may also deposit a significant amount of chemically enriched material into the AGN disk. This work provides a physical framework for connecting hydrodynamical stellar mergers with the long-term evolution of AGN stars and their observational and chemical signatures.

astro-ph.GA↗

arXiv2026

4th TDAMM Workshop White Paper

Time-Domain and Multi-Messenger Astrophysics (TDAMM) is entering a new era in which the rate and diversity of transient discoveries will grow rapidly across electromagnetic, gravitational-wave, neutrino, and cosmic-ray facilities. The scientific return from these investments will increasingly depend not on discovery alone, but on the ability to identify, prioritize, and coordinate follow-up observations across a heterogeneous and globally distributed network of observatories. This white paper summarizes the outcomes of the Fourth TDAMM Workshop and assesses the near-term discovery landscape, the infrastructure and tools that support coordinated observations, and the technical, policy, and capability gaps that may limit future progress. The workshop identified three principal challenges: insufficiently scalable and interoperable alert and coordination infrastructure, policies that impede rapid multi-facility observations and rare-event science, and the potential loss of critical high-energy, rapid-response, and spectroscopic capabilities. The white paper identifies the need for sustained support for alert distribution, brokers, standardized observatory metadata, cross-facility coordination platforms, and unified follow-up repositories; expanded joint observing opportunities and funding mechanisms for coordinated analysis; and strategic investment in future TDAMM facilities. The white paper also present a framework for community observing plans that would establish pre-coordinated responses to rare, high-impact events, supported by transparent governance, immediate public data release, and regular community revision. Science overviews and detailed observing strategies are provided for gamma-ray bursts, tidal disruption events, X-ray binaries, novae, supernovae, magnetars, compact binary mergers, and high-energy neutrino sources.

astro-ph.HE↗

arXiv2026

The Light Curve of Wind-Reprocessed Tidal Disruption Events

The source of the optical/UV emission in tidal disruption events (TDEs) remains an enduring question in the field. Connecting the observed emission to the source is critical for both our understanding of these transients and for using TDEs to study the efficiency of super-Eddington accretion and black hole growth. To explore this connection, we ran time-dependent 1D radiation hydrodynamic simulations of TDE emission with the Sedona monte carlo radiative transfer code, focusing on the reprocessing paradigm. Our simulations follow a compact, evolving X-ray and EUV bright source and surrounding reprocessing outflow over multiple months, using luminosities and mass flow rates consistent with hydro simulations of tidal disruptions. We determine the efficiency of reprocessing as a function of time in this dramatically changing environment and reproduce key observables including timescales, luminosities, and color evolution. Notably, we see a strong wavelength-dependence in the emission timescale due to reprocessing effects. Early on there is an X-ray flare which quickly fades as material builds up and obscures the hot source. At the same time, the optical/UV luminosity begins to rise. Though the optical/UV light curve has a similar shape to the bolometric light curve, the optical peak is offset by $\sim$3 weeks from the bolometric peak due to the time required to build up the reprocessing layer. This implies that early time, high energy emission may be missed for TDEs discovered in optical surveys, and the initial disruption and mass return time to the black hole may occur earlier than optical light curves suggest.

astro-ph.HE↗

arXiv2026

Resolving Oblique Star-Disk Collisions in Quasi-Periodic Eruptions: Numerical Requirements and the Importance of Geometry

Star-disk collisions have been proposed as a promising mechanism for producing quasi-periodic eruptions (QPEs) in galactic nuclei. Because the stellar atmospheric scale height is orders of magnitude smaller than the stellar radius, studying the shock launching by stars poses a significant numerical challenge. We implement an immersed solid-boundary method in Athena++ to study bow-shock formation and ejecta launching when a solid sphere crosses an accretion disk at supersonic speed. After validating the method against experimental results for solid bodies in uniform flows, we perform two- and three-dimensional adiabatic simulations of star-disk collisions. We find that resolving the bow-shock stand-off distance during the compression phase is essential: under-resolved simulations severely underestimate the ejecta mass and energy. When adequately resolved, the ejecta properties agree well with analytical estimates. We further show that collision geometry plays a critical role. Oblique encounters, which arise naturally due to disk rotation, allow easier shock breakout from the disk's backside and substantially reduce the luminosity contrast between forward and backward ejecta compared to perpendicular collisions. These results emphasize the importance of both numerical resolution and three-dimensional geometry in modeling star-disk collisions and interpreting QPEs.

astro-ph.HE↗

arXiv2026

Physiological and Semantic Patterns in Medical Teams Using an Intelligent Tutoring System

Effective collaboration requires teams to manage complex cognitive and emotional states through Socially Shared Regulation of Learning (SSRL). Physiological synchrony (i.e., longitudinal alignment in physiological signals) can indicate these states, but is hard to interpret on its own. We investigate the physiological and conversational dynamics of four medical dyads diagnosing a virtual patient case using an intelligent tutoring system. Semantic shifts in dialogue were correlated with transient physiological synchrony peaks. We also coded utterance segments for SSRL and derived cosine similarity using sentence embeddings. The results showed that activating prior knowledge featured significantly lower semantic similarity than simpler task execution. High physiological synchrony was associated with lower semantic similarity, suggesting that such moments involve exploratory and varied language use. Qualitative analysis triangulated these synchrony peaks as ``pivotal moments'': successful teams synchronized during shared discovery, while unsuccessful teams peaked during shared uncertainty. This research advances human-centered AI by demonstrating how biological signals can be fused with dialogues to understand critical moments in problem solving.

cs.AI↗

arXiv2026

"I Use ChatGPT to Humanize My Words": Affordances and Risks of ChatGPT to Autistic Users

Large Language Model (LLM) chatbots like ChatGPT have emerged as cognitive scaffolding for autistic users, yet the tension between their utility and risk remains under-articulated. Through an inductive thematic analysis of 3,984 social media posts by self-identified autistic users, we apply a technology affordance lens to examine this duality. We found that while users leveraged ChatGPT to offload executive dysfunction, regulate emotions, translate neurotypical communication, and validate their autistic identity, these affordances coexist with risks to their well-being: reinforcing delusional thinking, erasing authentic identity through automated masking, and triggering conflicts with the autistic sense of justice. As part of our preliminary work, this poster identifies trade-offs in autistic users' interactions with ChatGPT and concludes by outlining our future work on developing neuro-inclusive technologies that address these tensions through beneficial friction, bidirectional translation, and the delineation of emotional validation from reality.

cs.HC↗

arXiv2026

Nonlinear Nanophotonic Chip-space Interfaces: On-chip Generation of Structured, Topological and Spatiotemporal Lights Via Nonlinear Čerenkov Radiation

Miniaturized and reconfigurable interfaces between confined optical modes within integrated photonic chips and structured light propagating in free space would serve as a cornerstone for fundamental optical science and modern photonic technology. In this work, we exploit the anisotropic nonlinear susceptibility tensors associated with thin-film lithium niobate to construct nanophotonic chip-space interfaces capable of flexibly generating and multi-dimensionally engineering structured light via injections of photons to on-chip waveguides. By harnessing the nonlinear Čerenkov radiation in integrated nonlinear microring resonators, we successfully tailor the spatial profile, polarization state, emission wavelength, topological charge and temporal wave packet of structured optical vortices, exhibiting reconfigurabilities and tuning ranges far beyond the state-of-the-art. To further showcase the capabilities of our platform, we use a single pump to generate tunable optical skyrmions via the spin-orbit coupling and multi-state integrated vortex microcombs in the visible range via synergistic $χ^{(2)}$ and $χ^{(3)}$ nonlinear optical processes. Our work bridges the research fields of structured light and integrated nonlinear optics, providing unprecedented opportunities for spatiotemporal light generation and on-chip multidimensional nonlinear optics.

physics.optics↗

arXiv2026

AT2024lhc and AT2024kmq in the landscape of featureless tidal disruption events

We study AT2024kmq and AT2024lhc, two tidal disruption events (TDEs) with blue featureless spectra associated with high-mass black holes ($M_{\rm BH}\sim 10^8\,M_\odot$). Both events show optical precursors consistent with shock dissipation from stream self-intersection. Their X-ray emission is luminous ($L_{\rm X}\sim 10^{44}\,{\rm erg\,s^{-1}}$), highly variable (with minimum observed variability timescales of 1.3\,hr and 4.8\,hr for factor of $\sim3$ flux changes), long-lasting ($>1\,\rm yr$), emerging no later than the optical peak, and well characterized by power-laws with $1.7<Γ<3$ (where $f_ν\propto ν^{1-Γ}$). The X-ray properties and radio non-detections support a compact corona ($\lesssim 10 r_{\rm g}$) producing Comptonized X-ray emission. Using all published featureless TDEs, we find statistically significant bimodality in the distribution of their peak UV/optical blackbody luminosities and radii. We assemble a comparison TDE sample with early-time X-ray observations with eROSITA, in which we find different $M_{\rm BH}$ distributions in TDEs with different X-ray spectral evolution properties: low-mass black holes ($M_{\rm BH} \sim 10^6 M_\odot$) remain soft ($Γ>4$) within $t\lesssim 2$\,yr, intermediate masses ($\sim 10^7 M_\odot$) transition from soft to hard at $\sim$1 yr, while high masses ($\sim 10^8 M_\odot$) are hard ($1.5<Γ\lesssim 3$) from the outset. We interpret this result as evidence that the soft-to-hard state transition in TDEs occurs at the critical threshold of $\dot{M}_{\rm acc} \sim 0.03 \dot M_{\rm Edd}$ (similar to X-ray binaries), using the fact that the transition timescale predicted by simple disk theory scales with black hole mass as $t_{\rm tr}\propto M_{\rm BH}^{-3/4}$.

astro-ph.HE↗

arXiv2025

LLM Use for Mental Health: Crowdsourcing Users' Sentiment-based Perspectives and Values from Social Discussions

Large language models (LLMs) chatbots like ChatGPT are increasingly used for mental health support. They offer accessible, therapeutic support but also raise concerns about misinformation, over-reliance, and risks in high-stakes contexts of mental health. We crowdsource large-scale users' posts from six major social media platforms to examine how people discuss their interactions with LLM chatbots across different mental health conditions. Through an LLM-assisted pipeline grounded in Value-Sensitive Design (VSD), we mapped the relationships across user-reported sentiments, mental health conditions, perspectives, and values. Our results reveal that the use of LLM chatbots is condition-specific. Users with neurodivergent conditions (e.g., ADHD, ASD) report strong positive sentiments and instrumental or appraisal support, whereas higher-risk disorders (e.g., schizophrenia, bipolar disorder) show more negative sentiments. We further uncover how user perspectives co-occur with underlying values, such as identity, autonomy, and privacy. Finally, we discuss shifting from "one-size-fits-all" chatbot design toward condition-specific, value-sensitive LLM design.

cs.CY↗

arXiv2025

PartnerMAS: An LLM Hierarchical Multi-Agent Framework for Business Partner Selection on High-Dimensional Features

High-dimensional decision-making tasks, such as business partner selection, involve evaluating large candidate pools with heterogeneous numerical, categorical, and textual features. While large language models (LLMs) offer strong in-context reasoning capabilities, single-agent or debate-style systems often struggle with scalability and consistency in such settings. We propose PartnerMAS, a hierarchical multi-agent framework that decomposes evaluation into three layers: a Planner Agent that designs strategies, Specialized Agents that perform role-specific assessments, and a Supervisor Agent that integrates their outputs. To support systematic evaluation, we also introduce a curated benchmark dataset of venture capital co-investments, featuring diverse firm attributes and ground-truth syndicates. Across 140 cases, PartnerMAS consistently outperforms single-agent and debate-based multi-agent baselines, achieving up to 10--15\% higher match rates. Analysis of agent reasoning shows that planners are most responsive to domain-informed prompts, specialists produce complementary feature coverage, and supervisors play an important role in aggregation. Our findings demonstrate that structured collaboration among LLM agents can generate more robust outcomes than scaling individual models, highlighting PartnerMAS as a promising framework for high-dimensional decision-making in data-rich domains.

cs.MA↗

arXiv2025

Radiation-magnetohydrodynamic Simulations of Accretion Flow Formation After a Tidal Disruption Event

We perform 3D radiation-magnetohydrodynamic simulations of the evolution of the fallback debris after a tidal disruption event. We focus on studying the effects of magnetic fields on the formation and early evolution of the accretion flow. We find that large magnetic fields can increase the debris stream thickness, moderately reducing the efficiency of the radiative acceleration of outflows during the first self-intersecting collisions. As gas accumulates and the collisions happen instead between the infalling stream and the accretion flow, magnetized and nonmagnetized systems evolve similarly at these early times: radiation-driven outflows dominate early after the initial stream-stream collision and a few days later, the accretion rate exceeds the mass outflow rate. We find that the MRI does not play a significant role in angular momentum transport and dissipation. Nor do we find evidence of a magnetocentrifugal driven outflow. Instead, collisions continue to dissipate kinetic energy into radiation that launches outflows and powers TDE luminosities reaching $L\sim4-6\times10^{44}$ erg s$^{-1}$. Shock-driven outflows and inflows redistribute angular momentum throughout the extent ($\sim50 r_s$) of the forming eccentric disk. Even in the presence of magnetic stresses, the accretion flow remains mostly eccentric with $e\sim0.2-0.3$ for $r\lesssim8r_s$ and $e\sim0.4-0.5$ for $10\lesssim r\,(r_s)\lesssim50$. Lastly, we find a polar angle-dependent density structure compatible with the viewing-angle effect, along with an additional azimuthal angle dependence established by the collisions.

astro-ph.HE↗

arXiv2025

Linking Facial Recognition of Emotions and Socially Shared Regulation in Medical Simulation

Computer-supported simulation enables a practical alternative for medical training purposes. This study investigates the co-occurrence of facial-recognition-derived emotions and socially shared regulation of learning (SSRL) interactions in a medical simulation training context. Using transmodal analysis (TMA), we compare novice and expert learners' affective and cognitive engagement patterns during collaborative virtual diagnosis tasks. Results reveal that expert learners exhibit strong associations between socio-cognitive interactions and high-arousal emotions (surprise, anger), suggesting focused, effortful engagement. In contrast, novice learners demonstrate stronger links between socio-cognitive processes and happiness or sadness, with less coherent SSRL patterns, potentially indicating distraction or cognitive overload. Transmodal analysis of multimodal data (facial expressions and discourse) highlights distinct regulatory strategies between groups, offering methodological and practical insights for computer-supported cooperative work (CSCW) in medical education. Our findings underscore the role of emotion-regulation dynamics in collaborative expertise development and suggest the need for tailored scaffolding to support novice learners' socio-cognitive and affective engagement.

cs.HC↗

arXiv2025

Multi-band Emission from Star-Disk Collision and Implications for Quasi-Periodic Eruptions

We perform two-dimensional, multi-group radiation hydrodynamic simulations to explore the observational properties of a solar-like star colliding with an accretion disk around a supermassive black hole at separation of $\sim 100$ gravitational radii. We find that the star-disk collision produces ejecta on both sides of the disk. As the ejecta expand and cool, transient flares arise, reaching peak bolometric luminosity of up to $L\gtrsim10^{43}\rm erg~s^{-1}$. We estimate that the typical light curve rises and decays on an hour timescale. The spectral energy distribution (SED) peaks in $20-50$eV. The optical depth in soft X-rays is lower than the frequency-integrated optical depth, yielding $100$eV-$1$KeV luminosity $νL_ν\gtrsim10^{42}\rm erg~s^{-1}$. The ejecta aligned with the star's incident direction shows breakout emission, leading to asymmetric SED evolution of the two ejecta. The SED evolution is roughly consistent with those seen in short-period quasi-periodic eruptions (QPEs), which have eruption duration ranging from sub-hour to hours, but the ejecta cooling emission alone may not be sufficient to explain the longer duration flares. Increasing incident velocity generally produces a brighter and harder flare. A larger disk scale height prolongs the breakout emission but leads to a somewhat softer SED. A higher disk surface density can lead to higher ejecta temperature, reducing bound-free opacity and increasing luminosity. When lowering the disk surface density, we find that the ejecta becomes optically thin when the scattering optical depth across disk is at the order of $τ_{\rm disk}\sim200$, and the ejecta disappear when $τ_{\rm disk}\sim10$.

astro-ph.HE↗

arXiv2025

The Most Luminous Known Fast Blue Optical Transient AT 2024wpp: Unprecedented Evolution and Properties in the X-rays and Radio

We present X-ray (0.3--79 keV) and radio (0.25--203 GHz) observations of the most luminous Fast Blue Optical Transient (LFBOT) AT\,2024wpp at $z=0.0868$, spanning 2--280 days after first light. AT 2024wpp shows luminous ($L_{\rm X} \approx 1.5 \times 10^{43}\, \rm erg\,s^{-1}$), variable X-ray emission with a Compton hump peaking at $δt \approx 50$ days. The X-ray spectrum evolves from a soft ($F_ν \propto ν^{-0.6}$) to an extremely hard state ($F_ν \propto ν^{1.26}$) accompanied by a re-brightening at $δt \approx 50$\,days. The X-ray emission properties favor an embedded high-energy source shining through asymmetric expanding ejecta. We detect radio emission peaking at $L_{\rm 9\,GHz} \approx 1.7 \times 10^{29}\,\rm erg\,s^{-1}\,Hz^{-1}$ at $δt \approx 73$ days. The spectral evolution is unprecedented: the early millimeter fluxes rise nearly an order of magnitude during $δt \approx 17-32$ days followed by a decline in spectral peak fluxes. We model the radio emission as synchrotron radiation from an expanding blast wave interacting with a dense environment ($\dot{M} \sim 10^{-3}\, \rm M_{\odot}\,yr^{-1}$ for $v_{\rm w} = 1000\,\rm km\,s^{-1}$). The inferred outflow velocities increase from $Γβc \approx 0.07\, \rm to\,0.42c$ during $δt \approx 32-73$ days, indicating an accelerating blast-wave. We interpret these observations as a shock propagating through a dense shell of radius $\approx 10^{16}$\,cm, then accelerating into a steep density profile $ρ_{\rm CSM}(r) \propto r^{-3.1}$. All radio-bright LFBOTs exhibit similar circumstellar medium (CSM) density profiles ($ρ_{\rm CSM} \propto r^{-3}$), suggesting similar progenitor processes. The X-ray and radio properties favor a progenitor involving super-Eddington accretion onto a compact object launching mildly-relativistic disk-wind outflows.

astro-ph.HE↗

arXiv2025

Perturbing AGN Accretion Disks with Stars and Moderately Massive Black Holes: Implications for Changing-Look AGN and Quasi-Periodic Eruptions

We present a model that explains some extreme variability phenomena observed in active galactic nuclei (AGN). In this model, an orbiting companion interacts with the accretion disk surrounding the central supermassive black hole (SMBH). This interaction excites spiral density waves, leading to bursts of mass inflow lasting a few orbital timescales, whose mass content depends sensitively on the sphere of influence of the orbiting companion. To explain changing-look (CL) AGN, we find that lighter SMBH companions are necessary, while we generally exclude stellar companions. The moderately massive black hole perturber must be on a highly eccentric orbit in order to account for the non-repeating nature of most CL AGN. When applied to quasi-periodic eruptions (QPEs), we find that stars with highly eccentric orbits and close pericenter passages can produce accretion flares with QPE-like characteristics. For many QPEs, low-mass main-sequence stars or stripped-envelope stars are required. Although moderately massive black hole perturbers could also match the observed properties of QPEs, the gravitational-wave merger timescales of such binary systems are prohibitively short.

astro-ph.HE↗

arXiv2025

SSRLBot: Designing and Developing a Large Language Model-based Agent using Socially Shared Regulated Learning

Large language model (LLM)--based agents have emerged as pivotal tools in assisting human experts across various fields by transforming complex tasks into more efficient workflows and providing actionable stakeholder insights. Despite their potential, the application of LLM-based agents for medical education remains underexplored. The study aims to assist in evaluating the students' process and outcomes on medical case diagnosis and discussion while incorporating the theoretical framework of Socially Shared Regulation of Learning (SSRL) to assess student performance. SSRL emphasizes metacognitive, cognitive, motivational, and emotional interactions, highlighting the collaborative management of learning processes to improve decision-making outcomes. Grounded in SSRL theory, this tool paper introduces SSRLBot, an LLM-based agent designed to enable team members to reflect on their diagnostic performance and the key SSRL skills that foster team success. SSRLBot's core functions include summarizing dialogue content, analyzing participants' SSRL skills, and evaluating students' diagnostic results. Meanwhile, we evaluated SSRLBot through diagnostic conversation data collected from six groups (12 participants, 1926 conversational turns). Results showed that SSRLBot can deliver detailed, theory-aligned evaluations, link specific behaviors to SSRL dimensions, and offer actionable recommendations for improving teamwork. The findings address a critical gap in medical education, advancing the application of LLM agents to enhance team-based decision-making and collaboration in high-stakes environments.

cs.HC↗