arXiv subjects

Hyunwoo Park

Publications and source records attributed to Hyunwoo Park.

At least 19 recordsLinked to original sources

arXiv2026

Faithful yet Collusive: Why Chain-of-Thought Monitoring Cannot Detect Collusion in LLM Pricing Agents under Oligopolistic Competition

Large language models (LLM) deployed as autonomous pricing agents may sustain supracompetitive prices through tacit coordination. We develop a causal graph divergence framework that separately measures structural faithfulness and intent faithfulness of LLM pricing agents in Bertrand competition. Across nine LLMs under duopoly and triopoly conditions, collusive behavior and chain-of-thought (CoT) faithfulness dissociate along both dimensions: the most collusive model accurately reports cooperative intent yet reasons structurally unfaithfully, while the most structurally faithful model sustains supra-Nash pricing under both market structures. These findings establish that CoT monitoring alone cannot serve as a standalone safeguard against algorithmic collusion.

cs.AI↗

arXiv2026

Market Signal Injection: Adversarial Context Manipulation of LLM Pricing Agents

Large language model (LLM) pricing agents may respond to how market data is presented, even when its numerical values remain unchanged. We introduce market signal injection (MSI), an attack that manipulates numerical formatting, competitor ordering, or qualitative market commentary without issuing explicit instructions. We evaluate nine open-weight models in simulated Bertrand duopoly and triopoly markets and three proprietary models in duopoly markets. Sentiment-based attacks produce the largest behavioral shifts, which propagate to other firms and alter profits and consumer surplus. Susceptibility varies across model families, and larger models are not consistently more robust. Matched neutral-text controls and a rule-based agent support a framing-based account of these shifts under the fixed demand parameters of our simulation. Episode-held-out probes distinguish baseline from attacked activations in all eleven re-evaluated model--condition pairs: linear AUC is 1.00 and MLP AUC ranges from 0.93 to 0.99. This separability does not by itself identify harmful pricing decisions. Input canonicalization removes the tested sentiment attacks, while decision boundary anchoring, which combines prompt constraints with output projection, provides partial mitigation under the tested adaptive attacks. These results identify data presentation as an attack surface for LLM pricing agents and motivate defenses that account for interactions among agents.

cs.AI↗

arXiv2026

Flat Score, Amplified Failures: How the Error Budget Masks Damage in Quantized LLM Agents

Post-training quantization to 4-bit weights is widely reported to be nearly lossless. We test this claim for multi-turn, tool-calling agents, where it now matters most. On $τ^2$-bench, across two open-weight model families in dense and MoE variants and two domains (eight cells, 456 episodes each, at 16-, 8-, and 4-bit weights), quantization indeed looks free on the standard metric. No cell shows a score change that survives multiple-comparison correction, and in the cell that carries the largest process damage, equivalence testing bounds the change within $\pm$7.5 points. The process tells a different story. Quantization amplifies the failure the model already exhibits at full precision (tool-name hallucination in telecom, with the same directional trend in retail entity errors) by up to 2.5$\times$ in volume (+17.6 points per task), while creating essentially no new failures. The failure set is the same at every precision (rank correlation $\geq$ 0.94, 0.18% novel events). The score stays flat because the benchmark's ten-error budget absorbs the extra failures. Shrinking the budget to two errors re-exposes a score gap of 17 points, and it does so only in the one cell where quantization added error volume, exactly as the masking account predicts. A targeted error-repair prompt, run for five telecom models at every precision, removes the damage exactly and only where it lives. Both diagnostics, the per-channel error rate and success under a shrinking budget, come from logs benchmarks already collect; we suggest reporting them alongside task reward.

cs.LG↗

arXiv2026

Humanity's Last Exam

Benchmarks are important tools for tracking the rapid advancements in large language model (LLM) capabilities. However, benchmarks are not keeping pace in difficulty: LLMs now achieve over 90\% accuracy on popular benchmarks like MMLU, limiting informed measurement of state-of-the-art LLM capabilities. In response, we introduce Humanity's Last Exam (HLE), a multi-modal benchmark at the frontier of human knowledge, designed to be the final closed-ended academic benchmark of its kind with broad subject coverage. HLE consists of 2,500 questions across dozens of subjects, including mathematics, humanities, and the natural sciences. HLE is developed globally by subject-matter experts and consists of multiple-choice and short-answer questions suitable for automated grading. Each question has a known solution that is unambiguous and easily verifiable, but cannot be quickly answered via internet retrieval. State-of-the-art LLMs demonstrate low accuracy and calibration on HLE, highlighting a significant gap between current LLM capabilities and the expert human frontier on closed-ended academic questions. To inform research and policymaking upon a clear understanding of model capabilities, we publicly release HLE at https://lastexam.ai.

cs.LG↗

arXiv2026

Domain-Prior-Regularized Graph Modeling for Anomaly Detection in Cyber-Physical Systems

Anomaly detection on multivariate sensor time series is critical for industrial monitoring of cyber-physical systems (CPS), where even subtle deviations from normal behavior can indicate process disruption. Recent graph-based approaches have made significant progress, but they often struggle in small-scale physical systems with scarce labeled anomalies and limited normal data. In such settings, graph-based models tend to capture spurious correlations and produce unstable sensor topologies. We propose DPR-GM (Domain-Prior-Regularized Graph Modeling), a forecasting-based framework that incorporates system design knowledge into graph construction. DPR-GM leverages a large language model (LLM) to extract directed physical couplings between sensor pairs from system documentation, which are encoded as a binary domain adjacency matrix serving as a structural gate over sensor relations. This gate is then modulated by Pearson correlations estimated from normal training data. The anomaly score is further weighted by sensor-level reliability derived from the coefficient of variation. All graph and weighting components are fixed prior to training and add no learnable parameters. On the SKAB benchmark, DPR-GM outperforms graph-based, statistical, and deep learning baselines across F1, AUROC, and AUPRC, showing that domain-structured graph priors are a practical alternative to fully learned topologies in data-scarce CPS.

cs.LG↗

arXiv2026

Domain Adaptation with Adaptive Imagination for Visual Reinforcement Learning under Limited Target Data

Sim-to-real transfer remains a major obstacle for reinforcement learning (RL), especially for vision-based control where image observations exacerbate the state-distribution shift between simulation and the real world. Domain adaptation (DA) is a promising remedy for this challenge. Prior sim-to-real DA works have demonstrated encouraging results, yet these approaches typically assume substantially more target data, which is not available in practice. Indeed, their performance degrades significantly when the target data budget is reduced. To address this challenge, we propose AIDA (Adaptive Imagination for Domain Adaptation), a domain adaptation framework for visual reinforcement learning that addresses sim-to-real transfer under scarce target data without requiring additional interaction with the target environment. Our key idea is adaptive imagination: generating reliable and semantic imagination rollouts to augment limited target data. Specifically, AIDA employs a distribution-shift-aware discriminator that truncates rollouts when imagined transitions drift into low-confidence regions, so that only reliable transitions contribute to the augmentation. On these reliable transitions, AIDA introduces a self-consistency loss that cycles through state -> image observation -> state, penalizing discrepancies between the original and reconstructed states. This provides additional adaptation signals beyond the scarce target data. Our experiments demonstrate that adaptive imagination effectively truncates unreliable rollouts. By enforcing a self-consistency loss on the resulting reliable transitions, AIDA learns semantically meaningful state representations and outperforms baselines across five MuJoCo tasks and two Gymnasium-Robotics tasks.

cs.AI↗

arXiv2026

Redefining Maritime Anomaly Detection via Equation-Grounded Synthetic Anomalies

Maritime anomaly detection is essential for ensuring maritime safety, security, and efficient traffic management at sea, with Automatic Identification System (AIS) data serving as a primary data source. Despite its importance, most publicly available AIS datasets lack predefined anomaly labels, forcing prior studies to rely on either distribution-based rarity or domain rule/expert-assisted labeling. These approaches, however, face fundamental limitations: statistical rarity often fails to reflect practically critical events, while expert-based labeling is costly, subjective, and difficult to scale. Moreover, both paradigms tend to overlook interaction-driven hazards such as near-miss approaches between vessels. To address these challenges, we propose an equation-grounded anomaly taxonomy that is implementable under a limited AIS observation schema and extensible to other AIS datasets. Specifically, the taxonomy defines three anomaly types: unexpected AIS activity (A1), route deviation (A2), and close approach (A3), covering both single-vessel and inter-vessel anomalies. Building on this taxonomy, we introduce a unified score-synthesize-label pipeline that produces LLM-guided plausibility scores, uses them to synthesize anomalies, and assigns timestamp-level labels. To rigorously assess detection performance, we further design benchmark evaluation settings that account for variations in temporal-window length and anomaly-type composition, and evaluate a broad range of time-series models and anomaly detection models. Together, these contributions provide a systematic basis for evaluating maritime anomaly detection methods across different anomaly types. Our code is available at https://github.com/snudial/open-maritime-anomaly-detection.

cs.LG↗

arXiv2026

ContractEval: A Benchmark for Evaluating Contract-Satisfying Assertions in Code Generation

Current code generation evaluation measures functional correctness on well-formed inputs that satisfy all input preconditions. This paradigm has a critical limitation: task descriptions often leave these preconditions implicit, while evaluation filters out inputs that violate them. As a result, generated code may achieve high pass@k scores while failing to enforce the preconditions that the task actually requires. To address this gap, we introduce ContractEval, a benchmark for evaluating whether generated code enforces such preconditions--commonly referred to as contracts. Built on HumanEval+ and MBPP+, ContractEval consists of 364 tasks, each with three components: (i) descriptions reconstructed to explicitly state the contracts, (ii) test cases synthesized through a neuro-symbolic pipeline that pairs an LLM with an SMT solver to evaluate whether generated code satisfies these contracts, and (iii) reference code combined with contracts. Using ContractEval to evaluate five representative open-source code LLMs, we reveal a stark disparity between functional correctness and contract satisfaction. Under standard prompting, these models achieve pass@1 of 75-82% with 0% contract satisfaction. Even when contracts are explicitly stated in the prompt, the satisfaction rate reaches only 23-41%. This indicates that current LLMs struggle to satisfy contracts in their generated code, establishing contract satisfaction as a crucial and previously overlooked axis of code generation quality. Our code is available at https://github.com/suhanmen/ContractEval.

cs.AI↗

arXiv2026

Occlusion-Aware Multimodal Beam Prediction and Pose Estimation for mmWave V2I

We propose an occlusion-aware multimodal learning framework that is inspired by simultaneous localization and mapping (SLAM) concepts for trajectory interpretation and pose prediction. Targeting mmWave vehicle-to-infrastructure (V2I) beam management under dynamic blockage, our Transformer-based fusion network ingests synchronized RGB images, LiDAR point clouds, radar range-angle maps, GNSS, and short-term mmWave power history. It jointly predicts the receive beam index, blockage probability, and 2D position using labels automatically derived from 64-beam sweep power vectors, while an offline LiDAR map enables SLAM-style trajectory visualization. On the 60 GHz DeepSense 6G Scenario 31 dataset, the model achieves 50.92\% Top-1 and 86.50\% Top-3 beam accuracy with 0.018 bits/s/Hz spectral-efficiency loss, 63.35\% blocked-class F1, and 1.33m position RMSE. Multimodal fusion outperforms radio-only and strong camera-only baselines, showing the value of coupling perception and communication for future 6G V2I systems.

eess.SP↗

arXiv2026

Sensing-Assisted Adaptive Beam Probing with Calibrated Multimodal Priors and Uncertainty-Aware Scheduling

Highly directional mmWave/THz links require rapid beam alignment, yet exhaustive codebook sweeps incur prohibitive training overhead. This letter proposes a sensing-assisted adaptive probing policy that maps multimodal sensing (radar/LiDAR/camera) to a calibrated prior over beams, predicts per-beam reward with a deep Q-ensemble whose disagreement serves as a practical epistemic-uncertainty proxy, and schedules a small probe set using a Prior-Q upper-confidence score. The probing budget is adapted from prior entropy, explicitly coupling sensing confidence to communication overhead, while a margin-based safety rule prevents low signal-to-noise ratio (SNR) locks. Experiments on DeepSense-6G (train: scenarios 42 and 44; test:43) with a 21-beam discrete Fourier transform (DFT) codebook achieve Top-1/Top-3 of 0.81/0.99 with expected beam probe of 2 per sweep and zero observed outages at θ = 0 dB with margin Δ = 3 dB. The results show that multimodal priors with ensemble uncertainty match link quality and improve reliability compared to ablations while cutting overhead with better predictive model.

eess.SP↗

arXiv2026

Environment-aware Near-field UE Tracking under Partial Blockage and Reflection

This paper proposes an environment-aware near-field (NF) user equipment (UE) tracking method for extremely large aperture arrays. By integrating known surface geometries and tracking the line-of-sight (LOS) and non-line-of-sight (NLOS) indicators per antenna element, the method captures partial blockages and reflections specific to the NF spherical-wavefront regime, which are unavailable under the conventional far-field (FF) assumption. The UE positions are tracked by maximizing the cosine similarity between the predicted and received channels, enabling tracking even under complete LOS obstruction. Simulation results confirm that increasing environment-awareness improves accuracy, and that NF consistently outperforms FF baselines, achieving a $0.22\,\mathrm{m}$ root-mean-square error with full environment-awareness.

eess.SP↗

arXiv2026

I Dropped a Neural Net

A recent Dwarkesh Patel podcast with John Collison and Elon Musk featured an interesting puzzle from Jane Street: they trained a neural net, shuffled all 96 layers, and asked to put them back in order. Given unlabelled layers of a Residual Network and its training dataset, we recover the exact ordering of the layers. The problem decomposes into pairing each block's input and output projections ($48!$ possibilities) and ordering the reassembled blocks ($48!$ possibilities), for a combined search space of $(48!)^2 \approx 10^{122}$, which is more than the atoms in the observable universe. We show that stability conditions during training like dynamic isometry leave the product $W_{\text{out}} W_{\text{in}}$ for correctly paired layers with a negative diagonal structure, allowing us to use diagonal dominance ratio as a signal for pairing. For ordering, we seed-initialize with a rough proxy such as delta-norm or $\|W_{\text{out}}\|_F$ then hill-climb to zero mean squared error.

cs.LG↗

arXiv2026

System-Level Comparison of Multimodal and In-Band mmWave Sensing for Beam Prediction in 6G ISAC

Integrated sensing and communication (ISAC) can reduce beam-training overhead in mmWave vehicle-to-infrastructure (V2I) links by enabling in-band sensing-based beam prediction, while exteroceptive sensors can further enhance the prediction accuracy. This work develop a system-level framework that evaluates camera, LiDAR, radar, GPS, and in-band mmWave power, both individually and in multimodal fusion using the DeepSense-6G Scenario-33 dataset. A latency-aware neural network composed of lightweight convolutional (CNN) and multilayer-perceptron (MLP) encoders predict a 64-beam index. We assess performance using Top-k accuracy alongside spectral-efficiency (SE) gap, signal-to-noise-ratio (SNR) gap, rate loss, and end-to-end latency. Results show that the mmWave power vector is a strong standalone predictor, and fusing exteroceptive sensors with it preserves high performance: mmWave alone and mmWave+LiDAR/GPS/Radar achieve 98% Top-5 accuracy, while mmWave+camera achieves 94% Top-5 accuracy. The proposed framework establishes calibrated baselines for 6G ISAC-assisted beam prediction in V2I systems.

eess.SP↗

arXiv2025

Spatio-Temporal Graphs Beyond Grids: Benchmark for Maritime Anomaly Detection

Spatio-temporal graph neural networks (ST-GNNs) have achieved notable success in structured domains such as road traffic and public transportation, where spatial entities can be naturally represented as fixed nodes. In contrast, many real-world systems including maritime traffic lack such fixed anchors, making the construction of spatio-temporal graphs a fundamental challenge. Anomaly detection in these non-grid environments is particularly difficult due to the absence of canonical reference points, the sparsity and irregularity of trajectories, and the fact that anomalies may manifest at multiple granularities. In this work, we introduce a novel benchmark dataset for anomaly detection in the maritime domain, extending the Open Maritime Traffic Analysis Dataset (OMTAD) into a benchmark tailored for graph-based anomaly detection. Our dataset enables systematic evaluation across three different granularities: node-level, edge-level, and graph-level anomalies. We plan to employ two specialized LLM-based agents: \emph{Trajectory Synthesizer} and \emph{Anomaly Injector} to construct richer interaction contexts and generate semantically meaningful anomalies. We expect this benchmark to promote reproducibility and to foster methodological advances in anomaly detection for non-grid spatio-temporal systems.

cs.LG↗

arXiv2025

Mobility-Aware Localization in mmWave Channel: Adaptive Hybrid Filtering Approach

Precise user localization and tracking enhances energy-efficient and ultra-reliable low latency applications in the next generation wireless networks. In addition to computational complexity and data association challenges with Kalman-filter localization techniques, estimation errors tend to grow as the user's trajectory speed increases. By exploiting mmWave signals for joint sensing and communication, our approach dispenses with additional sensors adopted in most techniques while retaining high resolution spatial cues. We present a hybrid mobility-aware adaptive framework that selects the Extended Kalman filter at pedestrian speed and the Unscented Kalman filter at vehicular speed. The scheme mitigates data-association problem and estimation errors through adaptive noise scaling, chi-square gating, Rauch-Tung-Striebel smoothing. Evaluations using Absolute Trajectory Error, Relative Pose Error, Normalized Estimated Error Squared and Root Mean Square Error metrics demonstrate roughly 30-60% improvement in their respective regimes indicating a clear advantage over existing approaches tailored to either indoor or static settings.

eess.SP↗

arXiv2025

SAGE:Specification-Aware Grammar Extraction for Automated Test Case Generation with LLMs

Grammar-based test case generation has proven effective for competitive programming problems, but generating valid and general grammars from natural language specifications remains a key challenge, especially under limited supervision. Context-Free Grammars with Counters (CCFGs) have recently been introduced as a formalism to represent such specifications with logical constraints by storing and reusing counter values during derivation. In this work, we explore the use of open-source large language models (LLMs) to induce CCFGs from specifications using a small number of labeled examples and verifiable reward-guided reinforcement learning. Our approach first fine-tunes an open-source LLM to perform specification-to-grammar translation, and further applies Group Relative Policy Optimization (GRPO) to enhance grammar validity and generality. We also examine the effectiveness of iterative feedback for open and closed-source LLMs in correcting syntactic and semantic errors in generated grammars. Experimental results show that our approach SAGE achieves stronger generalization and outperforms 17 open and closed-source LLMs in both grammar quality and test effectiveness, improving over the state-of-the-art by 15.92%p in grammar validity and 12.34%p in test effectiveness. We provide our implementation and dataset at the following anonymous repository:https://anonymous.4open.science/r/SAGE-5714

cs.CL↗

arXiv2025

DropGaussian: Structural Regularization for Sparse-view Gaussian Splatting

Recently, 3D Gaussian splatting (3DGS) has gained considerable attentions in the field of novel view synthesis due to its fast performance while yielding the excellent image quality. However, 3DGS in sparse-view settings (e.g., three-view inputs) often faces with the problem of overfitting to training views, which significantly drops the visual quality of novel view images. Many existing approaches have tackled this issue by using strong priors, such as 2D generative contextual information and external depth signals. In contrast, this paper introduces a prior-free method, so-called DropGaussian, with simple changes in 3D Gaussian splatting. Specifically, we randomly remove Gaussians during the training process in a similar way of dropout, which allows non-excluded Gaussians to have larger gradients while improving their visibility. This makes the remaining Gaussians to contribute more to the optimization process for rendering with sparse input views. Such simple operation effectively alleviates the overfitting problem and enhances the quality of novel view synthesis. By simply applying DropGaussian to the original 3DGS framework, we can achieve the competitive performance with existing prior-based 3DGS methods in sparse-view settings of benchmark datasets without any additional complexity. The code and model are publicly available at: https://github.com/DCVL-3D/DropGaussian release.

cs.CV↗

arXiv2025

SPECTra: Scalable Multi-Agent Reinforcement Learning with Permutation-Free Networks

In cooperative multi-agent reinforcement learning (MARL), the permutation problem where the state space grows exponentially with the number of agents reduces sample efficiency. Additionally, many existing architectures struggle with scalability, relying on a fixed structure tied to a specific number of agents, limiting their applicability to environments with a variable number of entities. While approaches such as graph neural networks (GNNs) and self-attention mechanisms have progressed in addressing these challenges, they have significant limitations as dense GNNs and self-attention mechanisms incur high computational costs. To overcome these limitations, we propose a novel agent network and a non-linear mixing network that ensure permutation-equivariance and scalability, allowing them to generalize to environments with various numbers of agents. Our agent network significantly reduces computational complexity, and our scalable hypernetwork enables efficient weight generation for non-linear mixing. Additionally, we introduce curriculum learning to improve training efficiency. Experiments on SMACv2 and Google Research Football (GRF) demonstrate that our approach achieves superior learning performance compared to existing methods. By addressing both permutation-invariance and scalability in MARL, our work provides a more efficient and adaptable framework for cooperative MARL. Our code is available at https://github.com/funny-rl/SPECTra.

cs.LG↗