Searcharxiv⌕ Search

arXiv subjects

Rose Yu

Publications and source records attributed to Rose Yu.

At least 19 recordsLinked to original sources

ACED-Bench: Evaluating How LLM Agents Acquire and Act on Causal Evidence

Large language models are increasingly used as scientific assistants, yet we still lack reliable ways to evaluate whether they can investigate a system rather than merely answer a prompt. A useful evaluation must let agents choose experiments, interpret finite evidence, and make causal decisions, while preserving objective ground truth. We introduce ACED (Active Causal Evidence and Decision Benchmark), a neuro-symbolic benchmark that separates the readable scientific surface from the formal causal world: natural-language scenarios describe the system, while a hidden causal model defines the data, the effect of every intervention, and the oracle answers. In ACED-Repair, agents diagnose a failing production system: within 15 experiments they must decide which controls to test, read confounded and filtered data, and recommend a fix, which we re-simulate on a hidden true objective. In ACED-Query, agents answer causal questions and make constrained causal decisions in worlds backed by categorical probabilistic graphical models. Acceptance on ACED-Repair ranges from 43% to 0% across 12 LLMs, while strong agents approach ceiling on ACED-Query's qualification questions. Tracing every experiment shows where investigations stop: most open-weight models test a true lever on its own in fewer than half of the worlds, the strongest models test the right levers but often miss the working dose or combination, and agents that do run a working fix almost always recommend it. No model reliably repairs systems with two independent causes or systems that need a subgroup-specific policy. These results suggest that reliable AI co-scientists need explicit support for choosing experiments, keeping track of evidence, and composing interventions. Code and data are available at https://github.com/Rose-STL-Lab/ACED-Bench.

cs.AI↗

Generative OOD-regularized Model-based Policy Optimization

We study sequential decision-making with offline reinforcement learning (RL). Traditional offline RL policies may result in out-of-distribution (OOD) actions when training relies only on sparse offline representations. To ensure safe offline policies in a sparse state-action space, we explore how density estimation models can be integrated into model-based RL methods to avoid OOD regions. Generative models are capable of explicitly modeling the density in sparse state-action spaces. Building on this, we introduce Generative OOD-regularized Model-based Policy Optimization (GORMPO), a density-regularized offline RL algorithm that uses generative density modeling to restrict policy updates to high-density areas of the dataset. Furthermore, we examine whether better OOD detection corresponds to better model-based offline policies. We compare (1) the OOD detection capabilities of various density estimators and (2) their performance within the GORMPO framework on a real-world medical dataset and sparse offline RL datasets. We provide theoretical guarantees bounding GORMPO's performance gap in terms of density estimation error, ensuring near-optimal policies under imperfect density estimates. Empirically, GORMPO remains competitive in reward and improves clinical metrics compared to state-of-the-art clinical RL models, and outperforms state-of-the-art offline RL models in offline RL benchmarks. Our empirical findings show that better OOD detection generally results in improved policies in environments with stable dynamics, while conservative penalties with poor density estimation are favored when dynamics are uncertain. Code, checkpoints, sparse, and OOD D4RL datasets are available at https://github.com/Rose-STL-Lab/GORMPO.

cs.LG↗

EMMA: Structured Episodic Memory for Multi-Agent Workflow Synthesis

Deploying LLM agents in specialized domains often require fine-grained task-specific procedures and knowledge a general model lacks, yet parameter training is costly and non-interpretable, and hand-engineered agent systems shift the cost to expert labor. Episodic memory updates at context level, but single agent adaptation struggles to alleviate cross-task interference, especially with complex tasks such as multi-application navigation or data pool analysis. Although multi-agent evolution alleviates this problem, existing methods lack clear definitions on update rules and rely on the backbone model to decide where and how much the system changes. This ill-scoped evolution makes learning follow the backbone's structural preferences rather than the observed failures: one backbone accumulates skills while another spawns agents. We present EMMA (structured Episodic Memory for Multi-Agent workflow synthesis), which treats the configuration of a multi-agent system (controller routing memory, specialists inheriting a generalist prompt, and per-step procedural skills) as episodic memory. EMMA makes the ownership and admissibility of updates explicit: a reflector assigns each diagnosed failure to the scope owning its correction and proposes one edit within it, and backbone-independent guards keep every accepted edit scoped, incremental and bounded. Across KramaBench, AppWorld and BBEH with five backbones and four baselines (ACE, GEPA, EvoMAS and ADAS), EMMA attains the best overall performance on every benchmark, up to 32.5% over the strongest baseline, maintains consistent improvements across backbones, and uses 17-38% fewer training executions than the most efficient baseline.

cs.MA↗

Zephyrus-R1: Agentic Reinforcement Learning for Weather Reporting

Reinforcement learning (RL) has emerged as a key method for training AI models in scientific applications, but RL remains difficult when outputs cannot easily be verified against a known ground-truth answer. Natural-language weather forecast reports are one such domain: they translate atmospheric data into assessments of weather evolution, hazards, and uncertainty for both the general public and key decision-makers. Unlike numerical weather-analysis questions, they admit many valid outputs, which limits deterministic verification. To address this, we develop Zephyrus-R1, a practical framework for RL on scientific weather forecast reporting. We focus on three key components of the agentic RL pipeline: reward design, curriculum learning, and an analysis of human-expert alignment. To encourage both report legibility and factual accuracy, we design a reward function that combines a meteorological rubric with bidirectional claim entailment, both evaluated against National Weather Service reference reports. Our framework optimizes this reward in a simulated tool-calling environment, enabling vision-language agents to gather and analyze forecast evidence across regions and lead times before producing a report. We use annotations from three meteorologists to audit the claim labels produced by our LLM judges. Finally, a curriculum helps small models first develop tool use and scientific reasoning through RL on verifiable weather-analysis questions, then optimize the open-ended report reward. After training Qwen3.5-4B with Zephyrus-R1, we improve the mean across six judge-metric scores by 26% over the base model and achieve results competitive with frontier open-weight models. For Qwen3.8-27B, we improve the same mean by 13% over the base model, by 6.7% over Kimi-K3, and by 2.7% over GPT-5.6-Luna.

cs.LG↗

Equilibrium Forcing: Adaptive Video Generation Without Noise Conditioning

Standard autoregressive video generation algorithms based on Diffusion and Flow Matching rely on rigid training objectives and static sampling schedules, limiting inference procedures from adapting to the data. We introduce Equilibrium Forcing (EqF), a simplified framework for video denoising generative models without noise level conditioning. EqF pioneers modular training- and inference-time designs for noise-unconditional generation that decouple learning the denoising field from sampling. This flexibility allows for inference-time algorithms that operate in a closed loop by adapting to feedback from the sample, improving video quality and consistency on challenging autoregressive video generation benchmarks. Extensive analysis elucidates exactly how removing the noise level conditioning enables EqF's data-dependent inference properties to surpass the performance of standard noise level-conditional denoising video methods.

cs.CV↗

VascuSR: Iterative Anatomy-Aware Diffusion for CT Super-Resolution

Generative super-resolution (SR) can recover sharp detail in computed tomography (CT) images from severely downsampled observations, but the missing high-frequency content is not uniquely determined by the low-resolution input. Consequently, visually plausible reconstructions may contain anatomically unsupported vascular detail, such as missing, spurious, or incorrectly connected vessels. To overcome this challenge, we introduce VascuSR, an iterative anatomy-aware diffusion framework that combines image reconstruction with explicit 3D vascular guidance. First, to provide richer anatomical guidance, we use an explicit 3D vascular representation that captures structural information beyond individual slices. This representation also simplifies vascular refinement by allowing a lightweight 3D generative refiner to focus on vascular structure rather than complex CT appearance. Second, to guide slice-wise SR, a lightweight anatomy controller injects the refined structure into the diffusion decoder, while iterative feedback updates this guidance from each new SR volume. On re-annotated MSD Task08 and HVM datasets, VascuSR outperforms interpolation and learning-based SR baselines in segmentation accuracy (Dice and clDice) and 3D vascular structure (connectivity and mean centerline distance), while maintaining image quality comparable to its SR backbone. Compared with learning-based baselines, VascuSR reduces class-averaged connected-component counts by over 20% on both datasets and mean centerline distance by over 10% on MSD.

cs.CV↗

ClimateBench v2.0: Probabilistic Climate Model Benchmarking

We present ClimateBench v2, a standardized protocol for evaluating climate models on diagnostics expected to be informative for their skill in projecting mid-century regional temperature and precipitation changes. The protocol is designed to evaluate any physics-based, data-driven, or hybrid climate model on equal footing using a common set of observational and out-of-distribution tests. We define three tiers of evaluation. Tier I establishes physical credibility through entry-ticket tests of energy conservation, coupled (co-)variability, and basic forced responses. Tier II scores models against post-2015 observations of surface temperature, precipitation, radiative fluxes, sea ice, and key modes of variability using fair CRPS as the primary probabilistic score, complemented by distributional and ensemble-consistency diagnostics. Tier III tests out-of-distribution generalization through paleoclimate simulations spanning the Last Interglacial, Last Glacial Maximum, and Mid-Holocene, and through perfect-model experiments in which data-driven models must predict the future climate of existing Earth system models from historical data alone. We reserve all observational data after 2015 for testing, and submissions must include multiple ensemble members to enable probabilistic evaluation. This reservation exploits a new opportunity provided by the decade of observations accumulated since the end of the CMIP6 historical experiment, which constitutes an out-of-sample record of forced climate change (and internal variability) for the current generation of models, and we quantify, in an idealized setting, the information it carries about mid-century warming. We provide the evaluation code, observational reference datasets, and perfect-model training data as an open benchmark to drive measurable progress in climate projection across all modeling approaches.

physics.ao-ph↗

MoGround: Measuring and Mitigating Modality Distraction in Vision-Language Models

We release MoGround, a vision-language dataset spanning four visual domains in which the answer to every question is guaranteed to be available from exactly one modality. This guarantee enables us to measure modality distraction, the failure in which a model answers a question correctly from one modality alone and then flips to a wrong answer once irrelevant content from the other modality is added. Existing probes rarely establish single-modality answerability this way, making it hard to isolate distraction in the first place. Across seven open-source VLMs, we find that modality distraction is not universal but model-dependent. The weaker-grounded modality is the more distracted one (r = +0.86), and distraction scales inversely with grounding strength (r = -0.90). The single-modality guarantee also enables a mitigation method that needs to distinguish between relevant and irrelevant context. Trained on one split of MoGround alone, a weight-space robustness vector reduces distraction on all seven models by 9% to 51%, at a cost of only 0.1 average points of accuracy on standard multimodal tasks.

cs.LG↗

Discovering Symmetries in Neural Network Parameter Spaces

Parameter space symmetries are important for understanding neural networks' loss landscape, training dynamics, and generalization. However, systematically identifying these symmetries remains a challenge. In this paper, we formalize data-dependent parameter symmetries and characterize loss invariance and the group-action axioms through infinitesimal conditions, which provide objectives for jointly learning group generators and nonlinear action maps. Our framework systematically uncovers parameter symmetries, including previously unknown ones. To study larger networks, we establish conditions under which subnetwork symmetries extend to the full model. The same construction gives an explicit family of finite-batch symmetries, providing both analytical examples and a foundation for discovery through small subnetworks. Using the infinitesimal characterization and subnetwork construction, we implement a framework for automated discovery of parameter symmetries, and successfully uncovered symmetries in various architectures, including pretrained transformer models.

cs.LG↗

Eluna: An Agentic LLM System for Automating Warehouse Operations with Reasoning and Task Execution

Warehouse operations are governed by Standard Operating Procedures (SOPs) that encode complex, multi-system decision logic, which must be executed reliably under strict time constraints, yet LLM agents lack mechanisms to enforce procedural compliance and degrade under the context overload full SOP specifications introduce. We present Eluna, a production-deployed agentic system for reliable SOP execution. Eluna is a graph-guided, multi-agent framework that encodes SOPs as directed acyclic graphs with progressive disclosure and delegates independent tasks to parallel sub-agents, each with persistent code execution and live data access. To meet production latency and accuracy needs, we use asymmetric episodic distillation where a strong teacher is improved through episodic error memories, then a smaller student is fine-tuned on the corrected trajectories with memory stripped, internalizing corrections without inference-time overhead. On a 13-task benchmark and two production applications, our fine-tuned models match or exceed their teacher, beat all larger off-the-shelf baselines, and reach 94% expert agreement on the ticket processing application.

cs.LG↗

SimulRAG: Simulator-based RAG for Grounding LLMs in Long-form Scientific QA

Large Language Models (LLMs) show promise in generating long-form scientific explanations that synthesize evidence and connect multiple factors. However, in long-form scientific question answering, LLMs often hallucinate, producing unsupported or inconsistent claims. Retrieval-Augmented Generation (RAG) improves trustworthiness by grounding generation in external sources; scientific simulators are valuable because they can validate quantitative hypotheses and capture evolving dynamics. Yet simulation-based RAG is non-trivial due to two challenges: how to retrieve from scientific simulators, and how to efficiently verify and update long-form answers. To overcome these challenges, we propose SimulRAG, a simulator-based RAG framework with a generalized retrieval interface that translates between text and simulator parameters/outputs. SimulRAG further introduces claim-level generation with uncertainty estimation and simulator boundary assessment (UE+SBA) to selectively verify and update claims. Unlike tool-first or holistic answer revision, it first elicits diverse answers without retrieval and then grounds uncertain, simulator-verifiable atomic claims with simulator evidence. We also release a long-form scientific QA benchmark spanning climate science, epidemiology, and urban planning, with ground truth verified by simulations and human annotators. Experiments show SimulRAG improves informativeness by 30.4% and factuality by 16.3% over the strongest adapted RAG baselines, while UE+SBA enhances claim-level efficiency and quality.

cs.CL↗

SimulCost: A Cost-Aware Benchmark and Toolkit for Automating Physics Simulations with LLMs

Evaluating LLM agents for scientific tasks has focused on token costs while ignoring tool-use costs like simulation time and experimental resources. As a result, metrics like pass@k become impractical under realistic budget constraints. To address this gap, we introduce SimulCost, the first benchmark targeting cost-sensitive parameter tuning in physics simulations. SimulCost compares LLM tuning cost-sensitive parameters against traditional scanning approach in both accuracy and computational cost, spanning 2,643 single-round (initial guess) and 2,304 multi-round (adjustment by trial-and-error) tasks across 11 simulators from fluid dynamics, solid mechanics, and plasma physics, whose costs are analytically defined and platform-independent. A twelfth simulator, a production plasma code measurable only by wall clock, is reported separately. Frontier LLMs achieve 45-62% success rates in single-round mode, dropping to 34-50% under high accuracy requirements, rendering their initial guesses unreliable especially for high accuracy tasks. Multi-round mode improves rates to 66-81%, but LLMs are 1.5-2.7x slower than traditional scanning, making them uneconomical choices. We also investigate parameter group correlations for knowledge transfer potential, and the impact of in-context examples and reasoning effort, providing practical implications for deployment and fine-tuning. We open-source SimulCost as a static benchmark and extensible toolkit to facilitate research on improving cost-aware agentic designs for physics simulations, and for expanding new simulation environments. Code and data are available at https://github.com/Rose-STL-Lab/SimulCost-Bench

physics.comp-ph↗

Emergence of Hierarchical Emotion Organization in Large Language Models

As large language models (LLMs) increasingly power conversational agents, understanding how they model users' emotional states is critical for ethical deployment. Inspired by emotion wheels, i.e., a psychological framework that argues emotions organize hierarchically, we analyze probabilistic dependencies between emotional states in model outputs. We find that LLMs naturally form hierarchical emotion trees that align with human psychological models, and larger models develop more complex hierarchies. We also uncover systematic biases in emotion recognition across socioeconomic personas, with compounding misclassifications for intersectional, underrepresented groups. Human studies reveal striking parallels, suggesting that LLMs internalize aspects of social perception. Beyond highlighting emergent emotional reasoning in LLMs, our results hint at the potential of using cognitively-grounded theories for developing better model evaluations.

cs.CL↗

Breaking the Factorization Barrier in Diffusion Language Models

Diffusion language models theoretically allow for efficient parallel generation but are practically hindered by the ``factorization barrier'': the assumption that simultaneously predicted tokens are independent. This limitation forces a trade-off: models must either sacrifice speed by resolving dependencies sequentially or suffer from incoherence due to factorization. We argue that this barrier arises not from limited backbone expressivity, but from a structural misspecification: models are restricted to fully factorized outputs because explicitly parameterizing a joint distribution would require the Transformer to output a prohibitively large number of parameters. We propose Coupled Discrete Diffusion (CoDD), a hybrid framework that breaks this barrier by replacing the fully-factorized output distribution with a lightweight, tractable probabilistic inference layer. This formulation yields a distribution family that is significantly more expressive than standard factorized priors, enabling the modeling of complex joint dependencies, yet remains compact enough to avoid the prohibitive parameter explosion associated with full joint modeling. Empirically, CoDD seamlessly enhances diverse diffusion language model architectures with negligible overhead, matching the reasoning performance of computationally intensive Reinforcement Learning baselines at a fraction of the training cost. Furthermore, it prevents performance collapse in few-step generation, enabling high-quality outputs at significantly reduced latencies. Code available at: https://github.com/liuanji/CoDD.

cs.LG↗

Demystifying Mergeability: Interpretable Properties to Predict Model Merging Success

Model merging combines knowledge from separately fine-tuned models, yet the factors driving its success remain poorly understood. While recent work treats mergeability as an intrinsic property of the models, we show with an architecture-agnostic framework that it fundamentally depends on both the merging method and the partner tasks. Using L1-regularized linear optimization over a set of interpretable pairwise metrics (e.g., gradient L_2 distance), we uncover properties correlating with post-merge normalized accuracy across five merging methods. We find architecture- and method-specific variation in success drivers (64.0% average top-5 metric overlap; 79.3% sign agreement), with certain methods, notably TIES, exhibiting distinct ``fingerprints'' that diverge from the broader consensus. Crucially, however, gradient alignment metrics consistently emerge as the most fundamental signals of compatibility. These findings provide a diagnostic foundation for understanding mergeability and motivate future merge-aware fine-tuning strategies.

cs.LG↗

U-Cast: A Surprisingly Simple and Efficient Frontier Probabilistic AI Weather Forecaster

AI-based weather forecasting now rivals traditional physics-based ensembles, but state-of-the-art (SOTA) models rely on specialized architectures and massive computational budgets, creating a high barrier to entry. We demonstrate that such complexity is unnecessary for frontier performance. We introduce \ours, a probabilistic forecaster built on a standard U-Net backbone trained with a simple recipe: deterministic pre-training on Mean Absolute Error followed by short probabilistic fine-tuning on the Continuous Ranked Probability Score (CRPS) using Monte Carlo Dropout for stochasticity. As a result, our model matches or exceeds the probabilistic skill of GenCast and IFS ENS at $1.5^\circ$ resolution while reducing training compute by over $10\times$ compared to leading CRPS-based models and inference latency by over $10\times$ compared to diffusion-based models. U-Cast trains in under 12 H200 GPU-days and generates a 15-day ensemble forecast in 3 seconds. These results suggest that scalable, general-purpose architectures paired with efficient training curricula can match complex domain-specific designs at a fraction of the cost, opening the training of frontier probabilistic weather models to the broader community.

cs.LG↗

Recursive Flow Matching

Generative models have emerged as a powerful paradigm for solving physics systems and modeling complex spatiotemporal dynamics. However, achieving high physical accuracy without incurring high computational cost remains a fundamental challenge, as existing approaches face a critical speed-fidelity trade-off. In this work, we introduce Recursive Flow Matching (RecFM), a generative framework for forecasting complex spatiotemporal dynamics. RecFM enforces self-consistency to align trajectories across discretization scales, reducing discretization errors and improving performance across metrics for physics-based tasks. To our knowledge, this is the first method to achieve high-fidelity one- and few-step (2-4 step) dynamic generation for scientific systems with performance comparable to state-of-the-art multi-step solvers. Across challenging scientific benchmarks, RecFM achieves up to a 20$\times$ speedup over leading diffusion-based emulators while improving predictive accuracy. Furthermore, RecFM reduces mean squared error by over 15% compared to vanilla flow matching, offering a scalable and efficient solution for real-time scientific emulation.

cs.LG↗

Calibrating LLMs with Semantic-level Reward

As large language models (LLMs) are deployed in consequential settings such as medical question answering and legal reasoning, the ability to estimate when their outputs are likely to be correct is essential for safe and reliable use, requiring well-calibrated uncertainty. Standard reinforcement learning with verifiable rewards (RLVR) trains models with a binary correctness reward that is indifferent to confidence, providing no penalty for confident but wrong predictions and thereby degrading calibration. Recent work addresses this by training models to produce verbalized confidence scores alongside answers and rewarding agreement with correctness. However, verbalized confidence is calibrated at the token level and thus exhibits inconsistency across textual variations with same semantic meaning. We propose \textbf{Calibration with Semantic Reward (CSR)}, a framework that calibrates language models directly in semantic space without a verbalized confidence interface. CSR combines the correctness reward with a novel semantic calibration reward that encourages exploitation among correct rollouts by promoting semantic agreement, and exploration among incorrect ones by discouraging spurious consistency. Experiments across three model families on HotpotQA (in-distribution) and TriviaQA, MSMARCO, and NQ-Open (out-of-distribution) show that CSR consistently achieves lower ECE and higher AUROC than verbalized-confidence baselines across nearly all settings, reducing ECE by up to $40\%$ and improving AUROC by up to $31\%$ over verbalized-confidence baselines, with calibration behavior generalizing robustly across all four evaluation settings.

cs.CL↗