arXiv subjects

Yang Yang

Publications and source records attributed to Yang Yang.

At least 19 recordsLinked to original sources

arXiv2026

Agent Planning Benchmark: A Diagnostic Framework for Planning Capabilities in LLM Agents

Planning is central to LLM agents: before acting, an agent must decompose goals, select tools, reason over constraints, and decide when a task is infeasible. Yet existing agent evaluations often report only end-to-end success, making it difficult to determine whether failures stem from planning or execution. We introduce Agent Planning Benchmark (APB), a planning-specific diagnostic benchmark with 4,209 multimodal cases across 22 domains and five settings, covering holistic planning, feedback-conditioned step-wise planning, and robustness under extraneous tools, broken tools, and unsolvable tasks. Across 12 MLLMs, APB reveals systematic weaknesses in long-horizon planning, tool-noise robustness, calibrated refusal, and inference-time refinement. We further validate APB on 200 ToolSandbox tasks and 200 $τ^2$-bench tasks, where APB-guided refinement consistently improves plan correctness, plan grade, and downstream execution metrics across three representative models. APB thus serves as an upstream diagnostic complement to execution benchmarks. The APB benchmark and code are available in \href{https://github.com/Mikivishy/AgentPlanningBenchmark}{this URL}.

cs.CL↗

arXiv2026

Non-split groups of Lie type and iSchur algebras with unequal parameters

We present a geometric framework for realizing quantum Schur algebras with unequal parameters, via constructible sheaves on flag varieties arising from non-split groups of Lie type. In the special cases of general unitary groups and minus-type orthogonal groups, this framework yields the iSchur algebras with unequal parameters, which are closely related to the quasi-split iquantum groups of type AIII. Such a geometric realization enables the construction of canonical bases, integral forms, and monoidal categorification for these unequal-parameter iSchur algebras and the corresponding iquantum groups. This material is not a formal generalization from the equal-parameter case to the unequal-parameter case. A nontrivial arithmetic structure is imposed on the geometric structure of split groups, giving rise to many new phenomena. For example, the support varieties of generators of an integral form may not be rationally smooth, the categorification is provided by the category of descent data of semisimple complexes fixed by the twisted Frobenius, and the positivity of the canonical basis is established using a refined covering.

math.RT↗

arXiv2026

VerifiedLab: Harnessing Knowns for Unknowns

Across human history, knowledge has undergone several transitions, from orality to writing and then to digital archives. At each transition, humans established new conventions to preserve knowledge for the new era. Nowadays, as research agents are increasingly deployed for laboratory experiments, knowledge is crossing another boundary: from records written for humans to those for machines. In this work, we introduce VerifiedLab, a multi-agent harness framework for this human-to-machine transition of knowledge. VerifiedLab transforms research output from passive artifacts into active systems that accelerate downstream use, adoption and prediction of future trends. In VerifiedLab, a team of AI scientists with distinct roles reasons over records verified field by field: a principal investigator plans, a librarian computes the evidence directly from the records, specialists draft, and a gate and a critic check each claim against the measured reliability of its data before the harness decides whether to release or withhold it. We demonstrate the efficacy of VerifiedLab through extensive experiments on perovskite solar cells: VerifiedLab recovers known physical trends, anticipates devices reported a year later, and lets AI scientists inherit the literature together with a measure of how far it can be trusted. By scaling the inference-time verification compute, VerifiedLab introduces a new pathway for knowledge dissemination and machine harness for AI co-scientists.

cs.AI↗

arXiv2026

Parity-equivariant prediction of conformer-resolved electronic circular dichroism spectra accelerates absolute configuration assignment

Electronic circular dichroism (ECD) is a key experimental probe for assigning the absolute configuration of chiral molecules, but interpreting measured spectra often requires costly time-dependent density functional theory (TDDFT) calculations. The few existing machine learning methods for ECD prediction are faster, but their accuracy still falls well short of that required for experimental applications. Here we introduce PhysECD, a parity-aware E(3)-equivariant framework that builds the spectrum from its underlying quantum-chemical quantities, ensuring correct chiroptical symmetry by construction. To improve generalization and support experimental applications, we construct SCECD, a conformer-resolved dataset of 578,104 computed spectra spanning diverse natural products with one to five stereocentres. PhysECD predicts ECD spectra from conformer geometries in milliseconds, achieving state-of-the-art accuracy on the CMCDS benchmark and SCECD. Validation against 77 experimental spectra further demonstrates that PhysECD can serve as a fast alternative to TDDFT for assigning the absolute configuration of complex chiral molecules.

physics.chem-ph↗

arXiv2026

Magnetoelectric Exchange Spring for Spin-Wave Logic with Ultralow Energy Consumption

Spin waves (magnons) are intrinsically free of Joule heating during their propagation in magnets. Exploring, understanding, and manipulating such quasiparticles not only helps reveal the exotic magnonic phenomena in condensed matter physics but also underpins the development of information devices with low energy consumption. However, achieving low-power and scalable control of spin-wave propagation remains a critical challenge. Herein, a magnetoelectric exchange spring has been artificially designed and constructed across an interface between ferroelectric BaTiO3 and ferromagnetic (La,Sr)MnO3 with low magnetic damping, in which polarization-modulated orbital reconstruction tailors local magnetic anisotropy and enables reversible control of spin-wave propagation. By successfully deviating from the Janovec-Kay-Dunn law, reversal polarization of engineered BaTiO3 (Ps~1.2 uC cm^-2, Vc~0.4 V) is sufficient to switch the coherent magnon transport in the (La,Sr)MnO3, indicating the magnetoelectric heterointerface may serve as a promising candidate for atto-joule control of spin-wave propagation (normalized to a 10*10 nm^2 device). Furthermore, taking advantage of amplitude, phase, and frequency to encode spin waves, all 16 compact Boolean logics with ultralow energy consumption have been designed. The artificial magnetoelectric exchange spring can be broadly applicable to various material choices, offering a versatile platform for developing energy-efficient and integrated magnonic devices.

cond-mat.mtrl-sci↗

arXiv2026

MedAdaptAgent: An Automatic Harness for Adapting Medical Imaging Models to New Sites

Reusing pretrained medical-imaging models offers an alternative to training from scratch. A model trained for the same task may perform poorly at a new hospital because imaging protocols and preprocessing differ. Effective adaptation depends on the model architecture, domain shift, and available labels and compute. Adaptation can improve scores on a small labeled set yet reduce performance on unseen data. We present MedAdaptAgent, an automatic harness that turns a supplied model, target data, and a free-text request into a new-site adaptation workflow. Its LLM-driven Adaptation Planner uses model-site evidence to choose compatible experiments and revise subsequent adjustments. The harness requires evidence of improvement over the pretrained model, then delivers the selected model as a complete, runnable package. Evaluation spans 26 segmentation and classification transfers across architectures and compute settings, with segmentation annotation budgets ranging from zero-shot transfer to few-shot adaptation. With 20 local annotations, mean segmentation Dice rises from 0.483 to 0.774 across 10 transfers, a 60.1% relative gain, with no harmful replacements. Mean classification AUROC rises from 0.810 to 0.837 across 13 transfers, a 3.4% relative gain. Comparing adapted models with the pretrained model reduces harmful classification replacements by 30.8% versus selecting the highest-scoring model on the available labels, using identical candidates. Seven public-model deployments demonstrate adaptation and reproducible package delivery across contrast and modality shifts. A CT-to-MRI study extends the evaluation to four LLM planners, including two open-weight models. We release the code on GitHub.

cs.CV↗

arXiv2026

Reinforcement Learning Done Right for Explicit Confidence Targets

Large language models (LLMs) can produce plausible but incorrect answers when they are uncertain, which can mislead users and undermine model reliability. Training models to abstain with reinforcement learning is a natural approach, but most existing methods use a fixed error penalty and therefore cannot adapt their behavior to different confidence requirements at inference time. We study \emph{explicit confidence targets}, where a user specifies a target $p$ in the prompt and the model directly chooses whether to answer or abstain, with the goal of achieving an accuracy of at least $p$ among answered questions. However, learning to respond to different confidence targets with a single model has proven difficult, and prior attempts have failed to distinguish different targets. We show that this failure comes from two problems: the reward signal that distinguishes different values of $p$ is often lost during optimization, while the original error penalty grows without bound as $p$ approaches one. We propose RLEC (\textbf{R}einforcement \textbf{L}earning with \textbf{E}xplicit \textbf{C}onfidence Targets), which preserves the learning signal needed to distinguish confidence targets, introduces a stable reward family that keeps the desired answer condition unchanged, and uses reward scheduling to balance effective learning and training stability. Together, these designs enable the first successful training of a single LLM for explicit confidence target control. Extensive experiments across diverse benchmarks and model scales show that RLEC largely preserves general capabilities and achieves competitive calibration performance. RLEC also supports fine-grained target control without an external decision system or threshold calibration after training. By making explicit confidence targets part of the trained policy, RLEC opens a new and more direct path toward behavioral calibration.

cs.LG↗

arXiv2026

CohortFlow: A Steerable Clinical Cohort Curation Agent with Localized Semantic Correction

Language model agents for clinical cohort curation should accommodate evolving eligibility criteria without repeatedly processing unchanged requirements. We introduce CohortFlow, a steerable agent that represents natural language corrections as localized updates to a structured cohort specification and reconciles them with a persistent execution graph. Explicitly recorded semantic dependencies enable affected computations to be selectively invalidated while preserving valid prior results. On 100 scenarios derived from clinical-trial eligibility criteria, comprising 126 correction turns, localized steering achieves 77.0% requirement micro-F1 versus 76.4% for full regeneration using the same 8B model, a small numerical advantage that is not statistically significant ($p=0.493$). It reduces mean correction latency by 64.8% after completion and 44.3% during execution, with 38.1% fewer model calls. In a separate proof-of-concept evaluation over MIMIC, all 13 cohort states execute successfully, while correction trajectories demonstrate selective preservation of unaffected computations and recomputation of changed or dependent nodes. Together, these results show that localized semantic steering can substantially reduce correction latency and model calls while maintaining strong requirement-level accuracy.

cs.AI↗

arXiv2026

Local Epistemic Uncertainty Guided Active Sampling for Plug-and-play Diffusive Image Restoration

Diffusion models have demonstrated remarkable effectiveness in image restoration tasks. However, when guiding image reconstruction, existing Diffusion Model-based Image Restoration (DMIR) methods typically rely on fixed data constraints and uniform step sizes, thereby overlooking the dynamic nature of the generative process. Such rigid designs render the models vulnerable to spatially non-uniform degradations, thus resulting in structural distortions and loss of fine details. Meanwhile, uniform step sizes introduce computational redundancy, whereas naïve step reduction strategies tend to accumulate approximation errors. To address these limitations, we propose a Local Epistemic Uncertainty Guided Active Sampling framework (LEADer). In the spatial domain, LEADer leverages pixel-wise uncertainty to dynamically modulate the prior strength within the null space, which effectively balances detail preservation and artifact suppression. In the temporal domain, it quantifies sampling stability via the uncertainty trace to enable adaptive trajectory pruning, thereby accelerating convergence. Theoretical proofs demonstrate that our framework achieves strict data consistency, while the trajectory pruning strategy admits a deterministic error bound, thereby guaranteeing stable convergence under skip sampling. Notably, our plug-and-play method can be seamlessly integrated into various DMIR baselines. Extensive experiments show that LEADer improves the performance of multiple state-of-the-art DMIR methods, while significantly reducing sampling time with negligible memory overhead. Code is available at https://www.jiaqizhang-sengoku.com/Code/LEADer.

cs.CV↗

arXiv2026

Characters and Polynomiality for Maximal Parabolic Unipotent Radicals in Finite Classical Groups

Characters and Polynomiality for Maximal Parabolic Unipotent Radicals in Finite Classical GroupsLet $q$ be a power of an odd prime. For the unipotent radicals of maximal rational parabolic subgroups of the finite symplectic, orthogonal and unitary groups, we determine all complex irreducible characters, their values, and the number of characters of each degree. Each of these numbers is a polynomial in $q-1$ with nonnegative integer coefficients, in analogy with a conjecture of Isaacs for unitriangular groups. For the orthogonal radicals, the character table and the power maps do not depend on the Witt type of the residual form, whereas the isomorphism type of the radical does when the isotropic dimension is at least three and the residual dimension is positive and even. Consequently, for $3\le a\le n-1$ the radicals of the stabilizers of totally isotropic $a$-spaces in $\SO^+_{2n}(q)$ and $\SO^-_{2n}(q)$ form Brauer pairs; for $a\le n-2$ both stabilizers are maximal parabolic subgroups. Finally, we express the multiplicities through $R$-polynomials, with the unequal parameters $q^2,\dots,q^2,q$ in the unitary case.

math.RT↗

arXiv2026

HRoPE: Homography Relative Positional Encoding

Geometric Relative Positional Encoding has become the primary mechanism for injecting spatial inductive biases into multi-view transformers. Existing designs condition attention on camera-level frustums or ray-marched depth, associating cross-view tokens through the sensor geometry. Such sensor-centric formulations, however, describe only where a token is observed from, leaving the rich surface geometry of the scene region depicted by the token. In this paper, we advocate a shift toward surface-aware positional encoding that explicitly grounds patch tokens in the geometry of physical surfaces. We introduce HRoPE, which represents the local geometry of each patch as a slanted 3D plane, following the slanted support-window assumption of classical multi-view stereo. We inject token-level, plane-induced homographies into attention as relative transformations. This equips the transformer with a geometric prior for rectifying perspective distortions and aligning patch features across viewpoints. Our encoding requires no ground-truth geometry: the plane parameters can be predicted end-to-end under a view-synthesis objective alone, or derived from foundation models. Extensive experiments on RealEstate10K, CO3Dv2, and DL3DV show that our best variant of HRoPE consistently outperforms the evaluated geometric positional encodings for novel view synthesis. Extensive ablations and analysis show the effectiveness of the proposed encoding. Please refer to our project page at: https://gaohchen.github.io/HRoPE

cs.CV↗

arXiv2026

Sage-A1.5: From Long-Horizon Execution to Scientific Exploration with Capability Composition

In this report, we introduce Sage-A1.5, a 35B Mixture-of-Experts agentic model that builds on A1 to advance long-horizon problem solving through adaptive capability composition. Compared with A1, Sage-A1.5 learns not only to solve individual tasks, but also to organize work and revise its approach during execution. Sage-A1.5 highlights three improvements: agentic orchestration, verification, and open scientific discovery. First, agentic orchestration extends single-agent execution through task delegation and parallel collaboration among subagents with isolated contexts, enabling complex tasks to be decomposed and addressed concurrently and supporting efficient execution while reducing interference across concurrent subagents. Second, agentic verification strengthens long-horizon reliability through progress checking, evidence validation, and reflective strategy revision, allowing the agent to recognize unproductive search paths and pursue alternative approaches. Third, open scientific discovery extends agentic capabilities beyond answering predefined questions to conducting exploratory research, connecting scientific inquiry with interactive analysis and inspectable research artifacts. We showcase these capabilities through complicated agentic tasks and multidisciplinary scientific applications. Besides, we hope Sage-A1.5 provides the community with an accessible foundation for open scientific discovery, offering a practical path from long-horizon task execution to collaborative, verifiable, and inspectable scientific exploration.

cs.AI↗

arXiv2026

PartiGen: Part-Aware Representations for Language-Conditioned Humanoid Motion Generation

Translating language into humanoid motion requires coordinating body parts, determining motion duration, and producing references suitable for robot execution. We introduce PartiGen, a part-aware latent diffusion framework that incorporates anatomical structure into a shared whole-body motion representation. Part-specific attention processes anatomically masked frame features, and its outputs are fused to combine local limb information with whole-body context. Conditioned on text and motion history, the model generates motion primitives autoregressively. Forward-kinematics supervision encourages kinematic consistency, while a learned end-of-sequence predictor selects a frame-level endpoint after generation. On HumanML3D retargeted to the Unitree G1, PartiGen achieves a segment-level FID of 3.165, a 16.8% reduction over TextOp, and improves R@1 by 1.4 percentage points. In the duration study with 16-frame primitives, endpoint prediction reduces mean absolute duration error from 12.471 to 3.080 frames compared with a fixed-length cutoff. We further evaluate robot execution using a pretrained, frozen GRIT tracker: 409 of 500 generated references (81.8%) pass the posture-based stability screen in MuJoCo. Following simulation screening and manual selection, 26 of 27 attempted motions are judged successful on the real G1.

cs.RO↗

arXiv2026

On the Adversarial Robustness of Hydrological Models

The evaluation of hydrological models is essential for both model selection and reliability assessment. However, simply comparing predictions to observations is insufficient for understanding the global landscape of model behavior. This is especially true for many deep learning models, whose structures are complex. Further, in risk-averse operational settings, water managers require models that are trustworthy and provably safe, as non-robustness can put our critical infrastructure at risk. Motivated by the need to select reliable models for operational deployment, we introduce and explore adversarial robustness analysis in hydrological modeling, evaluating whether small, targeted perturbations to meteorological forcings induce substantial changes in simulated discharge. We compare physical-conceptual and deep learning-based hydrological models across 1,347 German catchments under perturbations of varying magnitudes, using the fast gradient sign method (FGSM). We find that, as expected, the FGSM perturbations systematically reduce KGE and increase MSE. However, catastrophic failure is rare and, surprisingly, LSTMs generally demonstrate greater robustness than HBV models. Further, changes in both the predicted hydrographs and the internal model states often respond approximately linearly (at least locally) as perturbation size increases, providing a compact summary of how errors grow under such perturbations. Similar patterns are also observed for random perturbations, suggesting that small input changes usually introduce approximately proportional changes in model output. Overall, these findings support further consideration of LSTMs for operational deployment (due both to their predictive power and robustness), and motivate future work on both characterizing model responses to input changes and improving robustness through architectural modifications and training design.

physics.geo-ph↗

arXiv2026

Constrained Nuclear-Electronic Orbital Time-Dependent Density Functional Theory for Excited-State Dynamics with Nuclear Quantum Effects

Nuclear quantum effects can strongly influence excited-state processes involving light nuclei, yet their inclusion in practical molecular dynamics remains challenging. We develop constrained nuclear-electronic orbital time-dependent density functional theory (CNEO-TDDFT), which incorporates quantum-nuclear delocalization into full-dimensional effective excited-state potential energy surfaces while retaining the formal structure and computational scaling of conventional TDDFT. Analytic gradients are also developed, enabling efficient on-the-fly excited-state dynamics. CNEO-TDDFT substantially improves excited-state vibrational frequencies involving hydrogen motion and reduces the root-mean-square deviation from experiment from 113 cm$^{-1}$ to 26 cm$^{-1}$. For excited-state proton transfer in 10-hydroxybenzo[h]quinoline (HBQ), CNEO-TDDFT yields a characteristic transfer time of 14.0 fs, compared with 25.5 fs from conventional TDDFT, consistent with the experimentally inferred ultrafast timescale of 12$\pm$6 fs. These results establish CNEO-TDDFT as an accurate and efficient framework for excited-state dynamics with nuclear quantum effects.

physics.chem-ph↗

arXiv2026

Size-Dependent High-Order Harmonic Generation from Linear Carbon-Chain Molecules in Linearly Polarized Laser Fields

High-order harmonic generation from molecules is highly sensitive to molecular geometry and strong-field electron dynamics, providing a powerful route for probing and controlling ultrafast processes in extended systems. In this work, we systematically investigate the influence of molecular chain length on HHG from linear carbon-chain molecules C$_2$H$_2$, C$_6$H$_2$, and C$_{10}$H$_2$ driven by an 800 nm linearly polarized laser field. To isolate the molecular-size effect from the influence of different ionization potentials, the laser intensities are adjusted to maintain the same Keldysh parameter for different molecules. Real-time time-dependent density functional theory simulations are performed with the molecular axis aligned parallel to the laser polarization direction. The results show that increasing the molecular chain length significantly enhances the harmonic yield and tends to extend the cutoff region. In particular, C$_{10}$H$_2$ exhibits much stronger plateau harmonics than C$_2$H$_2$, while the intermediate molecule C$_6$H$_2$ shows harmonic intensities between those of C$_2$H$_2$ and C$_{10}$H$_2$. Time-frequency analysis and charge-density evolution reveal that the enhanced HHG emission in longer chains originates from the enlarged electron acceleration distance and increased probability of multi-center recollision, especially near the terminal carbon atoms. These findings demonstrate that molecular-size engineering offers an effective strategy for controlling harmonic emission and optimizing attosecond light sources in extended molecular systems.

quant-ph↗

arXiv2026

P2TPO: Structure-Aligned Page-to-Token Credit Assignment for Full-Page Document Parsing

End-to-end full-page document parsing must preserve the content and structure of heterogeneous elements, yet otherwise accurate outputs can contain local errors and omissions. A single page-level advantage does not explicitly identify which elements differ in quality across sampled outputs or where their errors occur. We introduce Page-to-Token Policy Optimization (P2TPO), a structure-aligned credit-assignment framework that operates on full-page policy trajectories. Reference-element alignment first associates block-level quality contrasts with generated spans. Unified Anchor Pricing (UAP) incorporates matched and missing element outcomes and provides feedback relative to a fixed quality ceiling when sampled outputs receive identical but imperfect scores for a reference element. Within matched blocks, Span Credit Redistribution (SCR) redistributes existing block credit according to aligned correct and erroneous spans, using boundary proxies for within-block omissions while preserving the total block-derived advantage across its tokens. Under a fixed-weight additive page utility, we show that element-indexed contrasts retain local quality differences that page-level aggregation can cancel out. In the main experimental comparison, P2TPO outperforms all evaluated policy optimization baselines in seed-averaged scores on each of the six document parsing benchmarks. Additional experiments demonstrate gains across model scales and initializations.

cs.LG↗

arXiv2026

LightMedSeg-ISLES: Stroke Lesion Segmentation with 81x Fewer Parameters than nnU-Net

Large networks and ensembles often lead medical image segmentation challenges, but their storage and inference demands complicate deployment. We present LightMedSeg-ISLES, a 1.26-million-parameter pipeline for T1-weighted stroke lesion segmentation in ISLES'26. On a 146-case held-out cohort, flip test-time augmentation produces 0.618 mean Dice and 0.599 lesion-wise F1. A 102.35-million-parameter nnU-Net ResEnc-L produces 0.634 Dice and 0.544 lesion-wise F1 after size filtering. LightMedSeg therefore retains 97.5\% of nnU-Net's Dice with 81.4$\times$ fewer parameters while improving lesion-wise F1 by 0.055. Its four-pass TTA operating point requires 4.7$\times$ fewer FLOPs per standardized patch than nnU-Net. It also slightly exceeds filtered UNETR++ and nnFormer. Longer training and stronger augmentation add 0.0358 Dice without increasing capacity, establishing a strong single-checkpoint alternative to much larger models.

cs.CV↗