arXiv subjects

Xin Liu

Publications and source records attributed to Xin Liu.

At least 37 records · Page 2Linked to original sources

arXiv2026

Choosing Before Acting: Comparative Value Estimation for Long-Horizon Tool-Use Agents

Large language models (LLMs) rely on long-horizon tool invocation sequences for complex tasks, where each invocation can alter the task state and condition subsequent decisions. In long-horizon tool use, final-outcome rewards provide weak credit assignment over long interaction traces. Step-level rewards can offer more targeted feedback, but obtaining reliable step supervision often requires human or LLM judgment, or additional rollouts to estimate the downstream effect of an intermediate decision. In this paper, we argue that effective tool-use agents should estimate the long-horizon value of a possible next tool invocation before executing it. This objective requires comparative supervision over alternative invocations under the same context, while logged trajectories only contain the invocation that was actually taken. Therefore, we propose Comparative Inference for Tool-use Agents (CITA). CITA trains a Comparative Inference Model (CIM) from paired signals that combine observed tool behavior, scalable supervision from a Bayesian tool-graph simulator, and semantic judgments from LLM-based comparison. The resulting CIM learns to estimate how likely a possible next tool invocation is to support final task success under the current context. Across three tool-use benchmarks and multiple backbone LLMs, CITA consistently improves Tool F1 and task success. Additional analysis shows that CIM learns accurate step-level value estimates for comparative tool choices.

cs.AI↗

arXiv2026

Training LLM Judges from Language Feedback via Position-Selective Self-Distillation

We study training LLM judges from natural language feedback, especially for subjective tasks where the verdict depends strongly on which evaluation criteria the judge invokes and how it weighs them. The dominant approach, outcome-supervised RL (e.g., GRPO), credits every token in the rollout with a single scalar determined only by the accuracy of the final verdict, providing no separate credit at the criterion-choice tokens and ignoring the rich language feedback (e.g., preference rationales) that naturally accompanies preference labels. Self-Distillation (SD) is one natural way to use this language feedback: the same model, conditioned on this feedback, acts as a teacher providing dense, position-level supervision. However, not all positions carry equally useful signal. Using the per-position entropy shift between teacher and student, we identify two regimes: context sharpening, where the teacher concentrates probability on a particular feedback-aligned criterion expression, and context spreading, where the teacher distributes probability across multiple feedback-aligned alternatives. We interpret these patterns as follows: sharpening encourages memorization of a particular criterion expression, whereas spreading promotes semantic understanding by preserving these alternatives. Motivated by this asymmetry, we introduce position masking based on the entropy shift that retains the lower tail of the entropy-shift distribution. Experiments show that masking higher-entropy-shift positions improves out-of-distribution generalization over naive SD. The resulting self-distilled judges outperform judges trained with outcome-supervised RL by 2-9 percentage points on the evaluated subjective subcategories, while remaining competitive on objective ones.

cs.CL↗

arXiv2026

Beyond State-as-Action: Exploiting Command-State Discrepancy for Robot Imitation Learning

Constructing action targets from measured robot motion is an established approach in imitation learning. Under interaction constraints, however, command-state discrepancy may reflect control demands that motion alone does not capture. We investigate when this information matters and how to exploit it. Across three real-robot tasks, task and phase analyses reveal larger supervision gaps under constrained interaction, while selective command retention provides evidence of locally useful command information. Building on these findings, we propose Command-State Discrepancy Weighting (CSDW), which accounts for robot response times and combines subsequent progress, persistent unmet demand, and demand changes into continuous weights for command supervision. The method requires no task-phase annotations or changes to policy architecture or inference. CSDW improves over uniform command supervision on constrained tasks, while methods perform similarly in the less constrained task. Project page: https://seen-e.github.io/CSDW/.

cs.RO↗

arXiv2026

Switching Anomalous Hall and Nernst Responses by Nonmagnetic N Occupation at Fixed Noncoplanar Mn Antiferromagnetic Order

Nonmagnetic atomic occupation can control anomalous transverse transport by modifying magnetic symmetry without changing the underlying magnetic order. We demonstrate this effect using controlled $γ$-Mn, Mn$_4$N, and MnN reference states with the same lattice constant and identical noncoplanar all-in-all-out Mn magnetic configurations, while varying only the occupation of the N sublattice. The anomalous Hall and anomalous Nernst responses exhibit a pronounced zero--finite--zero evolution across the series despite the unchanged Mn spin order. In $γ$-Mn and MnN, the high magnetic symmetry enforces complete cancellation of the Brillouin-zone-integrated Berry curvature. In Mn$_4$N, N occupation lowers the magnetic symmetry while preserving inversion and breaking the relevant twofold rotational symmetries, thereby lifting the cancellation constraint and permitting an uncompensated Berry-curvature contribution along the [111] direction. The resulting finite anomalous Hall conductivity reaches $-126$~S/cm near the Fermi level. These results establish nonmagnetic sublattice occupation as a symmetry-control parameter for Berry-curvature-driven transport in compensated antiferromagnets, independent of changes in the magnetic order.

cond-mat.mtrl-sci↗

arXiv2026

Randomized Branch Methods with Inexact Subproblems for Bouligand Stationarity in Linear and Quadratic Programs with Complementarity Constraints

We develop randomized branch methods for finding Bouligand-stationary (B-stationary) points of linear and quadratic programs with complementarity constraints (LPCCs and QPCCs) using only linear programming subproblems. The methods exploit the finite-union geometry of the feasible set and search for first-order descent on randomly selected compatible branches. For LPCCs, an exact method optimizes over sampled branches, while an inexact simplex method can accept an improving branch-feasible vertex before solving the sampled penalty problem to optimality. For QPCCs, including problems with indefinite quadratic objectives, branch quadratic programs are replaced by linearized trust-region subproblems; a ratio test ensures actual decrease, and thresholded sampling detects branches that emerge only at accumulation points. Under the stated assumptions, the LPCC methods stabilize after finitely many changes at B-stationary points almost surely. For the QPCC method, finite termination yields a B-stationary point, and every accumulation point of an infinite run is B-stationary almost surely. Experiments on bilevel-induced instances, instances arising from inverse quadratic programming, and sparse affine generalized Nash equilibrium instances, together with 129 MacMPEC embedding tests, show that the methods return points with competitive objective quality and runtimes on large-scale complementarity systems.

math.OC↗

arXiv2026

Do Emotion Concepts Generalize Across Sources, Modalities, and Architectures in Vision-Language Models?

Recent studies suggest that large language models encode emotion concepts as structured internal representations, but most existing work focuses on text and a single architecture. Therefore, we ask, do emotion concepts generalize across sources, modalities, and architectures in vision--language models (VLMs)? To address this, we construct CMES (Cross-Modal Emotion Stimuli), a multi-source collection of emotion-conditioned stories, real facial expressions, synthetic portraits, and synthetic emotion-evoking scenes. For each stimulus source, we extract a separate set of six Ekman emotion vectors from each of three VLMs. We report four main findings as follows: 1) Image-derived emotion vectors form a low-dimensional geometry similar to that of text-derived vectors. Valence is relatively stable across sources, while arousal varies more. 2) Text- and image-derived emotion vectors have modest cosine similarity but still show held-out cross-modal correspondence. Text-derived vectors can also steer image interpretation. 3) Cross-architecture correspondence remains even when native cosine is near zero. Transformations estimated from generic ImageNet activations recover both correspondence and causal transfer without using the six emotion vectors or their labels. 4) After aligning representations across architectures, we construct a shared emotion subspace that preserves affective geometry and selective steering effects. The corresponding consensus emotion vectors also generalize to a held-out fourth architecture at two model sizes. These results suggest that emotion representations can share relational structure and causal effects across sources, modalities, and architectures, even when individual vector directions differ.

cs.CV↗

arXiv2026

Convergent representations of elastic-wave structure emerge across deliberately distinct seismic training routes

Elastic-wave propagation connects laboratory fracture with earthquakes, raising the prospect of seismic models that reuse waveform structure across physical scales. Here we show that the phase picker PNSN and the multi-task model SeismicXM organize unseen laboratory acoustic emissions around common waveform relations. Their representations agree on 512 held-out records relative to matched random networks. Four earthquake-model families also track displaced laboratory arrivals without fitting target neural weights. Receiver-function classification is accessible to frozen pretrained features, although standardized random features remain competitive. Noise correlations test the extension to continuous propagation outputs: a nonlinear SeismicXM ensemble improves on random topology, while a period-wise median remains more accurate. Waveform interventions and synthetic controls reveal that the observed agreement depends on feature calibration and the waveforms being compared. These results establish convergent waveform organization across distinct seismic training routes and show that cross-scale arrival transfer is already accessible to compact models.

physics.geo-ph↗

arXiv2026

Does High Signal-to-Noise Ratio Identify Better Training Data for Seismic Deep Learning?

Hard signal-to-noise ratio (SNR) screening removes weak seismic records, but does retaining clearer waveforms improve learning enough to compensate for the discarded data? We test this question in phase picking and ambient-noise dispersion, first matching training counts and then restoring the full eligible dispersion pool at fixed compute. Phase-picking screening gave no consistent unfiltered-test benefit under fine-tuning or random initialization, including a control matched on distance and phase composition. Dispersion screening increased error at the original five-epoch endpoint but improved on an equally sized unscreened set after longer training. Retaining all 29,788 eligible fit paths instead of 9,929 randomly sampled paths reduced unfiltered-test error by 3.0% across three seeds at the same update budget. Full-available and strict-SNR training then had similar mean errors, 0.0405 and 0.0406 km s$^{-1}$, with mixed seed-paired ordering; strict training retained a 9.9% advantage on the SNR-selected test. In two-day monitoring, SNR regulated pick streams but event recovery depended on its measurement definition. High SNR did not reliably identify better training data: gains depended on the task, training schedule, and test domain, and fixed-count comparisons omitted the benefit of retaining additional valid examples.

physics.geo-ph↗

arXiv2026

Bond-selective modulation of scalar spin chirality in strained Mn4N

Scalar spin chirality (SSC) underlies a variety of Berry-phase-driven transport phenomena in noncoplanar magnets. Mn4N is a unique ferrimagnetic system in which both collinear and noncoplanar magnetic configurations have been reported at different lattice parameters, featuring vanishing and finite SSC, respectively. However, the microscopic mechanism governing the competition between these magnetic states and the associated modulation of SSC remains unclear. This issue is particularly important for Mn4N because its high magnetic ordering temperature (TN = 740 K) provides an attractive platform for exploring chiral magnetic states and their associated topological functionalities at elevated temperatures. Here, using first-principles calculations, we investigate the strain-driven evolution of the magnetic ground state and SSC in Mn4N and uncover the microscopic origin of the collinear-to-noncoplanar magnetic transition. We demonstrate that tensile strain continuously stabilizes the noncoplanar configuration and enhances SSC, as quantified by the magnitude of the chirality-order vector. Orbital-resolved crystal orbital Hamilton population and charge-density-difference analyses reveal that strain selectively weakens the Mn3c-N hybridization while preserving direct Mn3c-Mn3c interactions, leading simultaneously to the activation of the Mn3c in-plane magnetic moment and the suppression of N-mediated ferromagnetic superexchange between nearest-neighbor Mn3c atoms. This bond-selective electronic response governs the magnetic ground state and consequently controls the emergence and enhancement of SSC in Mn4N. Our work establishes bond selectivity as an effective strategy for engineering SSC in high-temperature ferrimagnetic materials.

cond-mat.mtrl-sci↗

arXiv2026

Rufus-Air: An Open LLM Post-Training Recipe

Rufus-Air is an open and reproducible post-training recipe on GLM-4.5-Air-Base (106B-A12B), organized as a serial pipeline of eight stages: SFT, Reasoning RL, Coding RL, Instruction-Following RL, General Agent, Coding Agent, Search Agent, and RLHF. We document the data, reward design, infrastructure, stage order, and stagewise results needed to reproduce the recipe. Stages progress from basic to advanced capabilities and from hard, verifiable rewards to softer judge-based signals. Training builds on open-source components and public data, much of it used as released, without new human annotation or an in-house distillation teacher. Our main findings are that (i) diverse, high-quality SFT establishes a strong capability floor; (ii) difficulty filtering keeps RL prompts within a productive learning range; (iii) reward reliability provides a practical principle for ordering stages; and (iv) infrastructure and engineering choices are part of the recipe, not just an implementation detail. Rufus-Air improves over the official GLM-4.5-Air post-trained release and is competitive with similarly sized open models.

cs.CL↗

arXiv2026

From Image Morphology to Multiphysics Earth Posteriors

Structural learning and physical-property inference can draw on different sources of knowledge. We learn morphology from 33,140 natural, satellite, and texture images, without geological training models, then infer Earth properties from physical observations. Identical frozen weights map 128 coordinates into each $256\times256$ compressional-velocity, shear-velocity, or density field. Fixed adapters assign physical meaning; observation-specific likelihoods determine new posteriors without retraining. Across 256 unseen Earth models, image coordinates reduce projection error fourfold relative to a dimension-matched cosine basis. Matched inversions favor image coordinates for the tested curved-velocity targets and a smooth radial basis for the tested faulted targets. A simplified 2.5-dimensional application with 915 measured observations along one 120.9-km southern-California profile constrains a velocity--density contrast. Grouped arrival-time and gravity errors fall by 43% and 44% relative to the pretrained image prior, although the matched smooth radial basis predicts better. Direct layered-Rayleigh updating reduces blind phase-velocity error by 28% at five sites, whereas P-and-gravity-only sharing worsens it, distinguishing reusable morphology from beneficial cross-property coupling. These results establish a practical separation: images supply structural alternatives, and heterogeneous physical observations determine their experiment-specific posterior probabilities.

physics.geo-ph↗

arXiv2026

Structure-dependent failure modes of neural priors in acoustic full-waveform inversion

Frequency continuation does not improve every neural representation, and better velocity recovery need not imply better prediction of unseen waveforms. We compare a velocity grid with total-variation regularization, an adapted sinusoidal coordinate network (SIREN), and a frozen image generator with a full-grid residual in two-dimensional acoustic full-waveform inversion. All methods use the same frozen SWEEP discretization, acquisition, observations, background, and budget of 1,500 shot--model gradient evaluations. Three exposed synthetic targets represent inclined layering, curved layering, and a high-contrast curved interface drawn from a fault-labelled family. With 2-to-10 Hz continuation, the generative-residual model attains velocity RMSEs of 218.7, 108.0, and 341.9 m/s, compared with 232.5, 100.3, and 412.9 m/s for Grid+TV. Thus the latter wins on curved layering, while the former improves model RMSE by 5.9% and 17.2% on the other targets. Grid+TV nevertheless predicts held-out 10 Hz shots better on all three. SIREN is worse than the common background in every cell; continuation worsens two targets but improves one. A five-weight TV sensitivity study preserves the CurveFault model-error ranking. An equal-budget variational extension fails both recovery and interval coverage. These results establish conditional rankings, not universal superiority or an isolated spectral-bias mechanism. Full-grid residuals also prevent attributing gains uniquely to the generator. We advocate joint reporting of model recovery, unseen-shot prediction, optimization cost, and negative outcomes when auditing neural FWI.

physics.geo-ph↗

arXiv2026

Enabling Robust Cloth Manipulation via Inference-Time Simulator-in-the-Loop Refinement

Simulator-in-the-loop optimization offers a promising inference-time mechanism for robot manipulation. It uses a physical simulator as a backend rollout engine to evaluate candidate trajectories in parallel and refine nominal actions online, a paradigm shown to be effective in rigid-body manipulation where state and contact are relatively tractable. We bring this paradigm to real-world cloth manipulation from a single RGB input through three pillars. (i) We design a scalable synthetic-data generation and inference-time rollout pipeline built on FLASH, a deformable-object simulator that provides a practical balance among physical fidelity, numerical stability, and rollout efficiency. (ii) We develop a real-to-sim module, trained purely on synthetic data, that maps a single RGB observation to simulation-compatible cloth state by fusing pretrained visual features with learnable canonical tokens. (iii) We perform online planning by coupling a sparse-mesh rollout backend with prior-guided MPPI, anchored at an offline-distilled policy trajectory, preserving manipulation-relevant deformation and contact while enabling sufficient parallel rollout batches. Real-robot experiments show higher success rates than baseline methods and closed-loop correction under mid-fold perturbations. Project page: https://silr-cloth.github.io/

cs.RO↗

arXiv2026

POPI: Personalizing LLMs via Optimized Natural Language Preference Inference

Large language models (LLMs) are typically aligned with population-level preferences, despite substantial variation across individual users. We introduce POPI, a user-level personalization framework that separates the problem into two components connected by a natural-language interface: a shared inference model that distills heterogeneous user signals into a concise preference summary, and a shared generator that conditions on this summary to produce personalized responses. Both components are trained under a unified preference-optimization objective, with reinforcement learning handling the non-differentiable inference step. This objective decomposes into generator approximation error and summary informativeness, revealing how a single loss simultaneously drives accurate generation and informative summarization. Because the interface is natural language, learned summaries can be inferred once per user and reused across different generators -- including frozen, black-box commercial APIs. Across four personalization benchmarks, POPI generally improves personalization quality while reducing context overhead by up to an order of magnitude.

cs.CL↗

arXiv2026

Construting Reverse Thinking: Developing Large Language Models' Reverse Thingking Ability

When facing complex problems, humans tend to try various ideas for different issues. Human thinking patterns exhibit remarkable flexibility in adapting to diverse scenarios. GPT-o1, GPT-o3, and DeepSeek-R1 adopt long chain-of-thought models to address complex problems by increasing reasoning depth, which default to a forward reasoning mode. We conducted statistical analysis on the accuracy of different mathematical problem datasets on models of different scales, and found five reasons for errors: Insufficient solution-space coverage, Computational mistakes, Unverified assumptions, Ignoring constraint conditions, Maximum response length limitation. To address the above issues, we proposed a backward reasoning pattern construction method aimed at enhancing the model's reverse thinking ability and dynamic adaptability. First, we constructed an easy-hard two-stage Math dataset for training large models and gradually improving their inference ability at different difficulty levels. The dataset contains forward reasoning paths as well as backward reasoning paths. And a two-stage supervised fine-tuning process is applied to progressively train the model's backward reasoning capability. Furthermore, a fine-grained reward mechanism is developed, employing smoothed reward signals to strengthen the model's ability to autonomously select thinking modes during the reasoning process, thereby avoiding reward hacking. A linear-decay balanced sampling strategy is designed to maintain a balance between forward and backward reasoning path samples during training, enabling the model to converge quickly and stably. Experimental results show that our method significantly improves reasoning efficiency and accuracy in tasks such as mathematical proofs, offering a flexible and efficient reasoning paradigm for solving complex problems.

cs.AI↗

arXiv2026

Technical Report OFDM-Assisted Simultaneous Quantum and Classical THz Communications

The feasibility of cost-effective simultaneous quantum and classical communication (SQCC) transmitting both the quantum key and classical information via a superimposed coherent state is investigated both in optical and Terahertz (THz) bands. Since the existing THz SQCC schemes assume single-carrier (SC) transmission over flat fading channels, we embark on investigating SQCC in realistic frequency-selective multipath THz fading channels. We then propose an orthogonal frequency division multiplexing (OFDM) based SQCC system for time-invariant frequency-selective THz scenarios, supported by low-density parity-check coded (LDPC) multidimensional QKD reconciliation schemes. Our simulation results demonstrate that the OFDM-based SQCC scheme is capable of achieving a practical secret key rate (SKR) over a wide range of power sharing scenarios between the classical and quantum signals. By contrast its single-carrier counterpart requires the classical signal to be at least 100 times stronger than the quantum signal in THz SQCC.

quant-ph↗

arXiv2026

A Multitask Large Reasoning Model for Molecular Science

Artificial intelligence in molecular science must move beyond pattern recognition toward chemically valid and interpretable reasoning. We present a task-adaptive large reasoning model that integrates chemical knowledge through a synergistic multispecialist architecture, chain-of-thought supervision, and molecule-informed reinforcement learning. Task-conditioned routing coordinates prediction and inference specialists across 10 molecular tasks spanning molecular description and generation, nomenclature translation, property prediction, and reaction prediction. The model outperforms more than 20 general-purpose and molecular large language models, improves aggregate performance over the base model by 50.3%, and surpasses the leading molecular multitask baseline on most tasks. Analyses of specialist representations and reasoning pathways reveal task-specific adaptation while retaining interpretable chemical inference. A case study further demonstrates an integrated workflow for central nervous system candidate generation, property screening, molecular interpretation, and retrosynthetic planning. These results demonstrate a versatile multi-task framework for knowledge-guided molecular reasoning and design, with the potential to serve as a core task engine for future molecular science agents.

cs.LG↗

arXiv2026

ThinkFlow: Self-Evolving Probabilistic Latent Memory for Lifelong Conversational Agents

Lifelong conversational agents rely on memory systems to maintain deep, context-aware interactions with users. However, existing explicit textual memory pipelines suffer from a severe information bottleneck, often losing subtle behavioral patterns and emotional shifts. Furthermore, being typically static post-deployment, they cannot autonomously adapt to personal habits and preferences without manual feedback. Cognitive science, however, suggests that humans maintain mental models purely in a latent space and continuously refine them through predictive coding. Inspired by this, we propose \textbf{ThinkFlow}, a novel end-to-end latent memory framework for lifelong conversational agents. ThinkFlow bypasses the text bottleneck by dynamically compressing conversational flows into probabilistic latent memory skills, autonomously consolidating complex user states into disentangled, continuous vectors without semantic interference. To break this barrier, we introduce a test-time evolution paradigm. By coupling teacher-guided latent alignment to bootstrap the initial state with a self-supervised next-user-utterance prediction task for continuous refinement, the framework successfully overcomes cold-start challenges and achieves label-free lifelong personalization. Extensive experiments on long-term conversation benchmarks demonstrate that ThinkFlow significantly outperforms prevailing memory systems, providing highly personalized and contextually accurate responses over extended multi-session interactions.

cs.AI↗