arXiv subjects

Xin Wang

Publications and source records attributed to Xin Wang.

At least 37 records · Page 2Linked to original sources

arXiv2026

What Personal Information Improves LLM-Based Next-Location Prediction?

Large language models (LLMs) are increasingly used for individual next-location prediction, with personal information easily added to prompts alongside mobility history. Yet the incremental predictive value of such information remains unclear. Using linked sociodemographic records and mobility traces from 5,000 Shenzhen residents, this study separates model responsiveness from predictive value. GPT-5 is the primary model, with GPT-5.5 and Claude Opus 4.6 used for replication. In 1,000 paired prediction instances, models rank 100 candidate destinations with and without age, gender, occupation and income while all other inputs are held fixed. Behavioural history raises top-1 accuracy from 5.6% to 18.5% as prior history increases from zero to six days. By contrast, sociodemographic attributes produce no detectable overall gain, although replacing correct attributes with those of another person reduces accuracy by 5.4 percentage points. Candidate construction also matters, removing distance raises accuracy by 7.7 points under proximity sampling but lowers it by 22.3 points under popularity sampling, with the reversal reproduced across all three LLMs. These findings identify behavioural history as the clearest source of incremental value and show that personal information should be evaluated under matched, explicitly specified conditions before its privacy and governance costs are justified.

cs.CY↗

arXiv2026

Beyond Report Imitation: Clinically Aware Multi-Image Ultrasound Report Generation from Visible Evidence

Generating ultrasound reports from multiple images requires aggregating clinical evidence across views, yet archived key frames capture only part of the dynamic examination. Raw-report imitation is therefore misaligned with visual supervision: content that is clinically valid for the full examination may be unverifiable from the images available to a model. This gap creates a clinical behavior alignment problem. A model must preserve visible findings, avoid diagnostic reversals and unsupported completion, and not collapse into conservative templates. We propose CAMEO, a Clinically Aware Multi-image Evidence-grounded Orchestration framework for ultrasound report generation. Stage I learns ultrasound visual-language primitives; Stage II performs Cross-View Evidence Grounding by distilling trusted visible report points into multi-image QA and report-style supervision; and Stage III performs Clinically Aware Preference Alignment using clinical-error-oriented preference pairs. From USReport, we construct USReport-Distilled with 17,670 evidence-grounded paired-image training instances and USReport-Pref with 21,869 preference pairs; we additionally use 25,631 PubMedVision-US ultrasound instruction samples for domain adaptation and multi-image instruction tuning. On the primary USReport-Distilled benchmark, CAMEO improves over EchoVLM from 0.25 to 0.40 BLEU-1, 0.28 to 0.45 ROUGE-1, and 0.27 to 0.43 METEOR, while raising ClinicalScore from 55.02 to 74.20. These results underscore the value of evidence-grounded supervision, clinically aware alignment, and clinically structured evaluation for reliable ultrasound report generation.

cs.CV↗

arXiv2026

Nearly Optimal T-Count for Symmetry-Based Quantum State Purification

Protecting quantum information from noise is essential for reliable quantum computation and quantum memories. Quantum state purification addresses this challenge by processing multiple noisy copies of an unknown quantum state to produce an output state of higher fidelity. Here we establish nearly tight upper and lower bounds on the non-Clifford resources required to implement the symmetric-projection purification protocol. For $n$ copies of a $d$-dimensional system, we construct a Clifford+T circuit that block-encodes the symmetric projector with operator-norm error at most $ε$ using $\widetilde{O}(n)$ T gates, where the tilde-$O$ notation suppresses polylogarithmic factors in $n$, $d$, and $1/ε$. Conversely, using stabilizer nullity, we prove that any Clifford+T implementation of such a block encoding with error $ε<\frac{1}{2}\sqrt{1-1/n}$ requires at least $2n-2$ T gates, even allowing arbitrary positive normalization and clean stabilizer ancillas. Taken together, these results establish the nearly optimal scaling of non-Clifford cost with the number of copies and uncover the fundamental resource requirements for coherent symmetry projection in quantum state purification.

quant-ph↗

arXiv2026

SWE-NFI: Studying and Benchmarking Coding Agents for Non-Functional Improvements

Although coding agents have achieved impressive performance on correctness-oriented benchmarks, their ability to make behavior-preserving non-functional improvements (NFIs) remains underexplored. In real-world software development, developers continuously improve software quality without changing observable behavior, yet existing benchmarks primarily evaluate functional correctness and provide limited support for assessing these non-functional improvements. In this paper, we present SWE-NFI, a benchmark for evaluating coding agents on NFIs beyond functional correctness. SWE-NFI contains 188 tasks constructed from real merged pull requests in open-source Python projects. We operationalize five developer-oriented NFI aspects into 92 executable rules and develop an evaluation suite that first applies task-specific functional preservation checks to assess whether key properties of the original code are preserved and then performs rule-based NFI evaluation. For outputs that pass these checks, we measure NFI improvement as the change in the normalized rule score for the task's target aspect relative to the original code. We evaluate eight commercial and open-source agent configurations and run each configuration five times on every task. At most 70.0% of valid agent outputs satisfy all task-specific functional preservation checks. Among outputs that pass these checks, NFI performance varies substantially across aspects. In particular, all evaluated configurations achieve mean Logic Patterns improvements between 0.0 and 1.3, below the Human Reference mean of 1.5. Our benchmark and findings provide a reproducible foundation for evaluating coding agents on non-functional improvements and identifying the NFI aspects where further advances are needed.

cs.SE↗

arXiv2026

SkillPoison: Progressive Skill Poisoning via Successful Experiences

Self-improving LLM agents increasingly distill successful experiences into persistent, reusable skills. Existing skill attack methods corrupt this learning pipeline by injecting malicious triggers, behaviors, or false facts into individual experiences or extracted skills. However, such attacks are easily detected, and the injected malicious behaviors often fail to accumulate as persistent skills. In this paper, we show that skill poisoning can arise even from verified successful experiences, without making any individual trajectory malicious. Based on this insight, we propose SkillPoison, a novel framework that progressively poisons skill via successful experiences. SkillPoison first constructs a set of successful experiences that reinforce a target behavior, and then removes the contextual conditions that constrain when the behavior applies. Rather than injecting malicious content, SkillPoison shapes how the skill extractor generalizes, allowing useful behavior to support task success while inducing harmful behavior when they are misapplied. Extensive experiments on three benchmarks show that SkillPoison achieves 95.71% attack success rates, while all injected experiences remain task-correct and pass verification and lexical inspection. Our code, data and implementation details are available for the community at https://github.com/DEEP-JLU/SkillPoison.

cs.CR↗

arXiv2026

Foresight-over-Graph: Reasoning Beyond Local Horizons for Knowledge Base Question Answering

Large language models (LLMs) have demonstrated strong capabilities in question answering, yet they still frequently suffer from hallucinations on knowledge-intensive tasks. Knowledge graphs (KGs) provide LLMs with structured, interpretable, and updatable factual grounding, making them a promising external knowledge source for reliable reasoning. However, existing LLM-guided graph reasoning methods typically rely on hop-wise greedy or beam-style pruning during evidence retrieval. Such local decision processes are inherently myopic: evidence that appears weak near the source may become crucial only after deeper graph context is explored, causing answer-critical branches to be discarded prematurely and making the reasoning chain difficult to recover. To address this limitation, we propose Foresight-over-Graph (FoG), a foresight-aware evidence retrieval framework for knowledge base question answering (KBQA). FoG iteratively constructs a question-relevant evidence subgraph and uses far-to-near feedback to guide path exploration, and maintains a compact memory subgraph to support continued exploration. Extensive experiments on widely used KBQA benchmarks demonstrate that FoG achieves state-of-the-art performance, with a particularly large improvement of 16.58% in Hit on CWQ, while also reducing LLM calls and token usage. Our code is available at https://github.com/yhong7/FoG .

cs.CL↗

arXiv2026

Adaptive Power Sampling for LLM Reasoning

Sequence-level power sampling has recently emerged as a training-free approach to reasoning by sampling from a sharpened output distribution of a base large language model (LLM). Nevertheless, existing methods typically sharpen the base model distribution uniformly across queries, overlooking variations in query difficulty and in how well the base model already handles each query. The goal of this work is to equip power sampling with query adaptivity. Theoretically, we show that the benefits of further sharpening are determined by the self-reward gap between correct and incorrect responses. Based on this insight, we propose \emph{Adaptive Power Sampling} (APS), which adjusts the sharpening exponent on a per-query basis at test time using the relationship between answer agreement and the model's self-reward. Experiments across diverse reasoning tasks, including MATH500, HumanEval, and GPQA, show that APS consistently outperforms power sampling with a fixed sharpening exponent, without additional training.

cs.AI↗

arXiv2026

Quantum incapacity from observable shadows

Quantum communication is ruled out when an eavesdropper can reconstruct the receiver's state. Yet states are operationally specified by measurement statistics, raising a sharper question: can access to every expectation value destroy communication? We show that it can. We call unbiased, variance-nonincreasing reconstruction under arbitrary reference extensions \emph{complete observable shadowing} and prove that it forces unassisted private and quantum capacities to vanish. An explicit qutrit channel realizes this mechanism while being neither antidegradable nor PPT, resolving the long-standing questions of whether quantum capacity can vanish outside those two classes and whether antidegradability is the only route to zero private capacity. Notably, it superactivates every finite-dimensional channel with zero quantum but positive private capacity. Statistical access can therefore preclude standalone communication without erasing latent coherent utility.

quant-ph↗

arXiv2026

Collective Quantum State Preparation Is Nonadditive

Quantum state preparation is a basic primitive of quantum computation and control, but its resource cost is usually analyzed for one target state or under an independent-copy construction. Here we study the many-copy problem under weighted Pauli control, where a Pauli-product rotation $e^{iϕP}$ is charged by its rotation angle $|ϕ|$, independently of the weight of $P$. We derive the exact single-qubit preparation cost and show that it is strictly nonadditive: a four-pulse collective protocol prepares two $T$ states at lower cost than two optimal one-copy protocols. We further identify finite regions of the Bloch sphere with collective saving, including trajectories that remain product throughout, showing that transient entanglement is not the only mechanism behind the advantage. Complementarily, a dimension-independent Rényi-entropy speed limit gives an extensive lower bound for every coherent target and an exponential fidelity penalty below a finite preparation rate. These results establish a many-copy geometry of state synthesis in which uncorrelated outputs can nevertheless benefit from collective control.

quant-ph↗

arXiv2026

Closed-Form Arbitrary-Gap Rényi Nonadditivity Above Any Positive Order via Direct Products of Free Groups and High-Girth Graphs

We give a closed-form finite-dimensional construction of quantum channels with real algebraic entries exhibiting arbitrarily large violations of minimum-output Rényi entropy additivity uniformly above any prescribed positive Rényi order, using a different finite realization based on direct products of free groups and fixed-field high-girth graphs. More precisely, for every $p_0>0$ and $g>0$, we construct one channel and one Bell input for which the additivity gap is greater than $g$ simultaneously for all $p\in[p_0,\infty]$. With $r=\lceil2g\rceil$, the construction uses $15r$ output qubits and $O(r2^{30r}+r^2(1+p_0^{-1}))$ input qubits. Compared with the stated parameters of Shou and Gorshkov \cite{ShouGorshkov2026}, our construction uses fewer output qubits for every target gap and has a smaller asymptotic input-qubit bound as the gap grows with the positive cutoff fixed. At the von Neumann order, a separate specialization gives an explicit channel with gap greater than $1/1024$ using $37608898$ input qubits and $8$ output qubits.

quant-ph↗

arXiv2026

EVISKILL: Grounding Skill Evolution in Replayable Evidence

Continual skill evolution enables LLM agents to accumulate and refine reusable procedural knowledge from interaction experience without updating model parameters. Its effectiveness depends on determining not only what to change, but also why a change is justified and when it should become persistent guidance. However, existing experience-driven methods can lose the behavioral evidence and task contexts supporting edits. Moreover, a global validation outcome provides an incomplete judgment of its constituent changes: locally supported corrections may be discarded with a rejected revision, while evidence may require further experience to inform useful updates. To this end, we introduce EVISKILL, an evidence-driven framework that organizes execution observations into Replayable Evidence Cards and synthesizes edits with explicit links to their supporting contexts. Targeted replay verifies these edits through re-execution and provides feedback for correction. Across epochs, EVISKILL preserves evidence and provisionally retains supported edits for further refinement, while global validation governs their incorporation into the final skill. Experiments on three interactive benchmarks across six LLM backbones demonstrate the effectiveness of this approach.

cs.AI↗

arXiv2026

Memadapter: Counterfactual Adaptation Against Memory-induced Sycophancy

Long-term memory enables LLM-based agents to retain and reuse information across tasks and sessions, supporting personalization and long-horizon interactions. However, persistent memories can also induce sycophancy, causing agents to over-align with users' historical beliefs even when they are inaccurate, outdated, or inconsistent with objective evidence. Existing mitigation methods assume that memory-induced sycophancy originates from biased or incorrect memories and attempt to reduce this risk by filtering such memories at different stages of the memory pipeline. However, in the real world, objective and correct memories can still induce sycophancy, and the same memory can warrant different influence across different contexts. To this end, we propose MemAdapter, a novel framework that adaptively integrates retrieved memories to support objective and reliable reasoning. Specifically, MemAdapter consists of three components: (i) Counterfactual Induction, which leverages counterfactual reasoning to uncover the potential risk of retrieved memories; (ii) Context-Aware Reflection, which calibrates the inferential influence of each retrieved memory in light of the current task via self-reflection; and (iii) Evidence-Based Reasoning, which grounds the final response in appropriate evidence while preserving the legitimate influence of memory. Extensive experiments on three benchmarks demonstrate that MemAdapter consistently improves memory reliability across diverse scenarios. Our code is available at https://github.com/DEEP-JLU/MemAdapter.

cs.AI↗

arXiv2026

Towards Automatically Pruning Logging Code with Coding Agents: How Far Are We?

Logging code supports debugging, monitoring, and software maintenance, but excessive logging can add noise, impose runtime overhead, and obscure diagnostic information. While prior research has extensively studied logging code generation and modification, logging removal remains comparatively underexplored. In this paper, we study developer logging removal practices and explore the use of coding agents for this task. We extract and manually validate logging removal cases from Python and Java repositories and derive 10 removal patterns and 11 removal reasons that characterize how and why logging code was removed in real-world software changes. We further construct LogRem, a dataset of 387 real-world cases covering direct logging statement removal, logging infrastructure removal, and logging replacement. We evaluate four coding agents with multiple model settings and compare their outputs with accepted real-world changes. Although 95.6% to 100.0% of outputs pass validity checks, only 11.1% to 19.6% remove the same logging code as the corresponding real-world change while preserving unrelated code. Agents differ through missed removals, extra removals, and unrelated code edits, with substantial variation across logging removal categories and trajectories. Execution cost varies widely, but higher cost does not consistently yield closer alignment. Commit messages and developer discussions provide the largest alignment gains, while taxonomy guidance consistently reduces runtime. Overall, our study establishes logging removal as a distinct software maintenance task and shows that reliable automation depends on accurately determining removal scope while preserving necessary code. To the best of our knowledge, this is the first study to examine logging code removal from this perspective.

cs.SE↗

arXiv2026

ROUTEAUDIT: Interaction-Aware Identification for Budgeted Multi-Verifier Routing

Adaptive multi-verifier systems are commonly compared through endpoint quality-cost gaps, even when the verifier catalog, availability, accounting, information filtration, or scorer changes with the policy. We formulate verifier routing as a contract-conditioned identification problem. The contract records request support, verifier catalog, realized availability, resource accounting, online filtration, and post-trace scoring; a matched route contrast changes only the policy coordinate. ROUTEAUDIT adds three measurable objects to this contract. A contract lattice averages coordinate increments over every admissible bridge order and reports the resulting attribution together with its path sensitivity. A policy-independent response tape identifies paired sequential contrasts when adaptive policies reveal different observations. For incomplete matching, request-level bounds use whichever potential outcome remains observed and give a sharp finite-population interval. The protocol commits paid observations and ledger events before the oracle join and returns an attribution certificate for each comparison. On two held-out raw-tail caches, matched static SF+SA equals the cascade, assigning the apparent gains of 0.1797 and 0.1250 over full static to the verifier-set edge. On 1,319 held-out task requests, the learned and RLVR studies report quality 0.9522 and 0.9553 versus 0.9484 for matched static; the RLVR-static paired difference is +0.0068 with a request-paired interval $[0.0015,0.0122]$ and a training-seed-by-request hierarchical interval $[0.0006,0.0131]$. Controlled attribution recovery yields route mean absolute error 0.0011 and endpoint reconstruction error 0.0004. Factorial, bridge-order, and stochastic-provider studies evaluate the certificate interface; RLVR supplies a learned-policy stress test under the same identification contract.

cs.AI↗

arXiv2026

FSPO: Policy-Consistent Risk and Pareto-Feasible Control for Budgeted LLM RL Post-Training

Adaptive LLM reinforcement-learning post-training changes multiple training actuators online, including rollout temperature, group size, clipping, KL regularization, verifier allocation, and update budget. Three coupled issues remain unresolved. A future-risk model trained from behavior trajectories need not estimate the risk induced by the controller that will be deployed; a score calibrated on logged state-action pairs can become miscalibrated after selective action choice; and independent per-resource minimum costs do not in general certify a feasible multi-resource continuation. We introduce FSPO, a feedback-state controller for budgeted LLM RL post-training that addresses these issues jointly. FSPO learns a policy-consistent risk-to-go model whose Bellman target follows the same frozen controller used for future decisions, together with a long-horizon utility model. Decision-conditioned trajectory calibration (DCTC) calibrates risk on cross-fitted trajectories generated by actions selected by provisional controllers. A Pareto resource continuation certificate (PRCC) admits an action only when a non-dominated cumulative reservation remains feasible over the residual horizon. Under a matched GRPO resource envelope, FSPO reaches 66.11% held-out and 59.43% OOD accuracy, compared with 64.47% and 57.03% for PB2, the strongest evaluated adaptive baseline. Three paired training seeds give gains of +2.42 and +3.19 percentage points over the contextual bandit on held-out and OOD evaluation. Under high behavior-deployment mismatch, policy-consistent risk lowers selected-decision ECE from 0.108 to 0.053; DCTC lowers it from 0.039 to 0.022 at matched acceptance; PRCC removes false-feasible admissions on an 18-action catalog ($0.197\rightarrow0.000$); and enabling all three components reduces trajectory failure from 0.181 to 0.083 in a factorial ablation.

cs.AI↗

arXiv2026

Multivariate quantum signal processing with optimal query complexity

Polynomial transformations of data encoded in quantum operations are a building block of quantum algorithms, and their query complexity measures how often those operations are used. For multiple variables, existing methods either realize restricted polynomial families or implement monomials separately at a query cost exponential in the number of variables. We present a quantum circuit that implements every multivariate trigonometric polynomial up to an explicit normalization. The circuit processes one variable coherently over the frequency components of the remaining variables, allowing all components to share the same signal queries. Each variable is queried exactly as many times as its degree in the polynomial, and we prove that this query complexity is optimal. We further extend the construction to commuting unitaries. The resulting circuit applies the multivariate polynomial simultaneously across their shared eigenbasis, using the minimum numbers of forward and inverse queries to each unitary. We also study trainable rotations with fixed preparation and a local readout of the last input. At query depth at least two, independent uniform initialization gives every active readout gradient a variance lower bound set by its squared branch weight and the inverse square root of the depth, uniformly over data states and dimensions. For supervised squared loss, retaining sample correlations gives an initialization gradient-variance bound in terms of targets and input spectra. This also bounds the expected loss decrease after the first exact gradient step with a specified step size. These results provide a scalable and practical solution for developing multivariate quantum algorithms and quantum learning models.

quant-ph↗

arXiv2026

Can External Sources Help the Knowledge Cut-off Issues in Audio Deepfake Detection?

In conventional deepfake audio detection pipelines, inference and evaluation are typically conducted using standalone, parameterized models trained exclusively on a fixed dataset. In contrast, we investigate a retrieval-augmented detection framework that queries an external knowledge database at inference time-analogous to retrieval augmented generation in large language models-to mitigate knowledge cutoffs and to find the conditions under which this retrieval-augmented detector outperforms purely parameterized baselines. The external knowledge database can be updated continuously, including during system operation, but its optimal use scenarios have not been previously well characterized. Our empirical results indicate that retrieval augmentation is most beneficial when the content of the knowledge database is distinct from the fine-tuning data of self-supervised learning (SSL)-based models yet remains aligned with the domain of the evaluation set; under these circumstances, linear score-level fusion with standalone detectors is also effective. Nonetheless, the retrieval-augmented system remains vulnerable to domain shifts, and the performance improvements are limited when the test distribution diverges substantially from the domain represented in the knowledge database.

cs.SD↗

arXiv2026

Mental-R1: Aligning LLM Reasoning for Mental Health Assessment

Mental health problems such as anxiety, depression, and suicide remain urgent global challenges, where timely and accurate assessment is critical for effective intervention. Recently, large language models have been explored for mental health assessment. However, existing general-purpose post-training methods do not align with the cognitive processes of human assessment, which may lead to unreliable reasoning outcomes. To bridge this gap, we propose Cognitive Relative Policy Optimization (CRPO), a reinforcement learning framework tailored for the mental health domain. CRPO extends group relative policy optimization by integrating stage-dependent uncertainty modeling into the policy optimization process. Specifically, we introduce a stage-wise entropy regularization mechanism that encourages broad exploration in early reasoning phases and progressively enforces confident decision-making in later stages, mimicking the human cognitive shift from uncertainty to certainty. In addition, inspired by cognitive appraisal theory, we formalize cognitive reasoning stages, thereby guiding theory-grounded interpretable inference. Experiments on 8 mental health datasets show that CRPO achieves an average improvement of 10.4 percentage points in weighted F1-score over the best reinforcement learning baseline. Furthermore, the CRPO-trained model Mental-R1 demonstrates clear advantages compared with existing large language models on reasoning-intensive cases, suggesting that CRPO enhances reasoning capabilities for mental health assessment.

cs.AI↗