Search arXiv⌕ Search

arXiv subjects

Shan Jiang

Publications and source records attributed to Shan Jiang.

At least 19 recordsLinked to original sources
arXiv2026

AgentDecept: Benchmarking Deceptive Behavior in Tool-Using LLM Agents under Pressure

LLM agents increasingly carry out multi-turn tasks across everyday applications, yet users often see only the agent's report rather than the observations, API calls, and state changes behind it. Existing deception benchmarks have studied long-horizon interactions and tool-use settings, but whether agents faithfully report their actions across realistic, stateful application workflows remains underexplored. To address this gap, we introduce AgentDecept, an executable benchmark for evaluating behavioral deception under pressure. AgentDecept contains 477 pressure variants derived from 257 source tasks across six pressure sources, each paired with a pressure-free counterpart. Interventions enter through event messages, task context, application state, tool responses, and service quotas, spanning explicit events and implicit task or environment changes. Our evidence-grounded protocol evaluates full trajectories by relating user-facing claims to time-ordered observations and executed outcomes, distinguishing falsification, concealment, and equivocation from honest failure and disclosed limitations. The resulting behavioral labels also provide a setting for testing existing activation-based probes. AgentDecept enables controlled analysis of when multi-turn agents' reports diverge from execution in realistic application interactions.

cs.AI↗
arXiv2026

Memory as Code: Declarative Retrieval over Codified Long-Term Memory

In long-term memory systems, memories are constructed from interaction histories and retrieved in response to queries, enhancing the reasoning ability of LLM agents. In complex scenarios, facts are scattered across sessions and their relationships evolve over time, making it difficult for existing memory systems to compose them to adapt to diverse queries. Motivated by the modularity and composability of code, we propose Memory as Code (MaC), a unified memory framework that jointly designs memory construction and retrieval through a shared code abstraction. MaC couples codified construction, which establishes executable memory abstractions, with declarative retrieval, which translates queries into structured retrieval programs. Specifically, codified construction builds a three-layer executable memory structure that progresses from an atomic function layer, through a relational layer, to a modular composition layer. Declarative retrieval recasts retrieval from relevance-based fact selection into declarative query processing over memory. Experiments on LoCoMo and LongMemEval show relative gains of up to 15.91% in overall LLM-judge accuracy over the strongest baseline in each setting, while substantially reducing token consumption, highlighting the effectiveness of memory as code for long-horizon memory tasks.

cs.CL↗
arXiv2026

OmniTrace: A Unified Framework for Generation-Time Source Attribution in Omni-Modal LLMs

An omni-modal language model can answer a question about a multimodal document, a recording, or a video, but it cannot show which part of the input the answer came from. Asking the model to cite its evidence yields what it says it used; measuring what it used has so far required rerunning it many times with parts of the input removed, a cost that grows with every second of audio and video. We show that the generation pass already holds most of this information. OmniTrace attributes each generated sentence to source units (text chunks, images, and seconds of audio or video) by reading late-layer attention as mass over units with no extra forward pass and no per-modality tuning; head weights can be trained where ablation data are available. With fixed causal test setting, the units OmniTrace selects are causally important for responses and for individual sentences in video, audio, and image-text question answering on Qwen3-Omni-30B, MiniCPM-o 4.5 and Qwen2.5-Omni-7B. With one generation pass, OmniTrace recovers 77-96% of the effect of leave-one-out attribution, which needs up to 41 extra passes. OmniTrace also agrees best with human-marked evidence: its response-level rankings reach an AUROC of 0.83 on documents and 0.64 on video, against 0.76 and 0.60 for the strongest baseline.

cs.CL↗
arXiv2026

Contour-integral and Fourier transform based multivariable quantum eigenvalue transformation for commuting matrices

We study the problem of implementing multivariable matrix-valued functions on a quantum computer and propose two quantum algorithms for multivariable matrix eigenvalue transformations acting on tuples of pairwise commuting matrices. The first algorithm is based on multivariable contour integrals and applies to arbitrary holomorphic functions on $\mathbb{C}^n$. The second algorithm is based on high-dimensional Fourier transforms and designed for smooth functions of commuting Hermitian matrices. For both algorithms, we discuss and analyze the complexity of their quantum implementation leveraging quantum singular value transformation, compression gadgets, and linear combination of unitaries. We additionally study their hybrid quantum--classical variants that reduce the number of required ancilla qubits to logarithmic dependence on the number of variables, at the cost of increased query complexity. As an application, we show that multivariable matrix polynomials can be implemented with no additional explicit degree dependence, depending only on global properties of the polynomials.

quant-ph↗
arXiv2026

Contour-integral based quantum eigenvalue transformation: analysis and applications

Eigenvalue transformations appear ubiquitously in scientific computation, ranging from matrix polynomials to differential equations, and are beyond the reach of the quantum singular value transformation framework. In this work, we study the efficiency of quantum algorithms based on contour integral representation for eigenvalue transformations from both theoretical and practical aspects. Theoretically, we establish a complete complexity analysis of the contour integral approach proposed in [Takahira, Ohashi, Sogabe, and Usuda. Quant. Inf. Comput., 22, 11\&12, 965--979 (2021)]. Moreover, we combine the contour integral approach and the sampling-based linear combination of unitaries to propose a quantum algorithm for estimating observables of eigenvalue transformations using only $3$ additional qubits. Practically, we design contour integral based quantum algorithms for linear ordinary differential equations, $φ$-functions, Fréchet derivatives of matrix functions, and matrix functions. In particular, we show that the contour integral algorithm can outperform all the existing quantum algorithms in the case of solving asymptotically stable differential equations.

quant-ph↗
arXiv2026

On Edge in the Dental Chair: Designing VR Support for Moments of Dental Anxiety

Dental anxiety can change as a procedure unfolds, yet dental virtual reality (VR) commonly provides continuous distraction or relaxation. We investigate how support can be coordinated with specific simulated dental events. Stakeholder interviews (N=36), participatory design with three returning dentists, and patient walkthroughs of a no-intervention prototype (N=12) informed five Anxiety Events and an intervention-module framework. Drawing on cognitive vulnerability and emotion regulation, we implemented a standardized event-contingent VR system with predefined event-module assignments and shared agency and safety controls. A randomized study (N=24) compared the intervention package with no-intervention VR. The adjusted intervention-minus-control difference averaged -12.83 VAS-A points across events (95% CI [-24.42, -1.70]). Physiological, behavioural, and qualitative measures contextualized participants' experiences. The findings inform timely, comprehensible support and reassuring social presence in simulated dental VR; they concern the complete package rather than individual modules or clinical effectiveness.

cs.HC↗
arXiv2026

Recovering Process Variables from Industrial Network Traffic via Search-Based Optimization

Process variables (PVs) provide the process evidence needed for process-aware security monitoring in industrial cyber-physical systems (CPSs). However, existing supervisory infrastructures expose only the subset of PV values recorded by historians, leaving many additional runtime PV values unobserved. To address this incomplete process visibility, we study the problem of recovering PV fields and their semantics directly from raw industrial network traffic through protocol reverse engineering (PRE). In this setting, existing PRE methods face two practical challenges: PV-carrying communication is mixed with heterogeneous runtime traffic, and PV-carrying payloads are often long and deployment-specific. Mixed runtime traffic obscures the PV-carrying communication paths, while long payloads create a vast segmentation space in which early segmentation errors can propagate and corrupt the recovery of later fields under sequential inference. In this paper, we formulate the recovery of PV fields from raw network traffic as a search-based optimization problem. Our key insight is that non-sequentially identifying correct segmentations in such a vast segmentation space can be cast as an optimization problem and addressed by searching for near-optimal solutions. We propose PVParser to approach this goal. PVParser first reduces the search space by identifying the PV-carrying payloads from network traffic via a periodic pattern detection mechanism. It then employs a modified Monte Carlo Tree Search to explore near-optimal segmentations, reducing error propagation from incorrect early boundary decisions. Experiments on three representative industrial CPS datasets demonstrate that PVParser achieves high accuracy and F1-score in PV-carrying payload localization and PV field inference, outperforming six state-of-the-art PRE approaches by a significant margin.

cs.CR↗
arXiv2026

Electron-phonon coupled hydrodynamics in semimetal TaAs_2

Hydrodynamic corrections to diffusive transport can arise when momentum-conserving collisions between quasiparticles become prominent, and they have been documented for both electrons and phonons. An emerging frontier topic is coupled electron-phonon (e-ph) hydrodynamics. Here, through electrical and thermal transport measurements on TaAs2 crystals with different impurity levels, we document the emergence of an e-ph bifluid in the temperature window of 5 to 15 K. Within this range, the lattice thermal conductivity exhibits a faster-than-T^3 temperature dependence, as a consequence of non-monotonic and purity-dependent phonon mean free paths, a signature of phonon Poiseuille flow. However, strong e-ph coupling impedes the emergence of a ballistic regime. This is corroborated by the observation of quantum oscillations in the lattice thermal conductivity. Prominent phonon-mediated momentum exchange between electrons amplifies the violation of the Wiedemann-Franz law and yields a two-order-of-magnitude discrepancy between quantum and transport lifetimes, a signature of electron hydrodynamics in semimetals. Our results imply that in semimetals with optimized e-ph coupling, thanks to matching between the cryogenic phonon wave?length and the Fermi wavelength, momentum and energy flow between the electron and phonon reservoirs as frequently as within each reservoir.

cond-mat.mtrl-sci↗
arXiv2026

LLM-Driven Joint Evolution of Coupled Heuristics Components for Routing Optimization

Heuristic design for combinatorial optimization remains heavily reliant on expert knowledge, while existing large language model (LLM)-enhanced evolutionary methods typically evolve isolated algorithmic components, even when one determines the search state on which another operates. This paper proposes LLM-driven Heuristic Components Joint Generation (LLM-HCJG), a population-based framework that jointly generates and co-evolves interdependent heuristic components under a shared design blueprint. Applied to guided local search (GLS), LLM-HCJG couples solution initialization with penalty construction and embeds the generated pair into an enhanced online search mechanism. The resulting form is further transferred from the traveling salesman problem (TSP) to the capacitated vehicle routing problem (CVRP). Theoretical analysis establishes the non-separable state-transition effects between the two components and the advantage in generation consistency. Across synthetic instances and 41 public TSPLIB/CVRPLIB benchmarks, LLM-HCJG attains consistently low optimality gaps, including best or tied-best results on 28 of 29 TSPLIB instances and all 12 CVRPLIB instances. Ablation and structural analyses further indicate that these gains are associated with cross-component compatibility and alignment rather than isolated-component recombination. These results support effective cross-instance transfer within the evaluated routing settings under limited-sample, modest-cost training.

cs.NE↗
arXiv2026

ScienceFlow: A long-horizon agent for ML research, scientific discovery and beyond

Enabling LLM agents to sustain productive, stable, and goal-aligned research over extended horizons is a central challenge for autonomous machine learning and scientific discovery, as progress hinges on continuously managing evolving state, exploration decisions, and computational resources. Pioneering autoresearch agents, despite great success, still lack mechanisms for continuity, recovery from dead ends, and value-driven compute allocation, which inherently undermines overall search efficiency, wastes computational resources, and lowers the chance of ultimate success. To bridge this gap, we introduce ScienceFlow, an end-to-end autoresearch agent framework that organizes long-horizon research work into research segments grounded in executable workspaces. It represents research progress as recoverable executable states, enabling efficient exploration, revision, and execution. Transitions between research segments are governed by Executable-State Transition through Re-Anchoring (ESTRA), which selects either the live state or an archived state as the next anchor and determines whether to continue or redirect the research trajectory. An evidence-aware execution controller allocates resources to physical jobs based on resource availability, remaining budget, and validated progress. We evaluate ScienceFlow on tasks spanning machine learning, scientific modeling, and mathematical optimization. Results on diverse long-horizon benchmarks demonstrate its ability to sustain effective research processes, highlighted by a SOTA 70.22 percent Any-Medal score on the full MLE-bench within a 24-hour budget, outperforming prior reported results by 4.92 percentage points. The efficacy of ScienceFlow further demonstrates that efficient state management, adaptive exploration, and objective-aligned execution are critical for scaling autonomous research beyond short-horizon interactions.

cs.AI↗
arXiv2026

Empowering Polymeric Materials Discovery by Artificial Intelligence

Polymeric materials underpin modern technologies spanning energy storage, microelectronics, healthcare and sustainable manufacturing. Yet their rational design remains exceptionally challenging because material performance emerges from complex interactions among molecular composition, chain architecture, processing history and hierarchical structural evolution across multiple length and time scales. Consequently, polymer research has long relied on labor-intensive experimentation and fragmented modeling approaches, limiting both mechanistic understanding and innovation efficiency. Recent advances in data infrastructure, machine learning, large artificial intelligence (AI) models and laboratory automation are beginning to reshape this landscape. Rather than functioning as isolated tools, polymer databases, predictive models, AI agents and automated laboratories are increasingly converging into interconnected discovery ecosystems. As a result, the central challenge is shifting from improving predictive accuracy alone to enabling reliable decision-making, adaptive learning and seamless integration across computation, experimentation and scientific reasoning. We argue that polymer science is entering an era of autonomous discovery, in which data, simulation, reasoning and experimentation operate within self-improving feedback loops that continuously generate hypotheses, design materials, execute experiments and refine predictive models. By unifying molecular design, process optimization, experimental validation and industrial translation, such autonomous ecosystems establish a more predictive, reproducible and scalable paradigm for polymer innovation, fundamentally transforming how polymer research is conducted.

physics.chem-ph↗
arXiv2026

FieldWorkArena: Agentic AI Benchmark for Real Field Work Tasks

This paper introduces FieldWorkArena, a benchmark for agentic AI targeting real-world field work. With the recent increase in demand for agentic AI, they are built to detect and document safety hazards, procedural violations, and other critical incidents across real-world manufacturing and retail environments. Whereas most agentic AI benchmarks focus on performance in simulated or digital environments, our work addresses the fundamental challenge of evaluating agents in the real-world. In this paper, we improve the evaluation function from previous methods to assess the performance of agentic AI in diverse real-world tasks. Our dataset comprises on-site captured images/videos in factories, warehouses and retails. Tasks were meticulously developed through interviews with site workers and managers. Evaluation results confirmed that performance evaluation considering the characteristics of Multimodal LLM (MLLM) such as GPT-4o is feasible. Furthermore, this study identifies both the effectiveness and limitations of the proposed new evaluation methodology. The complete dataset and evaluation program are publicly accessible on the website (https://en-documents.research.global.fujitsu.com/fieldworkarena/)

cs.AI↗
arXiv2026

Quantum Algorithms for Triangle Cut Sparsification

Triangles capture higher-order structures in graphs and are fundamental to applications such as clustering and network analysis. To enable efficient use of such structures at scale, we study the problem of triangle cut sparsification, which aims to reduce the graph size while approximately preserving triangle counts across every cut. We investigate quantum algorithms for this problem, using triangle listing as our main technical ingredient. In particular, we present a quantum algorithm for triangle listing that, for a graph with $n$ vertices, $m$ edges, and $t$ triangles, runs in time $T_{\mathrm{q\text{-}list}} =$ $\widetilde{O}\bigl(\min(n^{5/4}t^{7/12} + n^{7/6}t^{7/9}, m + m^{3/4}t^{1/2},$ $n^{3/2}t^{1/2})\bigr)$, improving upon the best known classical bounds over a broad range of parameters. Our algorithm is based on a heavy-light vertex partition and an extension of triangle detection via quantum walks and Grover search. Leveraging this result, we design a quantum algorithm for constructing $\varepsilon$-triangle cut sparsifiers of size $\widetilde{O}(n/\varepsilon^2)$ in time $\widetilde{O}(T_{\mathrm{q\text{-}list}} + \sqrt{mn}/\varepsilon)$. Finally, we demonstrate applications to clustering algorithms based on triangle-related measures and prove a lower bound of $Ω(n/\varepsilon^2)$ on the size of any $\varepsilon$-triangle cut sparsifiers.

quant-ph↗
arXiv2026

GlobalDentBench: A Multinational Benchmark for Evaluating LLM Clinical Reasoning in Dentistry with Expert Calibration

While large language models (LLMs) hold transformative potential for medicine, their reasoning robustness and safety in real-world clinical scenarios remain critically underexplored, particularly in dentistry. Here we introduce GlobalDentBench, the first multinational dental benchmark, featuring a taxonomy that encompasses 14 dental specialties across 88 countries and regions spanning six continents. The benchmark comprises 8,978 expert-validated questions across three formats (multiple-choice, short-answer, and case-based questions) and assesses three progressive reasoning levels: knowledge recall (L1), routine reasoning (L2), and individualized reasoning (L3). To ensure data quality, the automated construction framework was calibrated by six senior dentists, achieving expert agreement rates of 99.98% for multiple-choice and short-answer questions and 96.78% for the more complex case-based questions. Evaluation of 12 frontier LLMs on GlobalDentBench revealed a sharp, stepwise performance degradation with increasing reasoning complexity. Specifically, accuracy plummeted from 81.34% on multiple-choice to 64.53% on short-answer and 22.34% on case-based questions, while declining markedly from 74.01% at L1 to 55.64% at L2 and 35.71% at L3. More critically, risk analysis of real-world dental cases demonstrated an alarming overall unsafe rate of 31.01% in LLM-generated clinical recommendations, with 4.51% posing risks of irreversible patient harm and risks particularly pronounced in specialties such as orthodontics. These findings expose fundamental limitations in the medical reasoning and safety of current LLMs. Consequently, GlobalDentBench provides a scalable foundation for trustworthy clinical AI evaluation, underscoring the urgent need for rigorous validation before the safe deployment of these models in healthcare.

cs.AI↗
arXiv2026

Sketch-and-Verify: Structured Inference-Time Scaling via Program Sketching

SKETCHVERIFY is a within-tier cost-performance policy, not a universal accuracy improvement. The operational question: a practitioner stuck with a small, cheap code model (here, Gemini 3.1 Flash Lite) for latency, deployment, or budget reasons -- how should they spend a small amount of extra test-time compute? SKETCHVERIFY factorizes the search space: the LLM enumerates K distinct algorithmic strategies, writes a program sketch for each (a partial program with ?? holes), and fills each sketch M times, producing K x M structurally diverse candidates that are verified by execution and selected by fingerprint clustering. Each extra sketch is guaranteed to explore a different algorithm; each extra flat sample likely duplicates an existing one. Our central evidence is a cost-quality Pareto plot on HumanEval+ across three Gemini tiers (Lite, Flash, Pro), and a reanalysis of the 19 problems where Lite greedy fails. Two findings: (1) Within-tier, sketching dominates flat sampling at matched candidate count. On the hard subset, Lite Sketch K=2, M=5 recovers 11/19 (58%) vs. flat N=10 at 5/19 (26%, +32pp); Lite Sketch K=10, M=10 recovers 15/19 (79%) vs. flat N=100 at 10/19 (53%, +26pp). Flat cannot close the gap even at ~3x the budget: flat N=50 still loses to Sketch K=2, M=5 by +11pp. (2) Cross-tier, sketching does not replace upgrading. Pro greedy (89%) dominates Lite Sketch K=10, M=10 (79%) on both pass@1 and dollar cost. Practitioner rule: if a stronger tier is available, use greedy on it; otherwise sketching is the cost-effective way to spend extra compute. We characterize the K-vs-M trade-off via a Flash Lite scaling sweep, report HumanEval+ saturation on Flash and Pro, and show the method composes cleanly with execution-based selection from the concurrent Semantic Voting line of work.

cs.LG↗
arXiv2026

Semantic Voting: Execution-Grounded Consensus for LLM Code Generation

LLM code-generation pipelines often sample multiple candidates and select one final answer without access to a complete oracle. Existing pipelines mix textual voting, ranking, and execution-based agreement, but the relative contribution of each component remains unclear. We study 18 configurations across different models, thinking levels, and benchmarks, comparing output-pattern majority voting, weighted voting, MBR-Exec, and SemanticVote - a method that clusters candidates by execution fingerprints on LLM-generated inputs. Three findings emerge. (1) The best execution-based selector exceeds output-pattern majority voting by 19-52 percentage points on every configuration, with every execution-based selector exceeding it by at least 18 points. (2) Once candidates are executed on diverse inputs, aggregation rule has limited effect: SemanticVote, weighted voting, and MBR-Exec are statistically indistinguishable across all 18 configurations. The largest factor is input quality: sketch-based input generation consistently outperforms direct LLM generation by 0.6-2.1 pp and random fuzzing by up to 11.3 pp. (3) Thinking level interacts differently with selection families: deeper thinking improves majority voting by 12 pp but execution-based methods stay flat or degrade as candidate diversity falls. These results frame inference-time code selection as a signal-quality problem rather than an aggregation-rule problem: when oracles are unavailable, the behavioral evidence matters more than the aggregation rule.

cs.SE↗
arXiv2026

Two-Stage Adaptation for Non-Normative Speech Recognition: Revisiting Speaker-Independent Initialization for Personalization

Personalizing automatic speech recognition (ASR) systems for non-normative speech, such as dysarthric and aphasic speech, is challenging. While speaker-specific fine-tuning (SS-FT) is widely used, it is typically initialized directly from a generic pre-trained model. Whether speaker-independent adaptation provides a stronger initialization prior under such mismatch remains unclear. In this work, we propose a two-stage adaptation framework consisting of speaker-independent fine-tuning (SI-FT) on multi-speaker non-normative data followed by SS-FT, and evaluate it through a controlled comparison with direct SS-FT under identical per-speaker conditions. Experiments on AphasiaBank and UA-Speech with Whisper-Large-v3 and Qwen3-ASR, alongside evaluation on typical-speech datasets TED-LIUM v3 and FLEURS, show that two-stage adaptation consistently improves personalization while maintaining manageable out-of-domain (OOD) trade-offs.

cs.SD↗
arXiv2026

OBsmith: LLM-Powered JavaScript Obfuscator Testing

JavaScript obfuscators are widely deployed to protect intellectual property and resist reverse engineering, yet their correctness has been largely overlooked compared to performance and resilience. Existing evaluations typically measure resistance to deobfuscation, leaving the critical question of whether obfuscators preserve program semantics unanswered. Incorrect transformations can silently alter functionality, compromise reliability, and erode security-undermining the very purpose of obfuscation. To address this gap, we present OBsmith, a novel framework to systematically test JavaScript obfuscators using large language models (LLMs). OBsmith leverages LLMs to generate program sketches abstract templates capturing diverse language constructs, idioms, and corner cases-which are instantiated into executable programs and subjected to obfuscation under different configurations. Besides LLM-powered sketching, OBsmith also employs a second source: automatic extraction of sketches from real programs. This extraction path enables more focused testing of project specific features and lets developers inject domain knowledge into the resulting test cases. OBsmith uncovers 11 previously unknown correctness bugs. Under an equal program budget, five general purpose state-of-the-art JavaScript fuzzers (FuzzJIT, Jsfunfuzz, Superion, DIE, Fuzzilli) failed to detect these issues, highlighting OBsmith's complementary focus on obfuscation induced misbehavior. An ablation shows that all components except our generic MRs contribute to at least one bug class; the negative MR result suggests the need for obfuscator-specific metamorphic relations. Our results also seed discussion on how to balance obfuscation presets and performance cost. We envision OBsmith as an important step towards automated testing and quality assurance of obfuscators and other semantic-preserving toolchains.

cs.SE↗