arXiv subjects

Hang Zheng

Publications and source records attributed to Hang Zheng.

At least 19 recordsLinked to original sources

arXiv2026

AMLBench: A Real-Incident Benchmark for Agentic Blockchain Anti-Money Laundering

Tracing illicit funds on public blockchains remains largely manual. As funds move across accounts and undergo asset conversions, they become mixed with other inflows, requiring repeated queries and expert judgment to trace. Large language model (LLM) agents offer a way to automate this process, but their ability to reconstruct case-related transfer networks from limited clues remains unclear. To bridge this gap, we present AMLBench, an anti-money laundering (AML) benchmark built from 24 real-world cases and 5.05 million Ethereum transfer records. For each case, agents start from limited clues and explore these transfer records through composable transaction-query and fund-flow analysis tools, deciding which accounts and branches to pursue. The final tracing results are evaluated against case annotations, while tool interaction logs reveal how agents discover and select relevant transfers and at what resource cost. We also develop AMLAgent, which integrates fund-tracing guidance and query feedback to dynamically guide investigative decisions. With GPT-6 Astra, AMLAgent achieves macro averages of 80.82% transfer-level precision and 84.73% query coverage across 24 real-world cases. Further analysis of the large-scale Bybit case reveals substantial differences in transfer retention and token usage across models, even with similar submission precision. AMLBench establishes a reproducible benchmark for evaluating both tracing outcomes and investigative processes, laying the groundwork for more reliable and efficient autonomous AML investigations.

cs.CE↗

arXiv2026

CylindTrack: Depth-Aware Cylindrical Motion Modeling for Panoramic Multi-Object Tracking in Mobile Robots

Maintaining consistent target identities and observation histories is essential for mobile robot perception. Panoramic Multi-Object Tracking (MOT) benefits from broad visual coverage but must address coordinate discontinuities at the equirectangular image seam and fluctuations in relative-depth estimates. Such fluctuations can undermine depth-aware association, highlighting the need for temporally consistent depth cues. We propose CylindTrack, a depth-aware cylindrical tracking-by-detection framework that jointly models panoramic topology and temporal depth consistency. Depth-Temporal Trajectory Modeling (DTM) maintains instance depth and its rate of change as filtered trajectory states. Spherical Spatio-Temporal Consistency Learning (SSTC) combines a Temporal Mixer with Spherical Geometry-aware Attention to refine depth-aware representations. A Topology-Aware Cylindrical Motion Model (TCMM) represents horizontal motion in an unwrapped angular state and incorporates periodic overlap, angular consistency, and filtered depth cues into association. Experiments on QuadTrack and JRDB demonstrate improved identity consistency and trajectory continuity, with HOTA scores of 33.67 and 31.12 and IDF1 scores of 40.45 and 34.33, respectively. The framework processes 28.56 and 21.34 frames per second, respectively, on an NVIDIA GeForce RTX 3090 GPU under the reported evaluation settings. These results support persistent panoramic multi-object tracking for mobile robot perception. The source code will be released at https://github.com/warriordby/CylindTrack.

cs.CV↗

arXiv2026

A Task-Centric Survey of Long-Document Visual Question Answering: Taxonomy, Evolution, and Future Directions

Visual document understanding is essential for acquiring knowledge from visually rich documents and is attracting growing research interest. Existing surveys emphasize architectures or technical approaches, with limited attention to how task bottlenecks shape technical choices and research priorities. We present a task-centric survey that decomposes long-document visual question answering (VQA) into four components: document parsing, evidence organization and retrieval, generator organization and learning, and evaluation. For each, we develop a fine-grained taxonomy and trace motivations, technical responses, and cross-component connections. We focus on explicit retrieval while covering direct reading. Our temporal analysis traces expanding priorities from multimodal content understanding to sufficient, high-fidelity evidence acquisition and sustained evidence management. We outline future directions in evidence sufficiency, verifiable and correctable understanding, and budget-aware coordination, with an outlook on continual document understanding.

cs.CV↗

arXiv2026

ARGUS: An Agenda-Driven Framework for Reliable User Simulation

High-fidelity user simulators are essential for evaluating and training agents in interactive environments. However, current LLM-based simulators struggle with reliability issues, such as goal omission and policy non-compliance. We propose ARGUS (Agenda-dRiven Goal-oriented User Simulator), a neuro-symbolic framework that maintains the user's goal state using a dynamic agenda stack manipulated via symbolic operations. By rigorously decoupling state tracking from natural language generation, ARGUS facilitates strict goal progression and constraint-aligned interactions. For cost-efficient deployment, we distill ARGUS into compact models using a unified pipeline: evaluator-guided SFT followed by online RL with dense step-level rewards. To rigorously evaluate behavioral fidelity, we introduce a rubric-based metric Composite Behavioral Score (CBS). Evaluations on $τ^3$-Bench and MultiWOZ demonstrate the significant superiority of the ARGUS architecture and the efficacy of our training pipeline. Code and data will be released soon.

cs.AI↗

arXiv2026

MixGuard: Towards Detecting and Understanding Mixer Laundering on Ethereum

Mixers protect privacy by concealing deposit--withdrawal links, but are also abused to launder illicit funds. Existing anti-money laundering studies do not specifically target mixer laundering, while mixer research focuses on deanonymization rather than identifying laundering-related transactions. Public reports remain fragmented, leaving no public case-level dataset for systematic measurement and detection. To fill this void, this paper presents the first comprehensive study of mixer laundering on Ethereum. We first construct \textsc{MixLaunder}, the first public case-level dataset of mixer laundering. It covers 27 cases involving Tornado Cash and Railgun from 2020 to 2025 and labels 9,300 laundering-related transactions with case identities and observable upstream and downstream fund flows, including deposits totaling approximately \$1.1 billion. By comparing these transactions with background mixer usage, we identify five common strategies, showing that laundering evidence spans complementary behavioral and fund-flow contexts, while same-case activity is locally tight but weakly connected across bursts. Our analysis further reveals coverage gaps in mixer-side risk screening and representative deanonymization heuristics. Guided by these findings, we develop \textsc{MixGuard}, which combines tri-view representation learning with two-stage grouping for transaction-level detection and case-aware grouping. Under strict case-level holdout evaluation, \textsc{MixGuard} outperforms representative baselines, achieving 97.89\% detection precision and 98.73\% group purity, while its top ten groups cover 95.09\% of each case's transactions on average.

cs.CR↗

arXiv2026

SoK: Cross-Chain Transaction Identification and Matching

Cross-chain bridges, instant cryptocurrency exchanges, and centralized cross-ledger platforms move assets across an increasingly multi-chain ecosystem. However, these systems have repeatedly become targets of high-value attacks and channels for cross-chain money laundering. Cross-chain transactions are substantially harder to analyze than single-chain transactions: no single ledger records an entire cross-chain transfer, its evidence is scattered across the source chain, the destination chain, and off-chain systems, and the availability and reliability of that evidence vary widely across systems. In this paper, we present a systematization of knowledge (SoK) on cross-chain transaction identification and matching. First, we classify deposit and withdrawal identification methods into four approaches and transaction matching methods into three mechanisms: deterministic identifier matching, field-constraint heuristics, and model-assisted matching. We find that their applicability and reported performance are shaped mainly by the evidence the underlying system exposes, and we further examine how matched pairs support downstream attack detection and fund tracing. Second, we assess the availability of existing datasets and artifacts, finding that fewer than half remain obtainable, and distill three artifact failure modes. Finally, we outline four open challenges toward auditable, reproducible, and actionable cross-chain analysis.

cs.CR↗

arXiv2026

No Action Without a NOD: A Heterogeneous Multi-Agent Architecture for Reliable Service Agents

Large language model (LLM) agents have increasingly advanced service applications, such as booking flight tickets. However, these service agents suffer from unreliability in long-horizon tasks, as they often produce policy violations, tool hallucinations, and misaligned actions, which greatly impedes their real-world deployment. To address these challenges, we propose NOD (Navigator-Operator-Director), a heterogeneous multi-agent architecture for service agents. Instead of maintaining task state implicitly in dialogue context as in prior work, we externalize a structured Global State to enable explicit task state tracking and consistent decision-making by the Navigator. Besides, we introduce selective external oversight before critical actions, allowing an independent Director agent to verify execution and intervene when necessary. As such, NOD effectively mitigates error propagation and unsafe behavior in long-horizon tasks. Experiments on $τ^2$-Bench demonstrate that NOD achieves higher task success rates and critical action precision over baselines. More importantly, NOD improves the reliability of service agents by reducing policy violations, tool hallucinations, and user-intent misalignment.

cs.AI↗

arXiv2026

Position: Academic Conferences are Potentially Facing Denominator Gaming Caused by Fully Automated Scientific Agents

The implicit policy of maintaining relatively stable acceptance rates at top AI conferences, despite exponentially growing submissions, introduces a critical structural vulnerability. This position paper characterizes a new systemic threat we term Agentic Denominator Gaming, in which a malicious actor deploys AI agents to generate and submit a large volume of superficially plausible but low-quality papers. Crucially, their objective is not the acceptance of low-quality papers, but rather to inflate the submission denominator and overwhelm reviewing capacity. Under a relatively stable acceptance rate, this dilution can systematically increase the publication probability of a small, targeted set of legitimate papers. We analyze the practical feasibility of this threat and its broader consequences, including intensified reviewer burnout, degraded review quality, and the emergence of industrialized automated agent mills. Finally, we propose and evaluate a range of mitigation strategies, and argue that durable protection will require system-level policy and incentive reforms, rather than relying primarily on technical detection alone.

cs.CL↗

arXiv2026

CapsID: Soft-Routed Variable-Length Semantic IDs for Generative Recommendation

Generative recommendation maps each item to a sequence of Semantic IDs (SIDs) and recasts retrieval as autoregressive token generation. In this paradigm the main bottleneck is the tokenizer rather than the Transformer: residual vector quantization with a hard nearest-neighbor assignment at every layer collapses multi-faceted item semantics at cluster boundaries and propagates early errors to later SID positions. A common workaround is to append a dense vector or attribute prefix to the SID, but this dual-representation design inflates inference cost and gives up the simplicity of a generative interface. We address the bottleneck at the tokenizer itself. CAPSID replaces hard residual quantization with capsule routing: at each layer an item probabilistically routes to several semantic capsules, the residual is updated by the routed reconstruction rather than by a single winning code, and the SID terminates once the active capsule's confidence is high enough. On top of CAPSID, SEMANTICBPE composes adjacent SID tokens into reusable subwords by combining their co-occurrence with their embedding compatibility. On Amazon Beauty, Sports, Toys, and a 35M-item proprietary industrial catalog, CAPSID+SEMANTICBPE improves Recall at 10 by 9.6% on average over ReSID, the strongest single-representation baseline, and matches or exceeds a COBRA-style sparse-dense system on every public benchmark while running at 51% of its inference latency. Ablations show that soft routing, iterative agreement, and confidence-driven length each contribute independently, and the gains are largest on tail items where boundary semantics dominate.

cs.IR↗

arXiv2026

AirQA: A Comprehensive QA Dataset for AI Research with Instance-Level Evaluation

The growing volume of academic papers has made it increasingly difficult for researchers to efficiently extract key information. While large language models (LLMs) based agents are capable of automating question answering (QA) workflows for scientific papers, there still lacks a comprehensive and realistic benchmark to evaluate their capabilities. Moreover, training an interactive agent for this specific task is hindered by the shortage of high-quality interaction trajectories. In this work, we propose AirQA, a human-annotated comprehensive paper QA dataset in the field of artificial intelligence (AI), with 13,956 papers and 1,246 questions, that encompasses multi-task, multi-modal and instance-level evaluation. Furthermore, we propose ExTrActor, an automated framework for instruction data synthesis. With three LLM-based agents, ExTrActor can perform example generation and trajectory collection without human intervention. Evaluations of multiple open-source and proprietary models show that most models underperform on AirQA, demonstrating the quality of our dataset. Extensive experiments confirm that ExTrActor consistently improves the multi-turn tool-use capability of small models, enabling them to achieve performance comparable to larger ones.

cs.CL↗

arXiv2026

DiSRouter: Distributed Self-Routing for LLM Selections

The proliferation of Large Language Models (LLMs) has created a diverse ecosystem of models with highly varying performance and costs, necessitating effective query routing to balance performance and expense. Current routing systems often rely on a centralized external router trained on a fixed set of LLMs, making them inflexible and prone to poor performance since the small router can not fully understand the knowledge boundaries of different LLMs. We introduce DiSRouter (Distributed Self-Router), a novel paradigm that shifts from centralized control to distributed routing. In DiSRouter, a query traverses a network of LLM agents, each independently deciding whether to answer or route to other agents based on its own self-awareness, its ability to judge its competence. This distributed design offers superior flexibility, scalability, and generalizability. To enable this, we propose a two-stage Self-Awareness Training pipeline that enhances each LLM's self-awareness. Extensive experiments demonstrate that DiSRouter significantly outperforms existing routing methods in utility across various scenarios, effectively distinguishes between easy and hard queries, and shows strong generalization to out-of-domain tasks. Our work validates that leveraging an LLM's intrinsic self-awareness is more effective than external assessment, paving the way for more modular and efficient multi-agent systems.

cs.CL↗

arXiv2025

Bohrium + SciMaster: Building the Infrastructure and Ecosystem for Agentic Science at Scale

AI agents are emerging as a practical way to run multi-step scientific workflows that interleave reasoning with tool use and verification, pointing to a shift from isolated AI-assisted steps toward \emph{agentic science at scale}. This shift is increasingly feasible, as scientific tools and models can be invoked through stable interfaces and verified with recorded execution traces, and increasingly necessary, as AI accelerates scientific output and stresses the peer-review and publication pipeline, raising the bar for traceability and credible evaluation. However, scaling agentic science remains difficult: workflows are hard to observe and reproduce; many tools and laboratory systems are not agent-ready; execution is hard to trace and govern; and prototype AI Scientist systems are often bespoke, limiting reuse and systematic improvement from real workflow signals. We argue that scaling agentic science requires an infrastructure-and-ecosystem approach, instantiated in Bohrium+SciMaster. Bohrium acts as a managed, traceable hub for AI4S assets -- akin to a HuggingFace of AI for Science -- that turns diverse scientific data, software, compute, and laboratory systems into agent-ready capabilities. SciMaster orchestrates these capabilities into long-horizon scientific workflows, on which scientific agents can be composed and executed. Between infrastructure and orchestration, a \emph{scientific intelligence substrate} organizes reusable models, knowledge, and components into executable building blocks for workflow reasoning and action, enabling composition, auditability, and improvement through use. We demonstrate this stack with eleven representative master agents in real workflows, achieving orders-of-magnitude reductions in end-to-end scientific cycle time and generating execution-grounded signals from real workloads at multi-million scale.

cs.AI↗

arXiv2025

Enhancing LLM Reliability via Explicit Knowledge Boundary Modeling

Large language models (LLMs) are prone to hallucination stemming from misaligned self-awareness, particularly when processing queries exceeding their knowledge boundaries. While existing mitigation strategies employ uncertainty estimation or query rejection mechanisms, they suffer from computational efficiency and sacrificed helpfulness. To address these issues, we propose the Explicit Knowledge Boundary Modeling (EKBM) framework, integrating fast and slow reasoning systems to harmonize reliability and usability. The framework first employs a fast-thinking model to generate confidence-labeled responses, enabling immediate utilization of high-confidence outputs, whereas uncertain predictions trigger a slow refinement model for accuracy improvement. To align model behavior with our proposed object, we propose a hybrid training pipeline, enhancing self-awareness without degrading task performance. Evaluations on dialogue state tracking tasks demonstrate that EKBM achieves superior model reliability over uncertainty-based baselines. Further analysis reveals that refinement substantially boosts accuracy while maintaining low computational overhead. The framework establishes a scalable paradigm for deploying reliable LLMs in error-sensitive applications, effectively balancing accuracy and practical utility.

cs.CL↗

arXiv2025

Performance Review on LLM for solving leetcode problems

This paper presents a comprehensive performance evaluation of Large Language Models (LLMs) in solving programming challenges from Leetcode, a widely used platform for algorithm practice and technical interviews. We began by crawling the Leetcode website to collect a diverse set of problems encompassing various difficulty levels and topics. Using this dataset, we generated solutions with multiple LLMs, including GPT-4 and GPT-3.5-turbo (ChatGPT-turbo). The generated solutions were systematically evaluated for correctness and efficiency. We employed the pass@k metric to assess the success rates within a given number of attempts and analyzed the runtime performance of the solutions. Our results highlight the strengths and limitations of current LLMs [10] in code generation and problem-solving tasks, providing insights into their potential applications and areas for improvement in automated programming assistance.

cs.SE↗

arXiv2025

A Challenge of Developing a Classifier for Multi-Band Classification of Variable Stars

Variable stars play a very important role in our understanding of the Milky Way and the universe. In recent years, many survey projects have generated a large amount of photometric data, necessitating classifiers that can quickly identify various types of variable stars. However, obtaining these classifiers often requires substantial manpower and computational resources. To conserve these resources, it would be best to have a classifier that can be used across surveys. We explore the possibility that a classifier created in one optical band can also work in other bands, likely from different survey facilities. We construct a random forest classifier based on photometric data in ASAS-SN V-band and OGLE I-band, and apply the classifier on ASAS-SN V-band and ZTF r-band light curves of variable star samples. We explore the classification differences of using the magnitude light-curves or the normalized flux light-curves, the periods derived from single band light-curves or the periods derived from the multi-band combined light-curves, and with or without color-related features. We find it feasible to develop a classifier capable of working in both V and r bands for certain types of variable stars, such as RRAB variables. For other types of variable stars, like Cepheids, the classifier is unable to make accurate identifications.

astro-ph.IM↗

arXiv2024

The Economic Analysis of the Common Pool Method through the HARA Utility Functions

Water market is a contemporary marketplace for water trading and is deemed to one of the most efficient instruments to improve the social welfare. In modern water markets, the two widely used trading systems are an improved pair-wise trading, and a 'smart market' or common pool method. In comparison with the economic model, this paper constructs a conceptual mathematic model through the HARA utility functions. Mirroring the concepts such as Nash Equilibrium, Pareto optimal and stable matching in economy, three significant propositions are acquired which illustrate the advantages of the common pool method compared with the improved pair-wise trading.

econ.GN↗

arXiv2024

Uni-Mol2: Exploring Molecular Pretraining Model at Scale

In recent years, pretraining models have made significant advancements in the fields of natural language processing (NLP), computer vision (CV), and life sciences. The significant advancements in NLP and CV are predominantly driven by the expansion of model parameters and data size, a phenomenon now recognized as the scaling laws. However, research exploring scaling law in molecular pretraining models remains unexplored. In this work, we present Uni-Mol2 , an innovative molecular pretraining model that leverages a two-track transformer to effectively integrate features at the atomic level, graph level, and geometry structure level. Along with this, we systematically investigate the scaling law within molecular pretraining models, characterizing the power-law correlations between validation loss and model size, dataset size, and computational resources. Consequently, we successfully scale Uni-Mol2 to 1.1 billion parameters through pretraining on 800 million conformations, making it the largest molecular pretraining model to date. Extensive experiments show consistent improvement in the downstream tasks as the model size grows. The Uni-Mol2 with 1.1B parameters also outperforms existing methods, achieving an average 27% improvement on the QM9 and 14% on COMPAS-1D dataset.

cs.LG↗

arXiv2024

Efficient and Precise Force Field Optimization for Biomolecules Using DPA-2

Molecular simulations are essential tools in computational chemistry, enabling the prediction and understanding of molecular interactions and thermodynamic properties of biomolecules. However, traditional force fields face significant challenges in accurately representing novel molecules and complex chemical environments due to the labor-intensive process of manually setting optimization parameters and the high computational cost of quantum mechanical calculations. To overcome these difficulties, we fine-tuned a high-accuracy DPA-2 pre-trained model and applied it to optimize force field parameters on-the-fly, significantly reducing computational costs. Our method combines this fine-tuned DPA-2 model with a node-embedding-based similarity metric, allowing seamless augmentation to new chemical species without manual intervention. We applied this process to the TYK2 inhibitor and PTP1B systems and demonstrated its effectiveness through the improvement of free energy perturbation calculation results. This advancement contributes valuable insights and tools for the computational chemistry community.

physics.chem-ph↗