arXiv subjects

Zhijie Zhong

Publications and source records attributed to Zhijie Zhong.

18 recordsLinked to original sources

arXiv2026

LongHarness: Advancing Agentic Reasoning over 100M-Token Corpora via Stateful Evidence Management

Corpus-level long-context reasoning requires agents to acquire and integrate evidence across document collections that exceed their context windows. Existing agent harnesses enable incremental access to these corpora, but acquired evidence and evolving conclusions often remain entangled in a growing interaction history. This implicit state management can lead to two coupled failure modes: unbounded exploration, where retrieval expands the interaction history without resolving decision-relevant information gaps, and evidence-state drift, where previously acquired evidence or subsequent corrections fail to inform the current conclusion. We present LongHarness, a model-agnostic harness that makes the interaction between acquired evidence and evolving conclusions explicit. Its core mechanism, Evidence-Conclusion Coevolution, uses unresolved conclusions to guide exploration toward missing information, while newly acquired evidence strengthens or revises the conclusions that directed the search. LongHarness couples this process with Evidence Lifecycle Management, which keeps accumulated evidence current and traceable throughout the interaction. Together, these mechanisms focus retrieval on remaining information needs and keep conclusions aligned with current evidence. We evaluate LongHarness on OfficeQA Pro V1 and V2, AA-LCR, and LongBench v2 using GLM-5.3-Flash and Qwen3.8-Flash. Compared with direct reasoning using the same backbone, LongHarness improves GLM-5.3-Flash exact match on OfficeQA Pro from 15.8% to 60.2% on V1 and from 4.4% to 61.1% on V2. Against state-of-the-art agent harnesses, it surpasses Claude Code by 12.0 percentage points on V1 and Codex by 18.9 points on V2. With Qwen3.8-Flash, LongHarness reaches 61.7% on V1, outperforming Claude Code by 8.3 points and Codex by 12.0 points.

cs.AI↗

arXiv2026

SmartMemory: Detecting On-chain-off-chain Communication Inconsistency for Smart Contract via Memory-based Agent

Smart contracts underpin decentralized finance, where growing demand for on-chain/off-chain communication(OFC) has driven diverse applications such as cross-chain bridges, real-world asset tokenization, and fiat-backed stablecoins. TheOFC-related security incidents in these applications are increasingly frequent, but prior studies address separate vulnerability categories within OFC applications rather than providing a unified view, causing vulnerabilities outside known patterns to be missed.In this paper, we identify OFC inconsistency (OFCI) as a root cause of OFC vulnerabilities, which arises from business-logic flaw and ultimately breaks the equivalence between the on-chain and off-chain asset representations to induce inconsistency.Automatically detecting OFCIs faces two challenges including (1)locating heterogeneous business logic, and (2) transferring existing vulnerability knowledge to identify unseen OFCI instances. To this end, we propose SmartMemory, the first framework to leverage a memory-based agent for OFCI detection. To address heterogeneity, SmartMemory maps diverse implementations ofOFC contracts into a canonical business-semantic representation to locate the business logic for OFCI inspection. For knowledge reuse, SmartMemory integrates a memory-based agent to distill vulnerability knowledge from features into patterns and detection rules, enabling knowledge transfer across cases to identify unseenOFCIs. Lastly, SmartMemory performs taint analysis to verify the reachability, type, and impact of each candidate OFCI. We construct the first real-world OFCI dataset comprising 48 DApps with 81 OFCIs for evaluation, on which SmartMemory achieves80.68% precision and 87.65% recall. In addition, through an analysis of 325 real-world OFC applications, SmartMemory detects 36 previously unknown OFCIs, all of which have been confirmed and fixed by corresponding parties.

cs.SE↗

arXiv2026

PI-Mem: Pushing Long-Context Reasoning to 3.6M Tokens with Parallel-Iterative Memory

Long-context reasoning remains a critical bottleneck for large language models, as recent recurrent-memory approaches face two inherent challenges: sequential chunk-wise updates can overwrite early critical evidence with later irrelevant content, and serial inter-chunk dependencies limit parallelism and cause latency to increase with context length. To address these issues, we propose PI-Mem (Parallel-Iterative Memory), a mechanism that processes all chunks in parallel and iteratively refines a shared memory over a bounded number of turns. In each turn, PI-Mem reads all chunks in parallel conditioned on the current memory, selects new or complementary evidence from each chunk, and merges the selected evidence into a compact shared memory for the next turn. To discourage redundant turns, we optimize the workflow through reinforcement learning with an auxiliary turn-efficiency reward, enabling the model to adaptively exit once sufficient evidence has been accumulated. We evaluate PI-Mem with Qwen3.5-35B-A3B and Qwen2.5-7B on the HotpotQA benchmark across context lengths up to 3.6 million tokens and find that it outperforms the recurrent-memory baseline by +6.25 and +7.81 absolute points while achieving 6.1$\times$ and 2.1$\times$ inference speedups, respectively. These results demonstrate that PI-Mem breaks the accuracy--efficiency trade-off in long-context reasoning and provides a scalable approach to complex multi-hop question answering over extremely long documents.

cs.CL↗

arXiv2026

Agents-K1: Towards Agent-native Knowledge Orchestration

Current LLM-based research agents have advanced through agent orchestration, yet largely overlook scientific knowledge orchestration. Existing works often reduce papers to abstracts, surface mentions, and flat \texttt{cites} edges, omitting key entities, claims, evidence, mechanisms, and method lineages essential for scientific reasoning. To this end, we introduce \textbf{Agents-K1}, an end-to-end knowledge orchestration pipeline that converts raw documents into agent-native scientific knowledge graphs. Agents-K1 integrates three components under a unifying theoretical foundation: a multimodal parser whose five-module schema captures entities, multimodal evidence, citations, and typed inter-entity relations across the full paper rather than abstracts alone; a 4B information-extraction backbone trained with GRPO under a rule-based reward; and a graphanything CLI, a tri-source agent interface that unifies web search, multimodal graph retrieval, and cross-document traversal. On top of this, we process 2.46 million scientific papers across six subjects to produce \textbf{Scholar-KG}, of which we release a one-million-paper subset, and the full Scholar-KG is accessible via the SCP link below. The same pipeline can be extended to general-domain corpora and to schema-conformant data synthesis. Extensive experiments demonstrate that Agents-K1 achieves superior performance in scientific information extraction, knowledge graph construction, and multi-hop scientific reasoning.

cs.AI↗

arXiv2026

Scaling the Horizon, Not the Parameters: Reaching Trillion-Parameter Performance with a 35B Agent

We introduce Agents-A1, a 35B Mixture-of-Experts Agentic Model that reaches trillion-parameter-level performance by scaling the agent horizon. We investigate agent-horizon scaling from two perspectives: scaling long-horizon trajectories and scaling heterogeneous agent abilities. To support this goal, we build a long-horizon knowledge-action infrastructure that connects external knowledge, actions, observations, and verifier outcomes, producing agentic trajectories with an average length of 45K tokens. Based on this, we train Agents-A1 with a three-stage recipe. First, we perform full-domain supervised fine-tuning to align the base model with broad agentic behaviors. Second, we train domain-level teacher models to capture specialized expertise in each domain. Third, we propose a multi-teacher domain-routed on-policy distillation with salient vocabulary alignment to improve knowledge transfer efficiency across different domains, unifying six heterogeneous domains into one deployable student model. Agents-A1 achieves strong and broad performance for long-horizon agent benchmarks. Compared with 1T-parameter model such as Kimi-K2.6 and DeepSeek-V4-pro, Agents-A1 achieves leading results on SEAL-0 (56.4), IFBench (80.6), HiPhO (46.4), FrontierScience-Olympiad (79.0), and MolBench-Bind (56.8), and remains highly competitive on SciCode (44.3), HLE (47.6) and BrowseComp (75.5). We hope this work provides the community with a practical path for scaling the horizon using a 35B agent that can reach or match the performance of 1T models on long-horizon tasks.

cs.CL↗

arXiv2026

Labels Matter More Than Models: Rethinking the Unsupervised Paradigm in Time Series Anomaly Detection

Time series anomaly detection (TSAD) is a critical data mining task often constrained by label scarcity. Consequently, current research predominantly focuses on Unsupervised Time-series Anomaly Detection (UTAD), relying on increasingly complex architectures to model normal data distributions. However, this algorithm-centric trend often overlooks the significant performance gains achievable from limited anomaly labels available in practical scenarios. This paper challenges the premise that algorithmic complexity is the optimal path for TSAD. Instead of proposing another intricate unsupervised model, we present a comprehensive benchmark and empirical study to rigorously compare supervised and unsupervised paradigms. To isolate the value of labels, we introduce \stand, a deliberately minimalist supervised baseline. Extensive experiments on five public datasets demonstrate that: (1) Labels matter more than models: under a limited labeling budget, simple supervised models significantly outperform complex state-of-the-art unsupervised methods; (2) Supervision yields higher returns: the performance gain from minimal supervision far exceeds the incremental gains from architectural innovations; and (3) Practicality: \stand~exhibits superior prediction consistency and anomaly localization compared to unsupervised counterparts. These findings advocate for a paradigm shift in TSAD research, urging the community to prioritize data-centric label utilization over purely algorithmic complexity. The code and benchmark are publicly available at https://github.com/EmorZz1G/STAND.

cs.LG↗

arXiv2026

Intern-S1-Pro: Scientific Multimodal Foundation Model at Trillion Scale

We introduce Intern-S1-Pro, the first one-trillion-parameter scientific multimodal foundation model. Scaling to this unprecedented size, the model delivers a comprehensive enhancement across both general and scientific domains. Beyond stronger reasoning and image-text understanding capabilities, its intelligence is augmented with advanced agent capabilities. Simultaneously, its scientific expertise has been vastly expanded to master over 100 specialized tasks across critical science fields, including chemistry, materials, life sciences, and earth sciences. Achieving this massive scale is made possible by the robust infrastructure support of XTuner and LMDeploy, which facilitates highly efficient Reinforcement Learning (RL) training at the 1-trillion parameter level while ensuring strict precision consistency between training and inference. By seamlessly integrating these advancements, Intern-S1-Pro further fortifies the fusion of general and specialized intelligence, working as a Specializable Generalist, demonstrating its position in the top tier of open-source models for general capabilities, while outperforming proprietary models in the depth of specialized scientific tasks.

cs.LG↗

arXiv2026

PathFinder: Advancing Path Loss Prediction for Single-to-Multi-Transmitter Scenario

Radio path loss prediction (RPP) is critical for optimizing 5G networks and enabling IoT, smart city, and similar applications. However, current deep learning-based RPP methods lack proactive environmental modeling, struggle with realistic multi-transmitter scenarios, and generalize poorly under distribution shifts, particularly when training/testing environments differ in building density or transmitter configurations. This paper identifies three key issues: (1) passive environmental modeling that overlooks transmitters and key environmental features; (2) overemphasis on single-transmitter scenarios despite real-world multi-transmitter prevalence; (3) excessive focus on in-distribution performance while neglecting distribution shift challenges. To address these, we propose PathFinder, a novel architecture that actively models buildings and transmitters via disentangled feature encoding and integrates Mask-Guided Low-Rank Attention to independently focus on receiver and building regions. We also introduce a Transmitter-Oriented Mixup strategy for robust training and a new benchmark, single-to-multi-transmitter RPP (S2MT-RPP), tailored to evaluate extrapolation performance (multi-transmitter testing after single-transmitter training). Experimental results show PathFinder outperforms state-of-the-art methods significantly, especially in challenging multi-transmitter scenarios. Our code and project site are available at: https://emorzz1g.github.io/PathFinder/.

cs.LG↗

arXiv2026

InternAgent-1.5: A Unified Agentic Framework for Long-Horizon Autonomous Scientific Discovery

We introduce InternAgent-1.5, a unified system designed for end-to-end scientific discovery across computational and empirical domains. The system is built on a structured architecture composed of three coordinated subsystems for generation, verification, and evolution. These subsystems are supported by foundational capabilities for deep research, solution optimization, and long horizon memory. The architecture allows InternAgent-1.5 to operate continuously across extended discovery cycles while maintaining coherent and improving behavior. It also enables the system to coordinate computational modeling and laboratory experimentation within a single unified system. We evaluate InternAgent-1.5 on scientific reasoning benchmarks such as GAIA, HLE, GPQA, and FrontierScience, and the system achieves leading performance that demonstrates strong foundational capabilities. Beyond these benchmarks, we further assess two categories of discovery tasks. In algorithm discovery tasks, InternAgent-1.5 autonomously designs competitive methods for core machine learning problems. In empirical discovery tasks, it executes complete computational or wet lab experiments and produces scientific findings in earth, life, biological, and physical domains. Overall, these results show that InternAgent-1.5 provides a general and scalable framework for autonomous scientific discovery.

cs.AI↗

arXiv2026

Is My RPC Response Reliable? Detecting RPC Bugs in Ethereum Blockchain Client under Context

Blockchain clients are fundamental software for running blockchain nodes. They provide users with various RPC (Remote Procedure Call) interfaces to interact with the blockchain. These RPC methods are expected to follow the same specification across different blockchain nodes, providing users with seamless interaction. However, there have been continuous reports on various RPC bugs that can cause unexpected responses or even Denial of Service weakness. Existing studies on blockchain RPC bug detection mainly focus on generating the RPC method calls for testing blockchain clients. However, a wide range of the reported RPC bugs are triggered in various blockchain contexts. To the best of our knowledge, little attention is paid to generating proper contexts that can trigger these context-dependent RPC bugs. In this work, we propose EthCRAFT, a Context-aware RPC Analysis and Fuzzing Tool for client RPC bug detection. EthCRAFT first proposes to explore the state transition program space of blockchain clients and generate various transactions to construct the context. EthCRAFT then designs a context-aware RPC method call generation method to send RPC calls to the blockchain clients. The responses of 5 different client implementations are used as cross-referring oracles to detect the RPC bugs. We evaluate EthCRAFT on real-world RPC bugs collected from the GitHub issues of Ethereum client implementations. Experiment results show that EthCRAFT outperforms existing client RPC detectors by detecting more RPC bugs. Moreover, EthCRAFT has found six new bugs in major Ethereum clients and reported them to the developers. One of the bug fixes has been written into breaking changes in the client's updates. Three of our bug reports have been offered a vulnerability bounty by the Ethereum Foundation.

cs.SE↗

arXiv2025

MVQA-68K: A Multi-dimensional and Causally-annotated Dataset with Quality Interpretability for Video Assessment

With the rapid advancement of video generation models such as Sora, video quality assessment (VQA) is becoming increasingly crucial for selecting high-quality videos from large-scale datasets used in pre-training. Traditional VQA methods, typically producing single numerical scores, often lack comprehensiveness and interpretability. To address these challenges, we introduce MVQA-68K, a novel multi-dimensional VQA dataset comprising over 68,000 carefully annotated videos, covering seven essential quality dimensions: overall aesthetics, camera movement, dynamic degree, texture detail, composition, visual quality, and factual consistency. Each annotation includes detailed chain-of-thought reasoning to facilitate interpretability and comprehensive understanding. Extensive experiments demonstrate that MVQA-68K significantly enhances the performance of various multimodal large language models (MLLMs) on the VQA task, achieving state-of-the-art results not only on our internal test set (Fig.1) but also on public benchmarks including LSVQ-test, LSVQ-1080p, and LIVE-VQC. Meantime, incorporating explicit reasoning process during VQA training substantially boosts the zero-shot generalization. Code and dataset will be available at github: https://github.com/Controller01-ai/MVQA-68K

cs.CV↗

arXiv2025

CCE: Confidence-Consistency Evaluation for Time Series Anomaly Detection

Time Series Anomaly Detection metrics serve as crucial tools for model evaluation. However, existing metrics suffer from several limitations: insufficient discriminative power, strong hyperparameter dependency, sensitivity to perturbations, and high computational overhead. This paper introduces Confidence-Consistency Evaluation (CCE), a novel evaluation metric that simultaneously measures prediction confidence and uncertainty consistency. By employing Bayesian estimation to quantify the uncertainty of anomaly scores, we construct both global and event-level confidence and consistency scores for model predictions, resulting in a concise CCE metric. Theoretically and experimentally, we demonstrate that CCE possesses strict boundedness, Lipschitz robustness against score perturbations, and linear time complexity $\mathcal{O}(n)$. Furthermore, we establish RankEval, a benchmark for comparing the ranking capabilities of various metrics. RankEval represents the first standardized and reproducible evaluation pipeline that enables objective comparison of evaluation metrics. Both CCE and RankEval implementations are fully open-source.

cs.LG↗

arXiv2025

PatchAD: A Lightweight Patch-based MLP-Mixer for Time Series Anomaly Detection

Time series anomaly detection is a pivotal task in data analysis, yet it poses the challenge of discerning normal and abnormal patterns in label-deficient scenarios. While prior studies have largely employed reconstruction-based approaches, which limit the models' representational capacities. Moreover, existing deep learning-based methods are not sufficiently lightweight. Addressing these issues, we present PatchAD, our novel, highly efficient multiscale patch-based MLP-Mixer architecture that utilizes contrastive learning for representation extraction and anomaly detection. With its four distinct MLP Mixers and innovative dual project constraint module, PatchAD mitigates potential model degradation and offers a lightweight solution, requiring only $0.403M$ parameters. Its efficacy is demonstrated by state-of-the-art results across $8$ datasets sourced from different application scenarios, outperforming over $30$ comparative algorithms. PatchAD significantly improves the classical F1 score by 6.84%, the Aff-F1 score by 4.27%, and the V-ROC by 2.49%. Simultaneously, an in-depth analysis of the mechanisms underlying PatchAD has been conducted from both theoretical and experimental perspectives, validating the design motivations of the model. The code is publicly available at https://github.com/EmorZz1G/PatchAD.

cs.LG↗

arXiv2025

SimAD: A Simple Dissimilarity-based Approach for Time Series Anomaly Detection

Despite the prevalence of reconstruction-based deep learning methods, time series anomaly detection remains a tremendous challenge. Existing approaches often struggle with limited temporal contexts, insufficient representation of normal patterns, and flawed evaluation metrics, all of which hinder their effectiveness in detecting anomalous behavior. To address these issues, we introduce a $\textbf{Sim}$ple dissimilarity-based approach for time series $\textbf{A}$nomaly $\textbf{D}$etection, referred to as $\textbf{SimAD}$. Specifically, SimAD first incorporates a patching-based feature extractor capable of processing extended temporal windows and employs the EmbedPatch encoder to fully integrate normal behavioral patterns. Second, we design an innovative ContrastFusion module in SimAD, which strengthens the robustness of anomaly detection by highlighting the distributional differences between normal and abnormal data. Third, we introduce two robust enhanced evaluation metrics, Unbiased Affiliation (UAff) and Normalized Affiliation (NAff), designed to overcome the limitations of existing metrics by providing better distinctiveness and semantic clarity. The reliability of these two metrics has been demonstrated by both theoretical and experimental analyses. Experiments conducted on seven diverse time series datasets clearly demonstrate SimAD's superior performance compared to state-of-the-art methods, achieving relative improvements of $\textbf{19.85%}$ on F1, $\textbf{4.44%}$ on Aff-F1, $\textbf{77.79%}$ on NAff-F1, and $\textbf{9.69%}$ on AUC on six multivariate datasets. Code and pre-trained models are available at https://github.com/EmorZz1G/SimAD.

cs.LG↗

arXiv2025

AgentDNS: A Root Domain Naming System for LLM Agents

The rapid evolution of Large Language Model (LLM) agents has highlighted critical challenges in cross-vendor service discovery, interoperability, and communication. Existing protocols like model context protocol and agent-to-agent protocol have made significant strides in standardizing interoperability between agents and tools, as well as communication among multi-agents. However, there remains a lack of standardized protocols and solutions for service discovery across different agent and tool vendors. In this paper, we propose AgentDNS, a root domain naming and service discovery system designed to enable LLM agents to autonomously discover, resolve, and securely invoke third-party agent and tool services across organizational and technological boundaries. Inspired by the principles of the traditional DNS, AgentDNS introduces a structured mechanism for service registration, semantic service discovery, secure invocation, and unified billing. We detail the architecture, core functionalities, and use cases of AgentDNS, demonstrating its potential to streamline multi-agent collaboration in real-world scenarios. The source code will be published on https://github.com/agentdns.

cs.AI↗

arXiv2024

A New Perspective on Time Series Anomaly Detection: Faster Patch-based Broad Learning System

Time series anomaly detection (TSAD) has been a research hotspot in both academia and industry in recent years. Deep learning methods have become the mainstream research direction due to their excellent performance. However, new viewpoints have emerged in recent TSAD research. Deep learning is not required for TSAD due to limitations such as slow deep learning speed. The Broad Learning System (BLS) is a shallow network framework that benefits from its ease of optimization and speed. It has been shown to outperform machine learning approaches while remaining competitive with deep learning. Based on the current situation of TSAD, we propose the Contrastive Patch-based Broad Learning System (CPatchBLS). This is a new exploration of patching technique and BLS, providing a new perspective for TSAD. We construct Dual-PatchBLS as a base through patching and Simple Kernel Perturbation (SKP) and utilize contrastive learning to capture the differences between normal and abnormal data under different representations. To compensate for the temporal semantic loss caused by various patching, we propose CPatchBLS with model level integration, which takes advantage of BLS's fast feature to build model-level integration and improve model detection. Using five real-world series anomaly detection datasets, we confirmed the method's efficacy, outperforming previous deep learning and machine learning methods while retaining a high level of computing efficiency.

cs.LG↗

arXiv2024

DAppSCAN: Building Large-Scale Datasets for Smart Contract Weaknesses in DApp Projects

The Smart Contract Weakness Classification Registry (SWC Registry) is a widely recognized list of smart contract weaknesses specific to the Ethereum platform. Despite the SWC Registry not being updated with new entries since 2020, the sustained development of smart contract analysis tools for detecting SWC-listed weaknesses highlights their ongoing significance in the field. However, evaluating these tools has proven challenging due to the absence of a large, unbiased, real-world dataset. To address this problem, we aim to build a large-scale SWC weakness dataset from real-world DApp projects. We recruited 22 participants and spent 44 person-months analyzing 1,199 open-source audit reports from 29 security teams. In total, we identified 9,154 weaknesses and developed two distinct datasets, i.e., DAPPSCAN-SOURCE and DAPPSCAN-BYTECODE. The DAPPSCAN-SOURCE dataset comprises 39,904 Solidity files, featuring 1,618 SWC weaknesses sourced from 682 real-world DApp projects. However, the Solidity files in this dataset may not be directly compilable for further analysis. To facilitate automated analysis, we developed a tool capable of automatically identifying dependency relationships within DApp projects and completing missing public libraries. Using this tool, we created DAPPSCAN-BYTECODE dataset, which consists of 6,665 compiled smart contract with 888 SWC weaknesses. Based on DAPPSCAN-BYTECODE, we conducted an empirical study to evaluate the performance of state-of-the-art smart contract weakness detection tools. The evaluation results revealed sub-par performance for these tools in terms of both effectiveness and success detection rate, indicating that future development should prioritize real-world datasets over simplistic toy contracts.

cs.SE↗

arXiv2023

Turn the Rudder: A Beacon of Reentrancy Detection for Smart Contracts on Ethereum

Smart contracts are programs deployed on a blockchain and are immutable once deployed. Reentrancy, one of the most important vulnerabilities in smart contracts, has caused millions of dollars in financial loss. Many reentrancy detection approaches have been proposed. It is necessary to investigate the performance of these approaches to provide useful guidelines for their application. In this work, we conduct a large-scale empirical study on the capability of five well-known or recent reentrancy detection tools such as Mythril and Sailfish. We collect 230,548 verified smart contracts from Etherscan and use detection tools to analyze 139,424 contracts after deduplication, which results in 21,212 contracts with reentrancy issues. Then, we manually examine the defective functions located by the tools in the contracts. From the examination results, we obtain 34 true positive contracts with reentrancy and 21,178 false positive contracts without reentrancy. We also analyze the causes of the true and false positives. Finally, we evaluate the tools based on the two kinds of contracts. The results show that more than 99.8% of the reentrant contracts detected by the tools are false positives with eight types of causes, and the tools can only detect the reentrancy issues caused by call.value(), 58.8% of which can be revealed by the Ethereum's official IDE, Remix. Furthermore, we collect real-world reentrancy attacks reported in the past two years and find that the tools fail to find any issues in the corresponding contracts. Based on the findings, existing works on reentrancy detection appear to have very limited capability, and researchers should turn the rudder to discover and detect new reentrancy patterns except those related to call.value().

cs.SE↗