Searcharxiv⌕ Search

arXiv subjects

Ming Wu

Publications and source records attributed to Ming Wu.

At least 19 recordsLinked to original sources
arXiv2026

Agent Zero Memory: Provenance-Aware Long-Term Memory for LLM Agents

Large language model (LLM) agents need durable, faithful memory of everything a user or organization has said and stored, yet most memory systems commit to a single organizing structure (a fact store, a vector index, or a knowledge graph) and inherit its blind spots. We present Agent Zero Memory, a provenance-aware long-term memory system that distils a user's conversations, files, and connected sources into three parallel memory systems, each capturing a different facet of the same history: an episodic Memory Events timeline that makes when and what changed first-class, an associative entity-event knowledge graph that links people and projects across sessions, and a semantic, curated, citation-locked Hierarchical Documentary Memory (HDM) of durable facts. A retrieval turn runs an intent gate (so self-contained turns add no latency), a source router, and three concurrent agentic searches, one per system, each a tool-using loop over hybrid (embedding + lexical) search under agent-controlled filters; their grounded, cited answers are integrated into one answer with a single confidence. We formalize the reading discipline: every learned item is a provenanced item carrying its origin, timestamp, and evidence pointer, and every answer is read under a citation lock, so it may cite only evidence its reader actually opened; fabrication is structurally excluded and the system abstains rather than guesses. On two public benchmarks the system sets a new state of the art: 95.60% on LongMemEval and 93.60% on LoCoMo, improving over the strongest prior systems by +0.73 and +1.10 points. A controlled study across eight backbone LLMs characterizes the accuracy-cost-latency frontier: accuracy varies by only 3.4 points while per-query cost varies by ~30x, with near-state-of-the-art quality at up to 20x lower cost per query, the signature of memory-driven, rather than model-driven, quality.

cs.CL↗
arXiv2026

From Reasoning Depth to Reasoning Breadth: Evaluating Multi-Point Associative Reasoning in Large Language Models

Large language models (LLMs) have made substantial progress on reasoning tasks that require increasingly long and complex inferential chains. This progress primarily reflects reasoning depth. A complementary and comparatively unexamined capability is reasoning breadth: exploring multiple semantic directions in parallel and integrating the resulting clues into one coherent answer. We introduce MPAR-Bench, a bilingual English-Chinese benchmark that isolates reasoning breadth through multi-point associative reasoning. Inspired by the cooperative game Just One, each item asks a model to recover a hidden target from several independently generated, semantically diverse clues. We construct 1,000 items using a multi-agent clue-generation pipeline, embedding-based diversity filtering, and human verification. Only the answer space is drawn from public word lists, whereas every clue set is generated from scratch. Beyond exact-match accuracy, we evaluate models using accuracy, ANLS, embedding similarity, reasoning-trace verification, and four perturbations: clue masking, order shuffling, distractor injection, and multi-step clues. Across evaluated models, perturbations reduce accuracy by 9-18 percentage points in English and 5-12 percentage points in Chinese. Thinking mode improves standard-setting accuracy, especially in English, but does not consistently reduce sensitivity to perturbations. Case-level analysis also shows that extended reasoning can overturn an initially correct hypothesis. These results indicate that greater reasoning depth does not automatically confer robust reasoning breadth, and that reasoning breadth remains largely uncovered by current benchmarks.

cs.CL↗
arXiv2026

Zero-change foundry compatible silicon photonics MEMS optical switch

Large-scale photonic switches are emerging as essential devices for energy-efficient optical interconnect in data centers and AI/ML clusters as a key enabler for high-bandwidth and low-latency connectivity. Combining micro-electro-mechanical (MEMS) based mechanical reconfigurability with silicon photonic integrated circuits can enable a large-scale, low-loss, programmable platform required for large-scale optical circuit switches. We demonstrate a broadband silicon photonics MEMS switch with more than 30 dB extinction ratio operating in C-band using a zero-change foundry-compatible process and Back-end-of-Line (BEOL) post-processing. The optical switch element exhibits an insertion loss of less than 1.5 dB with a low static power consumption of approx 20 nW at maximum actuation voltage. Our results illustrate that MEMS-based silicon photonics modulators and phase shifters can be used alongside standard silicon photonics components seamlessly in scenarios where performance in terms of footprint, extinction ratio, broad bandwidth, and low-loss operation is of paramount importance.

physics.optics↗
arXiv2026

SkyVLaM: Multimodal Large Language Model for UAV Video Understanding in Remote Sensing

Recent advances in Multimodal Large Language Models (MLLMs) have significantly improved remote sensing (RS) multimodal understanding. Language-conditioned segmentation is crucial for fine-grained target understanding in Unmanned Aerial Vehicle (UAV) videos. However, this task remains challenging due to the prevalence of small, visually ambiguous targets and dynamic aerial perspectives. In this paper, we propose SkyVLaM, a multimodal large language model for UAV video understanding. SkyVLaM constructs sparse tokens directly from patch-level video representations through a temporal basis perceiver, regularizes the sparse basis to encourage complementary temporal cues, and adaptively selects a temporally coherent dense segment for high-resolution inspection. The resulting sparse and dense tokens are jointly processed by a large language model for query-conditioned segmentation. We further build SkyVid, consisting of SkyVid-VGCG and SkyVid-RVOS for video grounded conversation generation and referring video object segmentation, respectively. SkyVid contains 101 videos, 33.6K frames, and 1.53M pixel-level object instances. Experiments show that SkyVLaM provides a more effective allocation of the visual token budget and improves language-conditioned video segmentation in UAV scenarios.

cs.CV↗
arXiv2026

Agentic Code Review in the Terminal: A Trajectory-Level Analysis of Behavior, Cost, and Human-Alignment

Agentic code review in terminal-based environments enables early feedback during local development before pull request creation. However, existing evaluations remain performance-centric and fail to capture the dynamic behaviors of repository-grounded agentic reviewers. Understanding these behaviors is critical for identifying how agentic reviewers succeed, fail, and incur hidden operational costs in practice. Then, we analyze the reviewers' behavior based on their trajectories. Our results show that agentic reviewers achieve higher review precision but incur substantial exploration and validation overhead, while successful reviews are associated with stronger planning and less downstream validation. These findings highlight the potential benefits of trajectory-aware and cost-sensitive evaluation of future agentic code review systems.

cs.SE↗
arXiv2026

Communication-Efficient Verifiable Attention for LLM Inference

Computation integrity of remote large language model (LLM) serving can be questionable. For conventional deep neural networks (DNNs), the existing TEE-shielded DNN partitioning (TSDP) approach uses Trusted Execution Environment (TEE) to compute non-linear components and verify the integrity of linear components offloaded to an untrusted GPU. However, directly applying TSDP to Transformer-based LLMs incurs significant TEE computation and TEE-GPU communication overhead. This paper presents Communication-efficient TEE-GPU Attention (\textsc{VeriAttn}) for accelerating verifiable LLM inference. \textsc{VeriAttn} offloads both linear and non-linear computations of attention to the GPU, while TEE performs verification. Moreover, for prefill, \textsc{VeriAttn} uses a two-level pipeline to overlap data movement, TEE pre-/post-processing, and GPU computation. For decoding, when the key-value cache exceeds available GPU memory, \textsc{VeriAttn} partitions attention across TEE and GPU to reduce repeated key-value transfers. Evaluation on an Intel TDX platform shows that \textsc{VeriAttn} achieves 2.60-3.38$\times$ and 3.86-5.42$\times$ acceleration over TSDP for 6k-token prompts and 10k-token outputs during prefill and decoding, respectively.

cs.LG↗
arXiv2026

Agora: Toward Autonomous Bug Detection in Production-Level Consensus Protocols with LLM Agents

Consensus protocols form the backbone of distributed systems and blockchains, where implementation bugs can cause data corruption and financial losses. While LLM-based approaches show promise in code analysis, they struggle with deep protocol-level logic bugs involving complex state-dependent behaviors across multiple execution stages. We present Agora, a domain-aware multi-agent framework that integrates hypothesis-driven testing with LLM capabilities for systematic protocol verification. Agora employs specialized agents that collaboratively explore protocol state spaces, synthesize attack scenarios using domain-specific constraints, and validate findings through iterative refinement. This explicit role separation enables reasoning about global protocol invariants beyond single-function code analysis. We evaluate Agora on four consensus implementations (Raft, EPaxos, HotStuff, BullShark) using four state-of-the-art LLMs. Agora discovers 15 previously unknown protocol-level logic bugs that violate safety properties, while existing LLM-based agents fail to detect any such protocol-level logic bugs. Our results demonstrate that domain-aware multi-agent collaboration is essential for detecting deep logic bugs in complex protocols.

cs.SE↗
arXiv2026

MemForest: An Efficient Agent Memory System with Hierarchical Temporal Indexing

Memory is a fundamental component for long-context LLM agents, supporting persistent state across interactions through a continuous serve-and-update lifecycle. Despite substantial prior work, many stateful systems retain sequential autoregressive extraction or state-dependent maintenance on the write path, delaying when new evidence becomes queryable. To address these challenges, we present MemForest, a memory framework that reformulates agent memory as a write-efficient temporal data-management problem. MemForest breaks the sequential bottleneck via parallel extraction, decoupling memory construction into concurrent, independent operations. We further introduce MemTree, a hierarchical temporal index that organizes memory as time-ordered trees and replaces global rewrites with localized dirty-path refresh. Dirty summaries can be refreshed in parallel across nodes and trees. End-to-end work remains proportional to incoming content; the logarithmic bound applies only to structural insertion and level-dependent refresh depth in balanced trees. We evaluate MemForest on two long-context benchmarks, LongMemEval-S and LoCoMo. Experiments use Qwen3-4B, Qwen3-30B, and Gemma-4-12B-IT. With Qwen3-30B, MemForest reaches 81.8 percent pass at 1 on LongMemEval-S, while its input-normalized build rate is 6.0 times that of EverMemOS. On LoCoMo categories 1 to 4, it reaches 84.09 percent, within 0.13 percentage points of EverMemOS; on a matched conversation, its build rate is 9.5 times higher. These results show that MemForest reduces memory-freshness latency while retaining strong answer quality.

cs.DB↗
arXiv2026

SaaS-Bench: Can Computer-Use Agents Leverage Real-World SaaS to Solve Professional Workflows?

Computer-Using Agents (CUAs) are rapidly extending large language models (LLMs) beyond text-based reasoning toward action execution in more complex environments, such as web browsers and graphical user interfaces (GUIs). However, existing web and GUI agent benchmarks often rely on simplified settings, isolated tasks, or short-horizon interactions, making it difficult to assess capabilities of agents in realistic professional workflows. Software-as-a-Service (SaaS) environments are a natural choice for CUA evaluation, as they host a large share of modern digital work and naturally involve dynamic system states, cross-application coordination, domain-specific knowledge, and long-horizon dependencies. To this end, we introduce SaaS-Bench, a benchmark built on 23 deployable SaaS systems across six professional domains, containing 106 tasks grounded in realistic work scenarios. These tasks require long-horizon execution, cover both text-only and multimodal settings, and are evaluated with weighted verification checkpoints that measure strict task completion and partial progress. Experiments show that representative LLM-based agents struggle on SaaS-Bench, with even the strongest model completing fewer than 4% of tasks end-to-end, exposing limitations in planning, state tracking, cross-application context maintenance, and error recovery. Code are available at https://github.com/UniPat-AI/SaaS-Bench for reproduction.

cs.AI↗
arXiv2026

RoadmapBench: Evaluating Long-Horizon Agentic Software Development Across Version Upgrades

Coding agents are increasingly deployed in real software development, where a single version iteration requires months of coordinated work across many files. However, most existing benchmarks focus predominantly on single-issue bug fixes from Python repositories, with coarse pass/fail evaluation outcomes, and thus fail to capture long-horizon, multi-target development at real engineering scale. To address this gap, we present RoadmapBench, a benchmark of 115 long-horizon coding tasks grounded in real open-source version upgrades across 17 repositories and 5 programming languages. Each task places the agent on a source-version code snapshot and provides a multi-target roadmap instruction requiring it to implement the functionality introduced in the target version, with a median modification of 3,700 lines across 51 files. We conduct a systematic evaluation on thirteen frontier models and find that even the strongest, Claude-Opus-4.7, resolves only 39.1% of tasks, while the weakest achieves merely 5.2%, in stark contrast to existing bug-fix benchmarks, suggesting that long-horizon software development remains a largely unsolved problem.

cs.SE↗
arXiv2026

HGP-Mamba: Integrating Histology and Generated Protein Features for Mamba-based Multimodal Survival Risk Prediction

Recent advances in multimodal learning have significantly improved cancer survival risk prediction. However, the joint prognostic potential of protein markers and histopathology images remains underexplored, largely due to the high cost and limited availability of protein expression profiling. To address this challenge, we propose HGP-Mamba, a Mamba-based multimodal framework that efficiently integrates histological with generated protein features for survival risk prediction. Specifically, we introduce a protein feature extractor (PFE) that leverages pretrained foundation models to derive high-throughput protein embeddings directly from Whole Slide Images (WSIs), enabling data-efficient incorporation of molecular information. Together with histology embeddings that capture morphological patterns, we further introduce the Local Interaction-aware Mamba (LiAM) for fine-grained feature interaction and the Global Interaction-enhanced Mamba (GiEM) to promote holistic modality fusion at the slide level, thus capture complex cross-modal dependencies. Experiments on four public cancer datasets demonstrate that HGP-Mamba achieves state-of-the-art performance while maintaining superior computational efficiency compared with existing methods. Our source code is publicly available at https://github.com/Daijing-ai/HGP-Mamba.git.

cs.CV↗
arXiv2026

Inference-time Alignment via Sparse Junction Steering

Token-level steering has emerged as a pivotal approach for inference-time alignment, enabling fine grained control over large language models by modulating their output distributions without parameter updates. While effective, existing methods rely on dense intervention at every decoding step. This persistent manipulation not only incurs substantial computational overhead but also risks compromising generation quality by excessively drifting from the model's intrinsic distribution. In this work, we show that dense intervention is unnecessary and propose Sparse Inference time Alignment (SIA), which performs sparse junction steering by intervening only at critical decision points along the generation trajectory. Our key insight is that high entropy junctions mark pivotal decision points in the generation trajectory and are particularly susceptible to misalignment, indicating the need to introduce alignment related reward signals at these points. Extensive experiments across different model families and alignment objectives show that steering only 20% to 80% of tokens achieves superior alignment-efficiency trade offs. For strong base models such as Qwen3, intervening on as few as 20% of tokens matches or even surpasses heavily post-trained instruct models. This sparsity enables stronger guidance while better preserving the model's native distribution, integrates seamlessly with search based methods such as Best-of-N, and reduces computational cost by up to 6x.

cs.CL↗
arXiv2026

AgenticSCR: An Autonomous Agentic Secure Code Review for Immature Vulnerabilities Detection

Secure code review is critical during pre-integration, where Atlassian developers rely on lightweight analysis tools, while deep security assessment is deferred to later stages, delaying feedback and increasing remediation costs. Existing static analyzers are often noisy and struggle with context-dependent or partially manifested vulnerabilities, while static large language model (LLM) reviewers are constrained by context windows and lack tool interaction. Agentic AI, which combines LLMs with code navigation, shows promise; however, its effectiveness for early-stage secure code review remains underexplored. We present AgenticSCR, an agentic secure code reviewer augmented with security-focused semantic memory that grounds reasoning in structured security knowledge to detect vulnerabilities before they fully manifest. AgenticSCR achieves at least 153% relative improvement in generating comments with correct localization, vulnerability type, and relevance over static LLM baseline, multi-agent reviewer, and SAST tools. In a shadow deployment, 54% of its comments were validated by security engineers for developer reporting, demonstrating practical utility while underscoring the difficulty of the task. These findings position the security-focused semantic memory as a promising direction for agentic secure code review, enabling early-stage vulnerability identification. Our approach builds an important step toward reliable localization, detection, and explanation in shift-left security practices

cs.CR↗
arXiv2026

HalluJudge: A Reference-Free Hallucination Detection for Context Misalignment in Code Review Automation

Large Language models (LLMs) have shown strong capabilities in code review automation, such as review comment generation, yet they suffer from hallucinations -- where the generated review comments are ungrounded in the actual code -- poses a significant challenge to the adoption of LLMs in code review workflows. To address this, we explore effective and scalable methods for a hallucination detection in LLM-generated code review comments without the reference. In this work, we design HalluJudge that aims to assess the grounding of generated review comments based on the context alignment. HalluJudge includes four key strategies ranging from direct assessment to structured multi-branch reasoning (e.g., Tree-of-Thoughts). We conduct a comprehensive evaluation of these assessment strategies across Atlassian's enterprise-scale software projects to examine the effectiveness and cost-efficiency of HalluJudge. Furthermore, we analyze the alignment between HalluJudge's judgment and developer preference of the actual LLM-generated code review comments in the real-world production. Our results show that the hallucination assessment in HalluJudge is cost-effective with an F1 score of 0.85 and an average cost of $0.009. On average, 67% of the HalluJudge assessments are aligned with the developer preference of the actual LLM-generated review comments in the online production. Our results suggest that HalluJudge can serve as a practical safeguard to reduce developers' exposure to hallucinated comments, fostering trust in AI-assisted code reviews.

cs.SE↗
arXiv2026

BabyVision: Visual Reasoning Beyond Language

While humans develop core visual skills long before acquiring language, contemporary Multimodal LLMs (MLLMs) still rely heavily on linguistic priors to compensate for their fragile visual understanding. We uncovered a crucial fact: state-of-the-art MLLMs consistently fail on basic visual tasks that humans, even 3-year-olds, can solve effortlessly. To systematically investigate this gap, we introduce BabyVision, a benchmark designed to assess core visual abilities independent of linguistic knowledge for MLLMs. BabyVision spans a wide range of tasks, with 388 items divided into 22 subclasses across four key categories. Empirical results and human evaluation reveal that leading MLLMs perform significantly below human baselines. Gemini3-Pro-Preview scores 49.7, lagging behind 6-year-old humans and falling well behind the average adult score of 94.1. These results show despite excelling in knowledge-heavy evaluations, current MLLMs still lack fundamental visual primitives. Progress in BabyVision represents a step toward human-level visual perception and reasoning capabilities. We also explore solving visual reasoning with generation models by proposing BabyVision-Gen and automatic evaluation toolkit. Our code and benchmark data are released at https://github.com/UniPat-AI/BabyVision for reproduction.

cs.CV↗
arXiv2026

RovoDev Code Reviewer: A Large-Scale Online Evaluation of LLM-based Code Review Automation at Atlassian

Large Language Models (LLMs)-powered code review automation has the potential to transform code review workflows. Despite the advances of LLM-powered code review comment generation approaches, several practical challenges remain for designing enterprise-grade code review automation tools. In particular, this paper aims at answering the practical question: how can we design a review-guided, context-aware, quality-checked code review comment generation without fine-tuning? In this paper, we present RovoDev Code Reviewer, an enterprise-grade LLM-based code review automation tool designed and deployed at scale within Atlassian's development ecosystem with seamless integration into Atlassian's Bitbucket. Through the offline, online, user feedback evaluations over a one-year period, we conclude that RovoDev Code Reviewer is effective in generating code review comments that could lead to code resolution for 38.70% (i.e., comments that triggered code changes in the subsequent commits); and offers the promise of accelerating feedback cycles (i.e., decreasing the PR cycle time by 30.8%), alleviating reviewer workload (i.e., reducing the number of human-written comments by 35.6%), and improving overall software quality (i.e., finding errors with actionable suggestions).

cs.SE↗
arXiv2025

Active Noise Control Method Using Time Domain Neural Networks for Path Decoupling

In decentralized active noise control (ANC) systems, crosstalk between multichannel secondary sources and error microphones significantly degrades control accuracy. Moreover, prefiltering reference signals in filtered-x (Fx) type algorithms may further introduce modeling errors. A theoretical analysis of the Fx-based decentralized control algorithm was performed, which reveals how prefiltering and crosstalk affect the control performance. Then, a hybrid method combining fixed-value neural networks and adaptive strategies was proposed for efficient decentralized ANC. The adaptive filter models the primary path of its own channel online using the least mean square (LMS) algorithm while the neural network (named DecNet) is used for secondary paths inverting and decoupling. The hybrid DecNet-LMS algorithm was implemented in the time domain to guarantee causality and avoid latency. Simulation results with measured acoustic paths show that the proposed method outperforms the existing ANC algorithms using either traditional adaptive filters or neural network-based fixed-coefficient methods under different acoustic conditions.

eess.SY↗
arXiv2025

What Types of Code Review Comments Do Developers Most Frequently Resolve?

Large language model (LLM)-powered code review automation tools have been introduced to generate code review comments. However, not all generated comments will drive code changes. Understanding what types of generated review comments are likely to trigger code changes is crucial for identifying those that are actionable. In this paper, we set out to investigate (1) the types of review comments written by humans and LLMs, and (2) the types of generated comments that are most frequently resolved by developers. To do so, we developed an LLM-as-a-Judge to automatically classify review comments based on our own taxonomy of five categories. Our empirical study confirms that (1) the LLM reviewer and human reviewers exhibit distinct strengths and weaknesses depending on the project context, and (2) readability, bugs, and maintainability-related comments had higher resolution rates than those focused on code design. These results suggest that a substantial proportion of LLM-generated comments are actionable and can be resolved by developers. Our work highlights the complementarity between LLM and human reviewers and offers suggestions to improve the practical effectiveness of LLM-powered code review tools.

cs.SE↗