arXiv subjects

Yawen Wang

Publications and source records attributed to Yawen Wang.

At least 19 recordsLinked to original sources

arXiv2026

VCE-Skill: Enhancing Skill Self-Evolution with Version-Change Experience

Agents increasingly rely on reusable skills to encode task knowledge, tool-use procedures, and validation rules. Existing skill self-evolution methods primarily revise skills using execution trajectories collected from current tasks, leaving the evolution knowledge accumulated in public skill version histories largely untapped. Our pilot study reveals a clear complementarity between the two sources: public skill changes provide reusable evolution priors, whereas trajectories provide evidence grounded in the current task. Motivated by this, we propose VCE-Skill, which distills noisy and implementation-specific public skill changes into reusable, structured version-change experience and adaptively fuses it with trajectory-derived proposals from the base evolver, thereby exploiting external experience while retaining task-specific evidence. Extensive experiments demonstrate that VCE-Skill improves skill self-evolution, increasing mean scores by 3.20--4.98 points; transfer experiments further show that the resulting skills achieve stronger cross-model transfer performance. Our work highlights public skill version changes as a previously underexplored yet effective source of prior knowledge and advances trajectory-driven skill self-evolution.

cs.MA↗

arXiv2026

Diagnosis-Driven Automatic Repair for Agentic Workflow via Symbolic Inference

Platform-orchestrated agentic workflows have become a popular paradigm for developing LLM-based applications. However, their reliability remains a major challenge due to the uncertainty of LLM outputs, complex inter-node dependencies, and heterogeneous tool interactions. Existing agentic workflow optimization and agent enhancement methods primarily rely on trajectory-level feedback. Without explicitly identifying the underlying failure root causes, their resulting repair plans are often insufficiently targeted. We propose FlowFixer, a diagnosis-driven automated repair framework for agentic workflows. FlowFixer first transforms workflow executions into unified symbolic traces and performs symbolic inference to derive executable behavioral specifications that capture node correctness, temporal dependencies, and causal relationships. Based on specification verification, it conducts failure attribution and root cause analysis, and then generates targeted repair patches. To reduce verification costs, FlowFixer further employs a multi-dimensional pre-execution assessment to filter infeasible repairs before dynamic verification. We evaluate FlowFixer on workflow failures collected from three popular development platforms: Dify, Coze and n8n. Results show that FlowFixer achieves a repair success rate of 71.3%, outperforming state-of-the-art baselines by 11.9% to 27.6%. It also improves failure attribution accuracy by 4.8% to 33.1% and root cause analysis accuracy by 15.3% to 38.8%. This work offers a new perspective on reliable diagnosis and repair of agentic workflows through symbolic modeling and inference.

cs.SE↗

arXiv2026

From Failed Trajectories to Reliable LLM Agents: Diagnosing and Repairing Harness Flaws

LLM agents increasingly rely on agent harness: the runtime infrastructure around the base model that defines execution environments, tool interfaces, context, lifecycle orchestration, observability, verification, and governance. Existing self-improving agents and automatic harness evolution methods mainly improve agents through runtime supervision, prompt optimization, workflow search, or harness modification based on final outcomes. However, they often fail to diagnose where the responsible evidence lies in failed trajectories and which harness implementation mechanism causes the unreliable behavior, resulting in broad, indirect, or poorly scoped changes. This paper proposes HarnessFix, a trace-grounded and diagnosis-driven framework for repairing agent harnesses. HarnessFix compiles raw execution traces and harness artifacts into a Harness-aware Trace Intermediate Representation (HTIR), which normalizes fragmented trajectory evidence, captures step-level data-flow and control-flow relations, and aligns runtime steps with the harness artifacts that shape their behavior. It then attributes failures to responsible steps and harness artifacts, and consolidates recurring diagnoses into repair-oriented flaw records. Finally, HarnessFix maps these records to scoped repair operators, generates patches under flaw-specific repair specifications, and accepts them through regression-aware validation. We evaluate HarnessFix on four popular benchmarks, and results show that it improves the performance over the initial harnesses by 6.3% to 18.4%, significantly outperforming human-designed and self-evolution baselines. HarnessFix highlights the value of treating failed trajectories not only as feedback signals, but also as structured evidence for diagnosing and repairing the harness mechanisms behind agent failures.

cs.SE↗

arXiv2026

OrchJail: Jailbreaking Tool-Calling Text-to-Image Agents by Orchestration-Guided Fuzzing

Tool-calling text-to-image (T2I) agents can plan and execute multi-step tool chains to accomplish complex generation and editing queries. However, this capability introduces a new safety attack surface: harmful outputs may arise from tool orchestration, where individually benign steps combine into unsafe results, making prompt-only jailbreak techniques insufficient. We present OrchJail, an orchestration-guided fuzzing framework for jailbreaking tool-calling T2I agents. Its core idea is to exploit high-risk tool-orchestration patterns: by learning from successful jailbreak tool-calling traces and their causal relationships to prompt wording, OrchJail directly guides the fuzzing search toward prompts that are more likely to trigger unsafe multi-step tool behaviors, rather than relying on surface-level textual perturbations. Extensive experiments demonstrate that OrchJail improves jailbreak effectiveness and efficiency across representative toolcalling T2I agents, achieving higher attack success rates, better image fidelity, and lower query costs, while remaining robust against common jailbreak defenses. Our work highlights tool orchestration as a critical, previously unexplored attack surface and provides a novel framework for uncovering safety risks in T2I agents.

cs.MA↗

arXiv2026

Where Did It Go Wrong? Capability-Oriented Failure Attribution for Vision-and-Language Navigation Agents

Embodied agents in safety-critical applications such as Vision-Language Navigation (VLN) rely on multiple interdependent capabilities (e.g., perception, memory, planning, decision), making failures difficult to localize and attribute. Existing testing methods are largely system-level and provide limited insight into which capability deficiencies cause task failures. We propose a capability-oriented testing approach that enables failure detection and attribution by combining (1) adaptive test case generation via seed selection and mutation, (2) capability oracles for identifying capability-specific errors, and (3) a feedback mechanism that attributes failures to capabilities and guides further test generation. Experiments show that our method discovers more failure cases and more accurately pinpoints capability-level deficiencies than state-of-the-art baselines, providing more interpretable and actionable guidance for improving embodied agents.

cs.MA↗

arXiv2026

Seeing the Whole Elephant: A Benchmark for Failure Attribution in LLM-based Multi-Agent Systems

Failure attribution, i.e., identifying the responsible agent and decisive step of a failure, is particularly challenging in LLM-based multi-agent systems (MAS) due to their natural-language reasoning, nondeterministic outputs, and intricate interaction dynamics. A reliable benchmark is therefore essential to guide and evaluate attribution techniques. Yet existing benchmarks rely on partially observable traces that capture only agent outputs, omitting the inputs and context that developers actually use when debugging. We argue that failure attribution should be studied under full execution observability, aligning with real-world developer-facing scenarios where complete traces, rather than only outputs, are accessible for diagnosis. To this end, we introduce TraceElephant, a benchmark designed for failure attribution with full execution traces and reproducible environments. We then systematically evaluate failure attribution techniques across various configurations. Specifically, full traces improve attribution accuracy by up to 76\% over a partial-observation counterpart, confirming that missing inputs obscure many failure causes. TraceElephant provides a foundation for follow-up failure attribution research, promoting evaluation practices that reflect real-world debugging and supporting the development of more transparent MASs.

cs.MA↗

arXiv2026

NTIRE 2026 The 3rd Restore Any Image Model (RAIM) Challenge: AI Flash Portrait (Track 3)

In this paper, we present a comprehensive overview of the NTIRE 2026 3rd Restore Any Image Model (RAIM) challenge, with a specific focus on Track 3: AI Flash Portrait. Despite significant advancements in deep learning for image restoration, existing models still encounter substantial challenges in real-world low-light portrait scenarios. Specifically, they struggle to achieve an optimal balance among noise suppression, detail preservation, and faithful illumination and color reproduction. To bridge this gap, this challenge aims to establish a novel benchmark for real-world low-light portrait restoration. We comprehensively evaluate the proposed algorithms utilizing a hybrid evaluation system that integrates objective quantitative metrics with rigorous subjective assessment protocols. For this competition, we provide a dataset containing 800 groups of real-captured low-light portrait data. Each group consists of a 1K-resolution low-light input image, a 1K ground truth (GT), and a 1K person mask. This challenge has garnered widespread attention from both academia and industry, attracting over 100 participating teams and receiving more than 3,000 valid submissions. This report details the motivation behind the challenge, the dataset construction process, the evaluation metrics, and the various phases of the competition. The released dataset and baseline code for this track are publicly available from the same \href{https://github.com/zsn1434/AI_Flash-BaseLine/tree/main}{GitHub repository}, and the official challenge webpage is hosted on \href{https://www.codabench.org/competitions/12885/}{CodaBench}.

cs.CV↗

arXiv2026

AIoT-based Continuous, Contextualized, and Explainable Driving Assessment for Older Adults

The world is undergoing a major demographic shift as older adults become a rapidly growing share of the population, creating new challenges for driving safety. In car-dependent regions such as the United States, driving remains essential for independence, access to services, and social participation. At the same time, aging can introduce gradual changes in vision, attention, reaction time, and driving control that quietly reduce safety. Today's assessment methods rely largely on infrequent clinic visits or simple screening tools, offering only a brief snapshot and failing to reflect how an older adult actually drives on the road. Our work starts from the observation that everyday driving provides a continuous record of functional ability and captures how a driver responds to traffic, navigates complex roads, and manages routine behavior. Leveraging this insight, we propose AURA, an Artificial Intelligence of Things (AIoT) framework for continuous, real-world assessment of driving safety among older adults. AURA integrates richer in-vehicle sensing, multi-scale behavioral modeling, and context-aware analysis to extract detailed indicators of driving performance from routine trips. It organizes fine-grained actions into longer behavioral trajectories and separates age-related performance changes from situational factors such as traffic, road design, or weather. By integrating sensing, modeling, and interpretation within a privacy-preserving edge architecture, AURA provides a foundation for proactive, individualized support that helps older adults drive safely. This paper outlines the design principles, challenges, and research opportunities needed to build reliable, real-world monitoring systems that promote safer aging behind the wheel.

cs.AI↗

arXiv2026

From Flat Logs to Causal Graphs: Hierarchical Failure Attribution for LLM-based Multi-Agent Systems

LLM-powered Multi-Agent Systems (MAS) have demonstrated remarkable capabilities in complex domains but suffer from inherent fragility and opaque failure mechanisms. Existing failure attribution methods, whether relying on direct prompting, costly replays, or supervised fine-tuning, typically treat execution logs as flat sequences. This linear perspective fails to disentangle the intricate causal links inherent to MAS, leading to weak observability and ambiguous responsibility boundaries. To address these challenges, we propose CHIEF, a novel framework that transforms chaotic trajectories into a structured hierarchical causal graph. It then employs hierarchical oracle-guided backtracking to efficiently prune the search space via sybthesized virtual oracles. Finally, it implements counterfactual attribution via a progressive causal screening strategy to rigorously distinguish true root causes from propagated symptoms. Experiments on Who&When benchmark show that CHIEF outperforms eight strong and state-of-the-art baselines on both agent- and step-level accuracy. Ablation studies further confirm the critical role of each proposed module.

cs.AI↗

arXiv2025

Adversarial Attack on Black-Box Multi-Agent by Adaptive Perturbation

Evaluating security and reliability for multi-agent systems (MAS) is urgent as they become increasingly prevalent in various applications. As an evaluation technique, existing adversarial attack frameworks face certain limitations, e.g., impracticality due to the requirement of white-box information or high control authority, and a lack of stealthiness or effectiveness as they often target all agents or specific fixed agents. To address these issues, we propose AdapAM, a novel framework for adversarial attacks on black-box MAS. AdapAM incorporates two key components: (1) Adaptive Selection Policy simultaneously selects the victim and determines the anticipated malicious action (the action would lead to the worst impact on MAS), balancing effectiveness and stealthiness. (2) Proxy-based Perturbation to Induce Malicious Action utilizes generative adversarial imitation learning to approximate the target MAS, allowing AdapAM to generate perturbed observations using white-box information and thus induce victims to execute malicious action in black-box settings. We evaluate AdapAM across eight multi-agent environments and compare it with four state-of-the-art and commonly-used baselines. Results demonstrate that AdapAM achieves the best attack performance in different perturbation rates. Besides, AdapAM-generated perturbations are the least noisy and hardest to detect, emphasizing the stealthiness.

cs.MA↗

arXiv2025

Automated Network Protocol Testing with LLM Agents

Network protocol testing is fundamental for modern network infrastructure. However, traditional network protocol testing methods are labor-intensive and error-prone, requiring manual interpretation of specifications, test case design, and translation into executable artifacts, typically demanding one person-day of effort per test case. Existing model-based approaches provide partial automation but still involve substantial manual modeling and expert intervention, leading to high costs and limited adaptability to diverse and evolving protocols. In this paper, we propose a first-of-its-kind system called NeTestLLM that takes advantage of multi-agent Large Language Models (LLMs) for end-to-end automated network protocol testing. NeTestLLM employs hierarchical protocol understanding to capture complex specifications, iterative test case generation to improve coverage, a task-specific workflow for executable artifact generation, and runtime feedback analysis for debugging and refinement. NeTestLLM has been deployed in a production environment for several months, receiving positive feedback from domain experts. In experiments, NeTestLLM generated 4,632 test cases for OSPF, RIP, and BGP, covering 41 historical FRRouting bugs compared to 11 by current national standards. The process of generating executable artifacts also improves testing efficiency by a factor of 8.65x compared to manual methods. NeTestLLM provides the first practical LLM-powered solution for automated end-to-end testing of heterogeneous network protocols.

cs.NI↗

arXiv2025

Is it Bigger than a Breadbox: Efficient Cardinality Estimation for Real World Workloads

DB engines produce efficient query execution plans by relying on cost models. Practical implementations estimate cardinality of queries using heuristics, with magic numbers tuned to improve average performance on benchmarks. Empirically, estimation error significantly grows with query complexity. Alternatively, learning-based estimators offer improved accuracy, but add operational complexity preventing their adoption in-practice. Recognizing that query workloads contain highly repetitive subquery patterns, we learn many simple regressors online, each localized to a pattern. The regressor corresponding to a pattern can be randomly-accessed using hash of graph structure of the subquery. Our method has negligible overhead and competes with SoTA learning-based approaches on error metrics. Further, amending PostgreSQL with our method achieves notable accuracy and runtime improvements over traditional methods and drastically reduces operational costs compared to other learned cardinality estimators, thereby offering the most practical and efficient solution on the Pareto frontier. Concretely, simulating JOB-lite workload on IMDb speeds-up execution by 7.5 minutes (>30%) while incurring only 37 seconds overhead for online learning.

cs.DB↗

arXiv2025

Demystifying the Lifecycle of Failures in Platform-Orchestrated Agentic Workflows

Agentic workflows built on low-code orchestration platforms enable rapid development of multi-agent systems, but they also introduce new and poorly understood failure modes that hinder reliability and maintainability. Unlike traditional software systems, failures in agentic workflows often propagate across heterogeneous nodes through natural-language interactions, tool invocations, and dynamic control logic, making failure attribution and repair particularly challenging. In this paper, we present an empirical study of platform-orchestrated agentic workflows from a failure lifecycle perspective, with the goal of characterizing failure manifestations, identifying underlying root causes, and examining corresponding repair strategies. We present AgentFail, a dataset of 307 real-world failure cases collected from two representative agentic workflow platforms. Based on this dataset, we analyze failure patterns, root causes, and repair difficulty for various failure root causes and nodes in the workflow. Our findings reveal key failure mechanisms in agentic workflows and provide actionable guidelines for reliable failure repair, and real-world agentic workflow design.

cs.AI↗

arXiv2025

MUCAR: Benchmarking Multilingual Cross-Modal Ambiguity Resolution for Multimodal Large Language Models

Multimodal Large Language Models (MLLMs) have demonstrated significant advances across numerous vision-language tasks. MLLMs have shown promising capability in aligning visual and textual modalities, allowing them to process image-text pairs with clear and explicit meanings. However, resolving the inherent ambiguities present in real-world language and visual contexts remains a challenge. Existing multimodal benchmarks typically overlook linguistic and visual ambiguities, relying mainly on unimodal context for disambiguation and thus failing to exploit the mutual clarification potential between modalities. To bridge this gap, we introduce MUCAR, a novel and challenging benchmark designed explicitly for evaluating multimodal ambiguity resolution across multilingual and cross-modal scenarios. MUCAR includes first a multilingual dataset where ambiguous textual expressions are uniquely resolved by corresponding visual contexts, and second a dual-ambiguity dataset that systematically pairs ambiguous images with ambiguous textual contexts, with each combination carefully constructed to yield a single, clear interpretation through mutual disambiguation. Extensive evaluations involving 19 state-of-the-art multimodal models--encompassing both open-source and proprietary architectures--reveal substantial gaps compared to human-level performance, highlighting the need for future research into more sophisticated cross-modal ambiguity comprehension methods, further pushing the boundaries of multimodal reasoning.

cs.CL↗

arXiv2025

Robust Multi-agent Communication Based on Decentralization-Oriented Adversarial Training

In typical multi-agent reinforcement learning (MARL) problems, communication is important for agents to share information and make the right decisions. However, due to the complexity of training multi-agent communication, existing methods often fall into the dilemma of local optimization, which leads to the concentration of communication in a limited number of channels and presents an unbalanced structure. Such unbalanced communication policy are vulnerable to abnormal conditions, where the damage of critical communication channels can trigger the crash of the entire system. Inspired by decentralization theory in sociology, we propose DMAC, which enhances the robustness of multi-agent communication policies by retraining them into decentralized patterns. Specifically, we train an adversary DMAC\_Adv which can dynamically identify and mask the critical communication channels, and then apply the adversarial samples generated by DMAC\_Adv to the adversarial learning of the communication policy to force the policy in exploring other potential communication schemes and transition to a decentralized structure. As a training method to improve robustness, DMAC can be fused with any learnable communication policy algorithm. The experimental results in two communication policies and four multi-agent tasks demonstrate that DMAC achieves higher improvement on robustness and performance of communication policy compared with two state-of-the-art and commonly-used baselines. Also, the results demonstrate that DMAC can achieve decentralized communication structure with acceptable communication cost.

cs.MA↗

arXiv2024

Understanding Individual Agent Importance in Multi-Agent System via Counterfactual Reasoning

Explaining multi-agent systems (MAS) is urgent as these systems become increasingly prevalent in various applications. Previous work has proveided explanations for the actions or states of agents, yet falls short in understanding the black-boxed agent's importance within a MAS and the overall team strategy. To bridge this gap, we propose EMAI, a novel agent-level explanation approach that evaluates the individual agent's importance. Inspired by counterfactual reasoning, a larger change in reward caused by the randomized action of agent indicates its higher importance. We model it as a MARL problem to capture interactions across agents. Utilizing counterfactual reasoning, EMAI learns the masking agents to identify important agents. Specifically, we define the optimization function to minimize the reward difference before and after action randomization and introduce sparsity constraints to encourage the exploration of more action randomization of agents during training. The experimental results in seven multi-agent tasks demonstratee that EMAI achieves higher fidelity in explanations than baselines and provides more effective guidance in practical applications concerning understanding policies, launching attacks, and patching policies.

cs.AI↗

arXiv2024

LAVA: Lifetime-Aware VM Allocation with Learned Distributions and Adaptation to Mispredictions

Scheduling virtual machines (VMs) on hosts in cloud data centers dictates efficiency and is an NP-hard problem with incomplete information. Prior work improved VM scheduling with predicted VM lifetimes. Our work further improves lifetime-aware scheduling using repredictions with lifetime distributions versus one-shot prediction. Our approach repredicts and adjusts VM and host lifetimes when incorrect predictions emerge. We also present novel approaches for defragmentation and regular system maintenance, which are essential to our data center reliability and optimizations, and are not explored in prior work. We show repredictions deliver a fundamental advance in effectiveness over one-shot prediction. We call our novel combination of distribution-based lifetime predictions and scheduling algorithms Lifetime Aware VM Allocation (LAVA). LAVA reduces resource stranding and increases the number of empty hosts, which are critical for large VM scheduling, cloud system updates, and reducing dynamic energy consumption. Our approach runs in production within Google's hyperscale cloud data centers, where it improves efficiency by decreasing stranded compute and memory resources by ~3% and ~2% respectively. It increases empty hosts by 2.3-9.2 pp in production, reducing dynamic energy consumption, and increasing availability for large VMs and cloud system updates. We also show a reduction in VM migrations for host defragmentation and maintenance. In addition to our fleet-wide production deployment, we perform simulation studies to characterize the design space and show that our algorithm significantly outperforms the prior state of the art lifetime-based scheduling approach.

cs.DC↗

arXiv2024

CardBench: A Benchmark for Learned Cardinality Estimation in Relational Databases

Cardinality estimation is crucial for enabling high query performance in relational databases. Recently learned cardinality estimation models have been proposed to improve accuracy but there is no systematic benchmark or datasets which allows researchers to evaluate the progress made by new learned approaches and even systematically develop new learned approaches. In this paper, we are releasing a benchmark, containing thousands of queries over 20 distinct real-world databases for learned cardinality estimation. In contrast to other initial benchmarks, our benchmark is much more diverse and can be used for training and testing learned models systematically. Using this benchmark, we explored whether learned cardinality estimation can be transferred to an unseen dataset in a zero-shot manner. We trained GNN-based and transformer-based models to study the problem in three setups: 1-) instance-based, 2-) zero-shot, and 3-) fine-tuned. Our results show that while we get promising results for zero-shot cardinality estimation on simple single table queries; as soon as we add joins, the accuracy drops. However, we show that with fine-tuning, we can still utilize pre-trained models for cardinality estimation, significantly reducing training overheads compared to instance specific models. We are open sourcing our scripts to collect statistics, generate queries and training datasets to foster more extensive research, also from the ML community on the important problem of cardinality estimation and in particular improve on recent directions such as pre-trained cardinality estimation.

cs.DB↗