Large language models (LLMs) are usually evaluated by final-output correctness or safety, yet an endpoint label does not reveal how a failure develops throughout the reasoning process. We therefore ask whether ordinary reasoning failures and adversarially induced failures can be characterized using the same internal co...
Zi-Rui Ding, Xin-Xin Fan, Hao Yuan et al.· 0 citations
The formation and motion of small polarons are ubiquitous in energy materials and influence photoinduced processes. Polaron transport is governed by thermally activated lattice dynamics and rare hopping events, requiring spatial and temporal scales only attainable with machine-learning molecular dynamics, which enables...
Daniela Mangano, Luca Leoni, Zhong-Fei Xu et al.· 0 citations
Agentic Reinforcement Learning (RL) trains LLM agents through multi-turn interactions with external tool environments. Its multi-turn nature exposes two system-level bottlenecks unaddressed by existing agentic RL frameworks. First, end-to-end training throughput is constrained by the slowest trajectories to complete, y...
Ming-Jun Zhang, Yu-Cheng Li, Meng-Hao Zhang et al.· 0 citations
Folding changes the linearized aeroelastic spectrum and can switch which mode becomes unstable first, with consequences for local postflutter interactions. This study formulates a three-component Z-fold wing by assigning every aerodynamic station to a structural component and a material coordinate. The same attachment...
Ge-Lin Chen, Haolin Yang, Chen Song et al.· 0 citations
Solving high-dimensional structural model updating problems requires an algorithm capable of navigating complex, non-convex landscapes with correlated parameters. Existing hybrid evolutionary algorithms typically rely on static architectures or fixed switching rules, resulting in disjointed search phases. To address th...
L. Li, Rong-Ye Shi, Wanhuan Zhou State Key Laboratory of Internet of Things fo City et al.· 0 citations
Coding-agent approval interfaces bind a human decision to a command or tool call, while developer tools execute the transitive workflow that invocation activates. Package installation can run lifecycle hooks and write files; an MCP call can exercise network authority. We call the resulting record-coverage failure appro...
Jin-Qian Zhang, Hao-Jun Xia, Shu-Jiang Wu et al.· 1 citation
Multi-step tool-calling LLM agents rely on host runtimes to preserve state across turns. When a runtime carries an external tool return into later model inputs, providers meter it again. An admitted malicious or compromised tool can thereby convert untrusted data into recurring victim-billed processing without victim c...
Jin-Qian Zhang, Hao-Jun Xia, Shu-Jiang Wu et al.· 0 citations
Generative Retrieval (GR) is promising for e-commerce search, yet existing methods struggle to maintain query-intent consistency throughout the training pipeline. First, semantic ID (SID) construction based on static product information limits the ability of SIDs to encode product-intent associations. Second, although...
Jiayi Tuo, He-Han Li, Dong-Jun Fu et al.· 0 citations
This paper presents a tutorial-style, collective-centric taxonomy for collective communication, which organizes recent advances into three layers: communication planning, which generates topology-aware collective schedules; communication execution and adaptation, which maps these schedules onto GPU runtimes and hardwar...
Xue-Bin Song, Menghao Zhang, Yue Liu et al.· IEEE Network· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
