PHMForge is an evaluation environment that tests large language model agents on industrial prognostics tasks using the Model Context Protocol (MCP). It provides 99 SME-authored scenarios across eight asset classes, 39 MCP-native tools wrapping published PHM algorithms, and deterministic evaluators that separate protocol fluency, reasoning, instrumentation, and tool use. The benchmark shows that the best agent configuration achieves 80.8% pass@1, with orchestration and tool sequencing errors as the main failure modes, and demonstrates the limitations of static retrieval for prognostic computation.
By Yusheng Li, Tianjun Feng, Yunfeng Chen, Chun-Yi Tsai, Yihan Sun, Ayan Das, Kaoutar El Maghraoui, Shuxin Lin, Dhaval Patel
arXiv:2605.02346v2 Announce Type: replace-cross
Abstract: Operational technology (OT) devices run safety-critical physical processes, yet their security testing remains manual and expert-intensive. A...
By Adel ElZemity, Budi Arief, Shujun Li, George Oikonomou, James Pope
arXiv:2609.10494v1 Announce Type: new
Abstract: Enterprises deploy systems, not checkpoints. Usable capability depends jointly on weights, serving route, precision, output contract, and harness, yet...
By Blake Stenstrom, Charangan Vasantharajan, Brian Sathianathan
arXiv:2608. 11241v1 Announce Type: new Abstract: Deploying LLM agents into industrial recommender operations exposes a three-way tension we frame as the autonomy-determinism-efficiency trilemma: general autonomy (interpreting operator intent, generating glue code zero-shot), industrial determinism (schema-conforming feature extraction, non-crashing A/B, zero compliance-path hallucination), and end-to-end efficiency.
By Dongyang Ao, Kaixiang Fang, Shijie Xu
arXiv:2607. 17269v1 Announce Type: new Abstract: Large language models encode world models implicitly in neural weights, which exposes four structural risks in high-precision domains such as medicine and finance: hallucination, frozen knowledge, poor explainability, and poor modifiability.
By Zhanbo Li, Shifeng Wu, Xiangjin Meng, Wenjie Cai
Enterprises deploy systems, not checkpoints. Usable capability depends jointly on weights, serving route, precision, output contract, and harness, yet all 18 audited benchmarks score advertised model...
arXiv:2606. 13706v1 Announce Type: cross Abstract: We present HierSVA, an integrated suite that combines a pipeline, dataset, and benchmark for LLM-driven hierarchical hardware formal verification.
By Maohua Nie, Jiang Zhu, Jingqun Zhang, Zhichen Zeng, Jiayi Wang, Sibo Zhang, Jialin Wang, C. -J. Richard Shi
FDE-Bench is a benchmark that tests large language model agents on 136 deployment‑configuration tasks involving Docker, Compose, and Kubernetes, in both greenfield and diagnose‑and‑repair scenarios. Agents submit declarative artifacts that are rebuilt and redeployed in a clean environment, and four binary check layers evaluate build, readiness, behavior, and specification conformance without an LLM judge. The benchmark includes a release gate, detailed check annotations, adversarial strategies, and reports that state‑of‑the‑art models resolve 52.9–75.0 % of tasks, while zero‑intelligence baselines solve none.
By Weihang Ding, Junfei Zhan, Yueting Li, Qirong Guo
arXiv:2608. 05773v1 Announce Type: new Abstract: A geometry-conditioned, neuro-symbolic closed-loop architecture is proposed for laser powder bed fusion, in which a standards-aligned ontology operates inside the control loop and couples symbolic reasoning with statistical learning to set the targets of a constraint-aware predictive controller.
By Gisuk Hong, Jaebong Cho, Hyunbo Cho
arXiv:2607. 16388v1 Announce Type: cross Abstract: Large-scale AI datacenter platforms comprise thousands of heterogeneous hardware components whose validation requires comprehensive fault injection test plans.
By Mohammed-Khalil Ghali, Saurabh Kulkarni, Prathamesh Kulkarni, Rohan Kulkarni, Sangwon Yoon, Daehan Won
arXiv:2607. 22639v1 Announce Type: new Abstract: Parametric retrieval enables LLMs to retrieve tools implicitly by assigning each API a unique virtual token and training the model to generate it via constrained beam search.
By Sai Shruthi Sistla, Ashutosh Hathidara, Christopher Toukmaji, Mayank Shrivastava, Karthikeyan Asokkumar
arXiv:2608.21375v1 Announce Type: new
Abstract: Heterogeneous agentic retrieval-augmented generation (RAG) systems increasingly orchestrate external APIs, internal databases, vector stores, and graph...
By Yong-eun Cho