Agentic Architect is a new framework that uses large language models to automatically evolve and optimize CPU microarchitectural designs. Starting from a seed design, the LLM proposes code changes, which are compiled, simulated, and evaluated against performance, area, and power constraints, with results feeding back into subsequent iterations. The framework was tested on prefetching, cache replacement, and branch prediction, achieving notable speedups and area reductions compared to state‑of‑the‑art designs.
By Vasilis Kypriotis, Alexander Blasberg, Alexandros Moiras, Dimitrios Skarlatos
The paper introduces A-LEMS, a framework that measures AI energy consumption at the goal level rather than per model invocation, defining Energy per Successful Goal (EpG) as total workflow energy divided by successfully completed goals. It also proposes the Orchestration Overhead Index (OOI) to quantify the extra energy cost of agentic systems compared to linear execution, revealing significant overheads across various hardware platforms and task families. The study demonstrates that traditional per-inference metrics underestimate the true energy cost of completing user goals in agentic AI workflows.
By Deepak Panigrahy, Aakash Tyagi, Stephen Abkin, David Kebo Houngninou, Rabi Mahapatra
The paper examines how pooled leaderboards in microservice root cause analysis (RCA) benchmarks obscure key details about which subsystems the rankings apply to and how scores are generated. By auditing three public benchmark families (OpenRCA, RCAEval, and PetShop) and running 16 released methods on 11 subsystems, the authors show that many reported leads do not hold across all subsystems and that differences in input tables and implementation details can reverse method rankings. They find that none of the 23 RCA papers examined provide the per‑case outputs needed to verify these claims, and they recommend that future pooled comparisons disclose subsystem coverage, score spread, input tables, handling of failures, and denominators, along with per‑case outputs.
By Lining Hu, Ting Liu, Yuzhuo Fu
LaCache introduces a redesigned semantic caching mechanism for large language model (LLM) serving that defends against cache‑collision attacks. By shifting integrity checks from queries to the first $k$ speculatively decoded tokens of the LLM response, LaCache can detect adversarial cache pollution with provable high probability. Experiments across multiple LLMs and benchmarks show that LaCache reduces attack hit rates to near zero while retaining over 90% of benign cache utility.
By Jiacheng Liang, Yuhui Wang, Tanqiu Jiang, Ting Wang
CockpitHAT is a hierarchical attribution framework for embodied multi‑agent systems that replaces positional windows with dependency‑distance thresholds derived from interaction DAGs, incorporates multi‑channel evidence through an embodied adapter, and applies a safety‑uplift to high‑risk failures during confidence‑weighted analyst consensus. The authors also release CockpitBench, a benchmark of 212 annotated failure traces labeled with ISO 26262 ASIL severity. On both the public Who&When benchmark and CockpitBench, CockpitHAT outperforms the text‑only state‑of‑the‑art ECHO, achieving higher agent‑level and step‑exact accuracies across multiple splits.
By Wei Wang, Shuanghe Liu, Zhu Zhuo, Jiaqi Zhong, Xiaozhao Zhao, Xiaojie Zuo, Jie Su
Bench2Robust is a framework that augments existing tool‑using LLM benchmarks with scenario‑controlled solvability, adding episodes that require retrying the original path, switching to a fallback tool, or recognizing that no viable path remains. It separates recovery‑policy quality from randomness in failure persistence, and across 7 models and 10 task slices, 69 of 70 model‑subset pairs degrade under tool failures by up to 46.7 percentage points. The authors introduce Bayesian Tool Memory (BTM) for structured runtime recovery context and use reinforcement learning (RL) for learned recovery behavior, achieving up to a 20.7‑point improvement over the base model without sacrificing clean performance.
By Chaoran Chen, Vy Nguyen, Ziji Zhang, Abhinav Gullapalli, Ziyi Wang, Yuxuan Lu, Dakuo Wang, Jing Huang, Zhou Yu, Jin Lai
LoopArena is a benchmark that evaluates how effectively a model (the Controller) can guide a separate coding agent (the Worker) through long-running tasks by monitoring progress, assigning work, and deciding when to stop. It consists of three settings: Type I with 160 low‑cost control questions, Type II with 80 task slices, and Type III with 80 full tasks. In full tasks, the best observed strict success rate is 36.25%, and Controllers can reduce inference cost by an average of 60.6% while maintaining a strong correlation in performance ranking.
By Yi Wang, Haopeng Zhang, Chengxiang Huang, Rui Dai, Kaikui Liu, Piotr Koniusz, Xiangxiang Chu
The paper introduces three interpretable metrics—Explanation Stability Index (ESI), Causal Faithfulness Score (CFS), and Perturbation Stability Score (PSS)—to assess the faithfulness of large language models (LLMs) in clinical decision support. Evaluating six LLMs on 150 MedQA-USMLE questions, the study finds that only 23.3% of cited clinical concepts are causally necessary, and that correct answers often have lower CFS than incorrect ones, with answer consistency negatively predicting faithfulness. These findings suggest that accuracy, consistency, and consensus are incomplete safety signals for clinical decision-making support.
By Bharath Kumar Bolla, Chaitali Deb Purkayastha, Vishnu Surya Reddy Nandi
The paper introduces “BMA-GAI”, an algorithm for test-time scaling that jointly selects which candidates to inspect and which verification attributes to evaluate under a shared computational budget. It frames the problem as multi-attribute good-arm identification, where each candidate is an arm evaluated across several costly attributes, aiming to certify as many candidates as possible whose mean scores exceed thresholds on all attributes. The authors provide asymptotic coverage guarantees, an information-theoretic converse, and demonstrate that “BMA-GAI” allocates verification resources more efficiently and certifies more high-quality candidates than competing methods on synthetic benchmarks and an LLM answer-verification task.
By Bo Xue, Ji Cheng, Shen-Huan Lyu, Yuanyu Wan, Shuang Qiu
SkillScriptBench is a 350‑task benchmark that evaluates how well large language models can self‑evolve executable agent skill packages by distinguishing between documentation repair, script repair, and preservation. The benchmark draws from 100 real GitHub skill packages, creating 150 repair tasks with injected script faults and a controlled track of 200 tasks that test clean, documentation‑faulty, script‑faulty, and combined‑faulty states. Experiments show that AST‑Guided Skill Revision—using abstract syntax trees to target relevant code locations—improves repair success by up to 27.7% and yields more consistent outcomes across repeated runs.
whyItMatters":"The benchmark provides a systematic way to measure and improve the reliability of automated skill package maintenance, which is essential for deploying robust LLM agents in real‑world applications."
By Yuxuan Liu, Haoran Li, Yuhao Zhang, Jiahe Guo, Hongyu Luo, Wenbin Hu, Huihao Jing, Kawai Chung, Junle Chen, Changxuan Fan, Qing Zong, Lingyun Xie, Yangqiu Song
arXiv:2610.17880v1 Announce Type: cross
Abstract: Persona vectors are linear directions in the residual-stream activations of LLMs that encode behavioral traits and enable fine-grained control over m...
By Juann Kim, Minku Kang
arXiv:2610.17113v1 Announce Type: cross
Abstract: Information extraction models often perform well on the datasets they are trained on, but transferring to new domains and annotation guidelines remai...
By Yang Wang, Hanlin Xiao, Yanan Ma, Chenghao Xiao, Chenghua Lin
arXiv:2610.14737v1 Announce Type: cross
Abstract: Training language agents on long-horizon interactive tasks is challenging because sparse terminal rewards provide weak credit signals for intermediat...
By Ruolin Chen, Yang Li, Jihang Wang, Zhuoya Zhao, Yuchen Liu, Jiaming Xu, Qian Zhang
arXiv:2610.15032v1 Announce Type: cross
Abstract: Industrial anomaly detection benchmarks have advanced rapidly, yet they remain largely static and therefore underrepresent deployment settings in whi...
By {\L}ukasz Marcjan, Dorota Wilk-Ko{\l}odziejczyk, Roberto Corizzo
arXiv:2610.15092v1 Announce Type: cross
Abstract: Quantization plays a crucial role in efficiently deploying deep learning models on resource-constrained devices. Post-training quantization does not...
By Reem Abdel-Salam, Ahmed H. Abdel-Gawad, Amr G. Wassal
arXiv:2610.19571v1 Announce Type: new
Abstract: Real-world engineering drawings are often large-format and information-dense. Answering practical engineering questions therefore requires both fine-gr...
By Ke Li, Tianyi Wang, Enning You, Chaoqun Wan, Zhen Huang, Shuxian Liang, Xian-Sheng Hua
arXiv:2610.16782v1 Announce Type: new
Abstract: Industrial manipulation in flexible manufacturing, e.g., high-mix, low-volume (HMLV) electronics assembly, requires robot policies to adapt to changing...
By Ming Shin Cindy Sung, Duan Leijiahao, Haoxiang Wang, Boning Tan, Liangna Fu, Chao Tan, Yafu Li, Yulong Chen, Chaoqun Wan, Zhen Huang, Shuxian Liang, Xian-Sheng Hua
arXiv:2610.17643v1 Announce Type: new
Abstract: An enterprise agent that answers under a written policy must choose an action before it says anything: answer, ask for a missing fact, ask for confirma...
By Hyojung Han, Ryangkyung Kang, Youngeun Kim, Seung-Hun Jeon
arXiv:2610.17016v1 Announce Type: cross
Abstract: Evaluating model uncertainty on real-world data is challenging because each instance provides only a single observed label, leaving true conditional...
By Yuyang Dai, Yuting Tang, Futoshi Futami, Takashi Ishida
arXiv:2610.18677v1 Announce Type: cross
Abstract: Online decision-making faces a tension between efficient inference and long-horizon reasoning. Value-based methods rely on short-horizon bootstrappin...
By Haldun Balim, Yilun Du, Na Li