Reflective text optimization makes agentic systems better, but the optimization loop is itself a resource-hungry workload whose sequential structure leaves parallel evaluation capacity idle. We extend the open-source GEPA optimizer to propose and evaluate a batch of candidates on each optimization step instead of one c...
Jialin Zhang, Lakshya A Agrawal, Shangyin Tan et al.· 0 citations
Large Language Models (LLMs) have made remarkable progress on solving competition-level mathematics, yet their ability to verify natural-language mathematical proofs remains relatively underexplored. This gap is especially pronounced for Olympiad-level proofs, which require meticulous assessment of each claim in a long...
Azim Ospanov, Zijin Feng, Ding Ding et al.· 0 citations
Fake news undermines public trust and the integrity of online information ecosystems. Temporally disordered fake news is especially elusive because it rearranges factual events into a false chronology. Individual events may remain factually valid even when their temporal relations are misrepresented. When similar event...
Chi Wang, Min Gao, Yifei Zhang et al.· 0 citations
Self-disclosures on the Web support diverse psychological analyses, from recognizing expressed experiences to identifying symptom-relevant information. We study a shared, question-conditioned decision interface for this heterogeneous problem in content analysis. We organize PsyJudgeBench, comprising 13 annotated datase...
Fang-Yuan Liu, Si-Rui Zhao, Xiao-Hao Wang et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Deformable image registration relies on accurate anatomical correspondences. However, explicitly coupling local matching reliability with spatial context selection and deformation update strength remains insufficiently explored in learning-based registration. This challenge is particularly pronounced in homogeneous, we...
Chenyu Guo, Wenjie Dai, Yiqian Chang et al.· 0 citations
Self-improving AI systems can revise the designs that govern their own behavior. Yet existing approaches center improvement on selected parent agents and their evolutionary experience, leaving the broader population largely underused. We identify a substantial gap between population coverage (i.e., the tasks solved by...
Shuo Yan, Ningning Hou, Haoyu He et al.· 0 citations
DiscernMem is proposed, a training-free framework that improves both memory quality and memory use and leads on code generation and symbolic planning across all three systems, including a PDDL score of 37.71 versus 28.48 on CAMEL.
Yi Hao, Yuxuan Cai, Wen-Kai Ji et al.· 0 citations
It is demonstrated that the share containing AI-generated text has increased precipitously, but unevenly, and suggested that AI is a prominent, but varied, contributor to public information and internet-based communication.
A. Visokay, Soumyakanti Pan, Molly Griston et al.· 0 citations
Sparse event responses produce uneven keypoint errors whose effects on spacecraft pose depend on correspondence geometry and the reliability of successive observations. We present a reliability-aware framework connecting polarity--time localization, geometric recovery, event--CAD refinement, and trajectory optimization...
Large language model (LLM) serving systems dynamically batch user requests for GPU execution, so the same request may be processed alongside different requests across runs. If the GPU kernels lack batch invariance (BI), this changing batch context can alter the numerical output for an unchanged input, undermining repro...
Decision models offer fast choices over sup- plied alternatives, while general-purpose large language models interpret open-ended tasks through flexible generation and reasoning at the cost of sequential decoding. Many work- loads expect a generative backend to determine what can be done and therefore provide no well-d...
Cheng-Xuan Pei, Zi-Yao Wang, Teng Mei et al.· 0 citations
Coding agents are beginning to develop the production-grade AI infrastructure that trains and serves large models, yet existing benchmarks cover only single kernels or single-GPU tasks, and grade with tests and prompts that misjudge both correct and incorrect patches. We introduce InfraDev, a benchmark of 36 tasks buil...
Yang-Shen Deng, Jia-Qi Ruan, Ye-Qi Huang et al.· 0 citations
