This paper introduces LLM-based automatic modeling and optimization, significantly advancing intelligent decision-making in complex operations research problems.

Yang Wang, Kai Li

EgoMem enables personalized dialogues with full-duplex models, achieving over 95% accuracy in user recognition.

Yiqun Yao, Naitong Yu, Xiang Li et al.

This survey explores reasoning topologies in time series with large language models, introducing three structures.

Ching Chang, Yidan Shi, Defu Cao et al.

Maestro employs multi-agent self-evolution with Critic and Judge modules, leveraging pairwise preferences to enhance text-to-image generation quality autonomously.

Xingchen Wan, Han Zhou, Ruoxi Sun et al.

Statistical techniques enhance reliability, control behavior, quantify uncertainty, and guide experiments in generative AI, ensuring safer and more trustworthy outputs.

Edgar Dobriban

Paper2Agent transforms research papers into AI agents, enhancing interactivity and reliability of scientific outputs.

Jiacheng Miao, Joe R. Davis, Yaohui Zhang et al.

RAFFLES uses iterative reasoning to detect faults in LLM systems, achieving 50% accuracy improvement on Who&When dataset.

Chenyang Zhu, Spencer Hong, Jingyu Wu et al.

OmniDPO reduces omni-modal hallucination using a preference optimization framework, enhancing multimodal reasoning.

Junzhe Chen, Tianshu Zhang, Shiyu Huang et al.

PosterForest employs hierarchical multi-agent collaboration for scientific poster generation, outperforming prior methods without additional training.

Jiho Choi, Seojeong Park, Seongjong Song et al.

Proposes Entropy Area Score (EAS), a sequence-level entropy integral for quantifying LLM uncertainty without external models, improving data selection.

Yongfu Zhu, Lin Sun, Guangxiang Zhao et al.

Instructional Agents reduce faculty workload by automating course material creation with multi-agent design.

Huaiyuan Yao, Wanpeng Xu, Justin Turnau et al.

Proposes the Experience-driven Lifelong Learning (ELL) framework integrating knowledge abstraction, skill transfer, and internalization, evaluated on the StuLife benchmark for autonomous self-evolving agents.

Yuxuan Cai, Yipeng Hao, Jie Zhou et al.

CMASE integrates generative agents with ethnography, enabling real-time human-in-the-loop social simulation and intervention.

Hanzhong Zhang, Muhua Huang, Jindong Wang

PowerChain automates DG analysis with verifiable DAG agents, reaching up to ~144% improvement.

Emmanuel O. Badmus, Peng Sang, Dimitrios Stamoulis et al.

HiFo-Prompt integrates Foresight and Hindsight mechanisms, significantly enhancing LLM-driven heuristic design with superior quality, faster convergence, and higher query efficiency.

Chentong Chen, Mengyuan Zhong, Ye Fan et al.

STEP method enhances semantic fusion and precision in conversational recommendation via curriculum learning.

Zhenye Yang, Jinpeng Chen, Huan Li et al.

OpenCUA leverages cross-OS human demonstration data and reflective long Chain-of-Thought reasoning to achieve 45% success rate, setting new open-source SOTA.

Xinyuan Wang, Bowen Wang, Dunjie Lu et al.

SEAgent employs autonomous exploration and experience-based reinforcement learning, achieving a 23.2% success rate increase (from 11.3% to 34.5%) across five novel software environments.

Zeyi Sun, Ziyu Liu, Yuhang Zang et al.

Developed ACES framework to evaluate AI shopping agents' biases, market share dependence, and stability across models, revealing volatile and model-dependent behaviors.

Amine Allouah, Omar Besbes, Josué D Figueroa et al.

QCBench evaluates 24 large language models on quantitative chemistry, revealing the gap between language fluency and scientific computation accuracy.

Jiaqing Xie, Weida Wang, Ben Gao et al.