Agent-based systems, coordination, cooperation
Bidipta Sarkar, Warren Xia, C. Karen Liu et al.
This work addresses the problem of effective communication in complex social settings for autonomous agents and humans, providing an incremental improvement in multi-agent reinforcement learning.
Beichen Huang, Ran Cheng, Kay Chen Tan
This addresses the challenge of automated and continual software development for developers and researchers, proposing a new paradigm rather than being incremental.
Salman Rahman, Liwei Jiang, James Shiffer et al.
This addresses critical safety risks in conversational AI by providing tools to mitigate sophisticated multi-turn attacks, though it is incremental in advancing multi-turn safety beyond single-turn approaches.
Licong Xu, Milind Sarkar, Anto I. Lonappan et al.
This addresses the problem of automating complex scientific discovery workflows for researchers, representing a novel application rather than an incremental improvement.
Rui Ye, Shuo Tang, Rui Ge et al.
This work addresses the problem of high inference costs and inadaptability in designing multi-agent systems for AI researchers and practitioners, offering a novel automated approach.
Shuofei Qiao, Zhisong Qiu, Baochang Ren et al.
This addresses inefficiencies in agent planning for AI systems, though it is incremental in improving existing methods.
Ali Essam Ghareeb, Benjamin Chang, Ludovico Mitchener et al.
This addresses the challenge of fully automating scientific discovery for researchers, establishing a new paradigm rather than being incremental.
Yao Zhang, Chenyang Lin, Shijie Tang et al.
This addresses the lack of full autonomy in agentic systems for scalable and adaptable task execution, representing a significant step rather than an incremental improvement.
Xiaowen Ma, Chenyang Lin, Yao Zhang et al.
This provides a scalable, data-driven framework for multi-agent systems, addressing limitations in adaptability and efficiency for complex tasks.
Qitong Sun, Jun Han, Tianlin Li et al.
This addresses GPU kernel optimization for AI systems, offering a more interpretable and efficient approach compared to prior LLM-based methods.
Jinxing Zhou, Yanghao Zhou, Mingfei Han et al.
This addresses the challenge of interpretable and efficient referring audio-visual segmentation for applications in video analysis and human-computer interaction, representing a novel approach rather than an incremental improvement.
Petar Steinberg, Juliusz Ziomek, Matej Jusup et al. · oxford
This provides a scalable solution for mean-field black-box optimization problems affecting multi-agent systems in domains like transportation and logistics.
Wenyi Wang, Hisham A. Alyahya, Dylan R. Ashley et al.
This addresses the problem of manual optimization in agentic systems for AI researchers and practitioners, offering a novel method for automatic feedback assignment.
Zhuoyun Du, Lujie Zheng, Renjun Hu et al.
This addresses the problem of scalable and effective medical training for healthcare professionals, representing a novel application of agent coevolution rather than an incremental improvement.
Shijun Guo, Haoran Xu, Yaming Yang et al.
This addresses the challenge of efficient and non-intrusive opinion guidance for social network governance, representing a new paradigm rather than an incremental improvement.
Sichao Wang, Ramesh Raskar, Mahesh Lambe et al.
This addresses the critical infrastructure problem for enterprises and developers deploying large-scale autonomous AI agent ecosystems, representing a foundational rather than incremental contribution.
Yihao Zhang, Zeming Wei, Xiaokun Luan et al.
This addresses critical security risks for users of interconnected multi-agent systems, exposing vulnerabilities that could lead to autonomous attacks without attacker intervention.
Shengguang Wu, Xiaohan Wang, Yuhui Zhang et al.
This addresses the problem of suboptimal tool utilization in visual programming for spatial reasoning tasks, representing a novel paradigm rather than an incremental improvement.
Shuo Tang, Rui Ye, Chenxin Xu et al.
This work addresses the challenge of decentralized and lifelong adaptive collaboration for multi-agent systems, which is incremental as it builds on existing multi-agent learning methods.
Aishwarya Sarkar, Sayan Ghosh, Nathan Tallent et al.
This work addresses the problem of inefficient data prefetching in distributed GNN training for researchers and practitioners, offering substantial performance gains.