This page shows the most relevant public items for Agentic AI, ranked by trend activity and review signal. Use weekly for fast changes, monthly for more stable patterns, and all-time for evergreen picks.
Paper • Jan 8, 2026 • arxiv.org • Junhyuk Choi, Jeongyoun Kwon, Heeju Kim, Haeun Cho, Hayeong Jung, Sehee Min, Bugeun Kim
Multi-agent systems utilizing large language models often assign authoritative roles to improve performance, yet the impact of authority bias on agent interactions remains underexplored. We present...
Paper • Jan 24, 2026 • arxiv.org • Jingbo Wang, Sendong Zhao, Jiatong Liu, Haochun Wang, Wanting Li, Bing Qin, Ting Liu
While multi-agent systems (MAS) have demonstrated superior performance over single-agent approaches in complex reasoning tasks, they often suffer from significant computational inefficiencies. Exis...
Paper • Jan 9, 2026 • arxiv.org • Xiaochen Zhu, Caiqi Zhang, Yizhou Chi, Tom Stafford, Nigel Collier, Andreas Vlachos
Multi-agent debate (MAD) is widely used to improve large language model (LLM) performance through test-time scaling, yet recent work shows that vanilla MAD often underperforms simple majority vote ...
Paper • Jan 9, 2026 • arxiv.org • Zhenghao Li, Zhi Zheng, Wei Chen, Jielun Zhao, Yong Chen, Tong Xu, Enhong Chen
Recent years have witnessed the rapid development of Large Language Model-based Multi-Agent Systems (MAS), which excel at collaborative decision-making and complex problem-solving. Recently, resear...
Paper • Jan 9, 2026 • arxiv.org • Percy Jardine
Recently, multi-time-scale agent architectures have extended the ubiquitous single-loop paradigm by introducing temporal hierarchies with distinct cognitive layers. While yielding substantial perfo...
Paper • Jan 9, 2026 • arxiv.org • Ruizhe Zhang, Xinke Jiang, Zhibang Yang, Zhixin Zhang, Jiaran Gao, Yuzhen Xiao, Hongbin Lai, Xu Chu, Junfeng Zhao, Yasha Wang
Multi-agent systems based on large language models, particularly centralized architectures, have recently shown strong potential for complex and knowledge-intensive tasks. However, central agents o...
Paper • Jan 12, 2026 • arxiv.org • Daniel Liu, Krishna Upadhyay, Vinaik Chhetri, A. B. Siddique, Umar Farooq
The rapid emergence of multi-agent AI systems (MAS), including LangChain, CrewAI, and AutoGen, has shaped how large language model (LLM) applications are developed and orchestrated. However, little...
Paper • Jan 13, 2026 • arxiv.org • Haoran Su, Yandong Sun, Congjia Yu
Reward engineering, the manual specification of reward functions to induce desired agent behavior, remains a fundamental challenge in multi-agent reinforcement learning. This difficulty is amplifie...
Paper • Jan 15, 2026 • arxiv.org • Zhiyuan Hu, Yunhai Hu, Juncheng Liu, Shuyue Stella Li, Yucheng Wang, Zhen Xu, See-Kiong Ng, Anh Tuan Luu, Xinxing Xu, Bryan Hooi, Cynthia Breazeal, Hae Won Park
Multi-agent systems have evolved into practical LLM-driven collaborators for many applications, gaining robustness from diversity and cross-checking. However, multi-agent RL (MARL) training is reso...
Paper • Jan 14, 2026 • arxiv.org • Xinxing Ren, Quagmire Zang, Caelum Forder, Suman Deb, Ahsen Tahir, Roman J. Georgio, Peter Carroll, Zekun Guo
Most existing Large Language Model (LLM)-based Multi-Agent Systems (MAS) rely on predefined workflows, where human engineers enumerate task states in advance and specify routing rules and contextua...
Paper • Jan 15, 2026 • arxiv.org • Rui Sun, Jie Ding, Chenghua Gong, Tianjun Gu, Yihang Jiang, Juyuan Zhang, Liming Pan, Linyuan Lü
Optimizing communication topology in LLM-based multi-agent system is critical for enabling collective intelligence. Existing methods mainly rely on spatio-temporal interaction paradigms, where the ...
Paper • Jan 15, 2026 • arxiv.org • Xi Shi, Mengxin Zheng, Qian Lou
Multi-agent systems (MAS) enable complex reasoning by coordinating multiple agents, but often incur high inference latency due to multi-step execution and repeated model invocations, severely limit...
Paper • Jan 16, 2026 • arxiv.org • Zixu Wang, Bingbing Xu, Yige Yuan, Huawei Shen, Xueqi Cheng
Multi-Agent Systems (MAS) built on large language models typically solve complex tasks by coordinating multiple agents through workflows. Existing approaches generates workflows either at task leve...
Paper • Jan 17, 2026 • arxiv.org • Yichen Jiang, Peng Ye, Jiakang Yuan, Chongjun Tu, Lei Bai, Tao Chen
Effectively processing long contexts remains a fundamental yet unsolved challenge for large language models (LLMs). Existing single-LLM-based methods primarily reduce the context window or optimize...
Paper • Jan 24, 2026 • arxiv.org • Yin Cai, Zhouhong Gu, Juntao Zhang, Ping Chen
Humans face countless scenarios that require reasoning and judgment in daily life. However, existing large language model training methods primarily allow models to learn from existing textual cont...
Paper • Jan 20, 2026 • arxiv.org • Apoorva Adimulam, Rajesh Gupta, Sumit Kumar
Orchestrated multi-agent systems represent the next stage in the evolution of artificial intelligence, where autonomous agents collaborate through structured coordination and communication to achie...
Paper • Jan 20, 2026 • arxiv.org • Gopal Vijayaraghavan, Prasanth Jayachandran, Arun Murthy, Sunil Govindan, Vivek Subramanian
AI Agents can perform complex operations at great speed, but just like all the humans we have ever hired, their intelligence remains fallible. Miscommunications aren't noticed, systemic biases have...
Paper • Jan 20, 2026 • arxiv.org • Yiyang Wang, Yiqiao Jin, Alex Cabral, Josiah Hester
Multi-agent systems (MAS) have recently emerged as promising socio-collaborative companions for emotional and cognitive support. However, these systems frequently suffer from persona collapse--wher...
Paper • Jan 29, 2026 • arxiv.org • Zixuan Ke, Yifei Ming, Austin Xu, Ryan Chin, Xuan-Phi Nguyen, Prathyusha Jwalapuram, Jiayu Wang, Semih Yavuz, Caiming Xiong, Shafiq Joty
While multi-agent systems (MAS) promise elevated intelligence through coordination of agents, current approaches to automatic MAS design under-deliver. Such shortcomings stem from two key factors: ...
Paper • Jan 21, 2026 • arxiv.org • Christopher Scofield
Multi-agent systems (MAS) composed of large language models often exhibit improved problem-solving performance despite operating on identical information. In this work, we provide a formal explanat...
It ranks public content for Agentic AI using recent discussion, review, and engagement signals so you can triage faster. This guidance is specific to Agentic AI topic page on Attendemia and is written so it still makes sense without reading other sections on the page.
Use weekly for fast-moving updates, monthly for stable trend confirmation, and all-time for evergreen references. This guidance is specific to Agentic AI topic page on Attendemia and is written so it still makes sense without reading other sections on the page.
Use the linked entities section to jump to labs, companies, and experts connected to this topic and explore their timelines. This guidance is specific to Agentic AI topic page on Attendemia and is written so it still makes sense without reading other sections on the page.
Yes. Use the follow button on this page to subscribe and track new high-signal activity. This guidance is specific to Agentic AI topic page on Attendemia and is written so it still makes sense without reading other sections on the page.