English
Related papers

Related papers: From Multi-Agent to Single-Agent: When Is Skill Di…

200 papers

Large reasoning models such as DeepSeek-R1 and their distilled variants achieve strong performance on complex reasoning tasks. Yet, distilling these models often demands large-scale data for supervised fine-tuning (SFT), motivating the…

Computation and Language · Computer Science 2026-01-16 Lechen Zhang , Yunxiang Zhang , Wei Hu , Lu Wang

Multi-task learning (MTL) is to learn one single model that performs multiple tasks for achieving good performance on all tasks and lower cost on computation. Learning such a model requires to jointly optimize losses of a set of tasks with…

Computer Vision and Pattern Recognition · Computer Science 2020-09-25 Wei-Hong Li , Hakan Bilen

Current long chain-of-thought (long-CoT) models excel at mathematical reasoning but rely on slow and error-prone natural language traces. Tool-augmented agents address arithmetic via code execution, but often falter on complex logical…

Computation and Language · Computer Science 2025-09-03 Weihua Du , Pranjal Aggarwal , Sean Welleck , Yiming Yang

Multi-agent systems are trained to maximize shared cost objectives, which typically reflect system-level efficiency. However, in the resource-constrained environments of mobility and transportation systems, efficiency may be achieved at the…

Multiagent Systems · Computer Science 2024-10-30 Jasmine Jerry Aloor , Siddharth Nayak , Sydney Dolan , Hamsa Balakrishnan

Deep Reinforcement Learning (RL) algorithms can solve complex sequential decision tasks successfully. However, they have a major drawback of having poor sample efficiency which can often be tackled by knowledge reuse. In Multi-Agent…

Multiagent Systems · Computer Science 2019-05-30 Ercüment İlhan , Jeremy Gow , Diego Perez-Liebana

Language agents increasingly improve by reusing \emph{skills} -- structured procedural artifacts distilled from past experience. In particular, \emph{domain-level} and \emph{model-generated} skills are especially promising. They offer fast…

Multi-agent systems (MAS) are critical for automating complex tasks, yet their practical deployment is severely hampered by the challenge of failure attribution. Current diagnostic tools, which rely on statistical correlations, are…

Artificial Intelligence · Computer Science 2025-09-11 Guoqing Ma , Jia Zhu , Hanghui Guo , Weijie Shi , Jiawei Shen , Jingjiang Liu , Yidan Liang

Current scaling laws for visual AI models focus predominantly on large-scale pretraining, leaving a critical gap in understanding how performance scales for data-constrained downstream tasks. To address this limitation, this paper…

Machine Learning · Computer Science 2025-04-21 Wenxuan Yang , Qingqu Wei , Chenxi Ma , Weimin Tan , Bo Yan

Finding controllers that perform well across multiple morphologies is an important milestone for large-scale robotics, in line with recent advances via foundation models in other areas of machine learning. However, the challenges of…

Robotics · Computer Science 2024-04-24 Alican Mertan , Nick Cheney

Agent Skills, structured packages of procedural knowledge loaded into an LLM agent at inference time, are widely reported to improve task pass rates by an average of 16.2~percentage points across diverse domains. Yet the same benchmarks…

Artificial Intelligence · Computer Science 2026-05-26 Samuel Jacob Chacko , James Hugglestone , Chashi Mahiul Islam , Xiuwen Liu

Agentic RL can benefit substantially from reusable experience, yet existing skill-based methods mainly extract trajectory-level guidance and often lack principled mechanisms for maintaining an evolving skill memory. We propose D2Skill, a…

Artificial Intelligence · Computer Science 2026-05-26 Songjun Tu , Chengdong Xu , Qichao Zhang , Yaocheng Zhang , Xiangyuan Lan , Linjing Li , Dong Li , Dongbin Zhao

Reinforcement learning (RL) has been widely used to train LLM agents for multi-turn interactive tasks, but its sample efficiency is severely limited by sparse rewards and long horizons. On-policy self-distillation (OPSD) alleviates this by…

Machine Learning · Computer Science 2026-04-14 Hao Wang , Guozhi Wang , Han Xiao , Yufeng Zhou , Yue Pan , Jichao Wang , Ke Xu , Yafei Wen , Xiaohu Ruan , Xiaoxin Chen , Honggang Qi

Recent advances in multimodal web agents often rely on increased inference-time computation, including rollout search, verifier passes, offline skill discovery, and specialist model stacks. This raises a central question: can a web agent…

Artificial Intelligence · Computer Science 2026-05-27 Yubo Li , Yidi Miao , Yuntian Shen , Yuxin Liu

Multi-agent systems (MAS) built on large language models promise improved problem-solving through collaboration, yet they often fail to consistently outperform strong single-agent baselines due to error propagation at inter-agent message…

Artificial Intelligence · Computer Science 2026-01-21 Bohan Lin , Kuo Yang , Zelin Tan , Yingchuan Lai , Chen Zhang , Guibin Zhang , Xinlei Yu , Miao Yu , Xu Wang , Yudong Zhang , Yang Wang

AI agents can extend their capabilities at inference time by loading reusable skills into context, yet equipping an agent with too many skills, particularly irrelevant ones, degrades performance. As community-driven skill repositories grow,…

Artificial Intelligence · Computer Science 2026-03-31 Fangzhou Li , Pagkratios Tagkopoulos , Ilias Tagkopoulos

Early-stage engineering design involves complex, iterative reasoning, yet existing large language model (LLM) workflows struggle to maintain task continuity and generate executable models. We evaluate whether a structured multi-agent system…

Artificial Intelligence · Computer Science 2025-11-04 Soheyl Massoudi , Mark Fuge

The remarkable growth in large language model (LLM) capabilities has spurred exploration into multi-agent systems, with debate frameworks emerging as a promising avenue for enhanced problem-solving. These multi-agent debate (MAD)…

Artificial Intelligence · Computer Science 2025-06-23 Yongjin Yang , Euiin Yi , Jongwoo Ko , Kimin Lee , Zhijing Jin , Se-Young Yun

Most deep reinforcement learning algorithms are data inefficient in complex and rich environments, limiting their applicability to many scenarios. One direction for improving data efficiency is multitask learning with shared neural network…

Code efficiency is a fundamental aspect of software quality, yet how to harness large language models (LLMs) to optimize programs remains challenging. Prior approaches have sought for one-shot rewriting, retrieved exemplars, or prompt-based…

Software Engineering · Computer Science 2026-03-31 Zimu Wang , Yuling Shi , Mengfan Li , Zijun Liu , Jie M. Zhang , Chengcheng Wan , Xiaodong Gu

While Multi-Agent Systems (MAS) are increasingly deployed for complex workflows, their emergent properties-particularly the accumulation of bias-remain poorly understood. Because real-world MAS are too complex to analyze entirely,…

Multiagent Systems · Computer Science 2026-04-14 Keyu Li , Jin Gao , Dequan Wang