English
Related papers

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

200 papers

Effective data selection is critical for efficient training of modern Large Language Models (LLMs). This paper introduces Influence Distillation, a novel, mathematically-justified framework for data selection that employs second-order…

Computation and Language · Computer Science 2025-05-27 Mahdi Nikdan , Vincent Cohen-Addad , Dan Alistarh , Vahab Mirrokni

Robust generalization in robotic manipulation is crucial for robots to adapt flexibly to diverse environments. Existing methods usually improve generalization by scaling data and networks, but model tasks independently and overlook…

Robotics · Computer Science 2026-01-19 Aoshen Huang , Jiaming Chen , Jiyu Cheng , Ran Song , Wei Pan , Wei Zhang

How should multi-agent systems be designed, and can that design knowledge be captured in a form that is inspectable, revisable, and transferable? We introduce ABSTRAL, a framework that treats MAS architecture as an evolving natural-language…

Artificial Intelligence · Computer Science 2026-03-25 Weijia Song , Jiashu Yue , Zhe Pang

Artificial Intelligence (AI) has increasingly influenced modern society, recently in particular through significant advancements in Large Language Models (LLMs). However, high computational and storage demands of LLMs still limit their…

Computation and Language · Computer Science 2025-04-23 Daniel Hendriks , Philipp Spitzer , Niklas Kühl , Gerhard Satzger

Self-supervised learning (SSL) has achieved remarkable success across various speech-processing tasks. To enhance its efficiency, previous works often leverage the use of compression techniques. A notable recent attempt is DPHuBERT, which…

Audio and Speech Processing · Electrical Eng. & Systems 2024-02-27 Luca Zampierin , Ghouthi Boukli Hacene , Bac Nguyen , Mirco Ravanelli

On-policy distillation (OPD) trains a student on its own trajectories under token-level teacher supervision, but existing methods are capped by a single-teacher capability ceiling: when the teacher errs, the student inherits the error. OPD…

Computation and Language · Computer Science 2026-05-05 Jianze Wang , Ying Liu , Jinlong Chen , Xuchun Hu , Qilong Zhang , Yu Cao , Jun Wang , Hua Yang , Yong Xie , Qianglong Chen

Learning generative models directly from corrupted observations is a long standing challenge across natural and scientific domains. We introduce Restoration Score Distillation (RSD), a unified framework for learning high fidelity, one step…

Machine Learning · Computer Science 2026-03-19 Yasi Zhang , Tianyu Chen , Zhendong Wang , Ying Nian Wu , Mingyuan Zhou , Oscar Leong

Despite the remarkable developments of recent large models in Embodied Artificial Intelligence (E-AI), their integration into robotics is hampered by their excessive parameter sizes and computational demands. Towards the Vision-and-Language…

Computer Vision and Pattern Recognition · Computer Science 2024-06-27 Liuyi Wang , Zongtao He , Mengjiao Shen , Jingwei Yang , Chengju Liu , Qijun Chen

Decentralized learning with private data is a central problem in machine learning. We propose a novel distillation-based decentralized learning technique that allows multiple agents with private non-iid data to learn from each other,…

Machine Learning · Computer Science 2022-11-30 Andrey Zhmoginov , Mark Sandler , Nolan Miller , Gus Kristiansen , Max Vladymyrov

A common dilemma in 3D object detection for autonomous driving is that high-quality, dense point clouds are only available during training, but not testing. We use knowledge distillation to bridge the gap between a model trained on…

Computer Vision and Pattern Recognition · Computer Science 2020-09-25 Yue Wang , Alireza Fathi , Jiajun Wu , Thomas Funkhouser , Justin Solomon

One of the long-standing challenges in Artificial Intelligence for learning goal-directed behavior is to build a single agent which can solve multiple tasks. Recent progress in multi-task learning for goal-directed sequential problems has…

Neural and Evolutionary Computing · Computer Science 2017-05-23 Sahil Sharma , Ashutosh Jha , Parikshit Hegde , Balaraman Ravindran

Recently, deep Multi-Agent Reinforcement Learning (MARL) has demonstrated its potential to tackle complex cooperative tasks, pushing the boundaries of AI in collaborative environments. However, the efficiency of these systems is often…

Machine Learning · Computer Science 2024-12-23 Yangkun Chen , Kai Yang , Jian Tao , Jiafei Lyu

Skills are a promising way to improve LLM agent capabilities without retraining, while keeping the added procedure reusable and controllable. However, high-quality skills are still largely written by hand. We introduce SkillGen, a…

Machine Learning · Computer Science 2026-05-13 Yuchen Ma , Yue Huang , Han Bao , Haomin Zhuang , Swadheen Shukla , Michel Galley , Xiangliang Zhang , Stefan Feuerriegel

Large language model multi-agent systems (LLM-MAS) offer a promising paradigm for harnessing collective intelligence to achieve more advanced forms of AI behaviour. While recent studies suggest that LLM-MAS can outperform LLM single-agent…

Artificial Intelligence · Computer Science 2025-10-07 Bohan Tang , Huidong Liang , Keyue Jiang , Xiaowen Dong

Skills provide an effective mechanism for improving LLM agents on complex tasks, yet in existing agent frameworks, their creation, refinement, and selection are typically governed by external teachers, hand-designed rules, or auxiliary…

Artificial Intelligence · Computer Science 2026-05-13 Min Yang , Jinghua Piao , Xu Xia , Xiaochong Lan , Jiaju Chen , Yongshun Gong , Yong Li

Existing methods for distillation do not efficiently utilize the training data. This work presents a novel approach to perform distillation using only a subset of the training data, making it more data-efficient. For this purpose, the…

Machine Learning · Computer Science 2021-04-26 Sourav Mishra , Suresh Sundaram

Population-population generalization is a challenging problem in multi-agent reinforcement learning (MARL), particularly when agents encounter unseen co-players. However, existing self-play-based methods are constrained by the limitation of…

Machine Learning · Computer Science 2025-05-19 Lang Feng , Jiahao Lin , Dong Xing , Li Zhang , De Ma , Gang Pan

In India, the majority of farmers are classified as small or marginal, making their livelihoods particularly vulnerable to economic losses due to market saturation and climate risks. Effective crop planning can significantly impact their…

Machine Learning · Computer Science 2025-02-25 Anubha Mahajan , Shreya Hegde , Ethan Shay , Daniel Wu , Aviva Prins

Owing to its rapid progress and broad application prospects, few-shot action recognition has attracted considerable interest. However, current methods are predominantly based on limited single-modal data, which does not fully exploit the…

Computer Vision and Pattern Recognition · Computer Science 2025-06-17 Weijia Feng , Yichen Zhu , Ruojia Zhang , Chenyang Wang , Fei Ma , Xiaobao Wang , Xiaobai Li

Large language model-based multi-agent systems have shown great abilities across various tasks due to the collaboration of expert agents, each focusing on a specific domain. However, the impact of clumsy or even malicious agents--those who…

Artificial Intelligence · Computer Science 2025-05-30 Jen-tse Huang , Jiaxu Zhou , Tailin Jin , Xuhui Zhou , Zixi Chen , Wenxuan Wang , Youliang Yuan , Michael R. Lyu , Maarten Sap