English
Related papers

Related papers: Sample-Efficient Online Learning in LM Agents via …

200 papers

Large transformer models powered by diverse data and model scale have dominated natural language modeling and computer vision and pushed the frontier of multiple AI areas. In reinforcement learning (RL), despite many efforts into…

Machine Learning · Computer Science 2023-05-29 Hao Liu , Pieter Abbeel

A long-term goal of language agents is to learn and improve through their own experience, ultimately outperforming humans in complex, real-world tasks. However, training agents from experience data with reinforcement learning remains…

Sparse rewards pose a significant challenge to achieving high sample efficiency in goal-conditioned reinforcement learning (RL). Specifically, in sequential manipulation tasks, the agent receives failure rewards until it successfully…

Robotics · Computer Science 2024-06-24 Yuming Huang , Bin Ren , Ziming Xu , Lianghong Wu

Large language model (LLM) agents have evolved to intelligently process information, make decisions, and interact with users or tools. A key capability is the integration of long-term memory capabilities, enabling these agents to draw upon…

Computation and Language · Computer Science 2025-08-04 Rana Salama , Jason Cai , Michelle Yuan , Anna Currey , Monica Sunkara , Yi Zhang , Yassine Benajiba

Large Language Models (LLMs) have demonstrated impressive capabilities for text rewriting. Nonetheless, the large sizes of these models make them impractical for on-device inference, which would otherwise allow for enhanced privacy and…

Computation and Language · Computer Science 2023-08-24 Yun Zhu , Yinxiao Liu , Felix Stahlberg , Shankar Kumar , Yu-hui Chen , Liangchen Luo , Lei Shu , Renjie Liu , Jindong Chen , Lei Meng

Large language model (LLM) agents perform well in sequential decision-making tasks, but improving them on unfamiliar domains often requires costly online interactions or fine-tuning on large expert datasets. These strategies are impractical…

Large language models (LLMs) have been increasingly employed for (interactive) decision-making, via the development of LLM-based autonomous agents. Despite their emerging successes, the performance of LLM agents in decision-making has not…

Machine Learning · Computer Science 2025-10-16 Chanwoo Park , Xiangyu Liu , Asuman Ozdaglar , Kaiqing Zhang

The evolution of Large Language Model (LLM) agents towards System~2 reasoning, characterized by deliberative, high-precision problem-solving, requires maintaining rigorous logical integrity over extended horizons. However, prevalent memory…

Artificial Intelligence · Computer Science 2026-05-15 Kaixiang Wang , Yidan Lin , Jiong Lou , Zhaojiacheng Zhou , Bunyod Suvonov , Jie Li

Large language models (LLMs) demonstrate strong reasoning abilities across mathematical, strategic, and linguistic tasks, yet little is known about how well they reason in dynamic, real-time, multi-agent scenarios, such as collaborative…

Multiagent Systems · Computer Science 2026-01-01 Shaurya Mallampati , Rashed Shelim , Walid Saad , Naren Ramakrishnan

Multi-agent systems provide a powerful way to extend large language models (LLMs) by decomposing a complex task into specialized subtasks handled by different agents. However, their performance is often hindered by error propagation,…

Machine Learning · Computer Science 2026-05-14 Zheng Wang , Yuang Liu , Yangkai Ding

Large-scale generative language and vision-language models (LLMs and VLMs) excel in few-shot learning but require high-quality demonstrations. We propose In-Context Abstraction Learning (ICAL), enabling VLM agents to transform suboptimal…

Computer Vision and Pattern Recognition · Computer Science 2025-09-19 Gabriel Sarch , Lawrence Jang , Michael J. Tarr , William W. Cohen , Kenneth Marino , Katerina Fragkiadaki

Language creates a compact representation of the world and allows the description of unlimited situations and objectives through compositionality. While these characterizations may foster instructing, conditioning or structuring interactive…

Machine Learning · Computer Science 2020-12-11 Geoffrey Cideron , Mathieu Seurin , Florian Strub , Olivier Pietquin

Reinforcement learning has become the central approach for language models (LMs) to learn from environmental reward or feedback. In practice, the environmental feedback is usually sparse and delayed. Learning from such signals is…

Machine Learning · Computer Science 2026-02-17 Taiwei Shi , Sihao Chen , Bowen Jiang , Linxin Song , Longqi Yang , Jieyu Zhao

Large Language Models (LLMs) offer a promising basis for creating agents that can tackle complex tasks through iterative environmental interaction. Existing methods either require these agents to mimic expert-provided trajectories or rely…

Computation and Language · Computer Science 2024-12-02 Dihong Gong , Pu Lu , Zelong Wang , Meng Zhou , Xiuqiang He

End-to-end Spoken Language Models (SLMs) hold great potential for paralinguistic perception, and numerous studies have aimed to enhance their capabilities, particularly for empathetic dialogue. However, current approaches largely depend on…

Computation and Language · Computer Science 2026-01-27 Yuhang Jia , Pei Liu , Haoqin Sun , Jiaming Zhou , Xuxin Cheng , Cao Liu , Ke Zeng , Xunliang Cai , Yong Qin

Prompt-based offline methods are commonly used to optimize large language model (LLM) responses, but evaluating these responses is computationally intensive and often fails to accommodate diverse response styles. This study introduces a…

Human-Computer Interaction · Computer Science 2025-11-12 Xiangxiang Dai , Yuejin Xie , Maoli Liu , Xuchuang Wang , Zhuohua Li , Huanyu Wang , John C. S. Lui

Large language models have been widely deployed in various applications, encompassing both interactive online tasks and batched offline tasks. Given the burstiness and latency sensitivity of online tasks, over-provisioning resources is…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-04-08 Zhibin Wang , Shipeng Li , Xue Li , Yuhang Zhou , Zhonghui Zhang , Zibo Wang , Rong Gu , Chen Tian , Kun Yang , Sheng Zhong

LLM-based Automatic Heuristic Design (AHD) within Evolutionary Computation (EC) frameworks has shown promising results. However, its effectiveness is hindered by the use of static operators and the lack of knowledge accumulation mechanisms.…

Artificial Intelligence · Computer Science 2026-02-10 Chentong Chen , Mengyuan Zhong , Ye Fan , Jialong Shi , Jianyong Sun

Large Language Model (LLM) agents are increasingly improved through interaction, yet most self-evolution methods adapt either the policy or the learning environment in isolation. We identify this structural gap as \emph{Agent-Environment…

Computation and Language · Computer Science 2026-05-26 Yihao Hu , Zhihao Wen , Xiujin Liu , Pan Wang , Xin Zhang , Wei Wu

Large language model (LLM) agents have recently demonstrated impressive capabilities in various domains like open-ended conversation and multi-step decision-making. However, it remains challenging for these agents to solve strategic…

Artificial Intelligence · Computer Science 2025-06-19 Zelai Xu , Wanjun Gu , Chao Yu , Yi Wu , Yu Wang