English
Related papers

Related papers: SKILL0: In-Context Agentic Reinforcement Learning …

200 papers

Language-conditioned robotic skills make it possible to apply the high-level reasoning of Large Language Models (LLMs) to low-level robotic control. A remaining challenge is to acquire a diverse set of fundamental skills. Existing…

Robotics · Computer Science 2024-08-19 Xufeng Zhao , Cornelius Weber , Stefan Wermter

We study building multi-task agents in open-world environments. Without human demonstrations, learning to accomplish long-horizon tasks in a large open-world environment with reinforcement learning (RL) is extremely inefficient. To tackle…

Machine Learning · Computer Science 2023-12-05 Haoqi Yuan , Chi Zhang , Hongcheng Wang , Feiyang Xie , Penglin Cai , Hao Dong , Zongqing Lu

Modern large language models (LLMs) are often evaluated and deployed under a one-shot, greedy inference protocol, especially in professional settings that require deterministic behavior. This regime can systematically under-estimate a fixed…

Artificial Intelligence · Computer Science 2026-02-13 Xinhai Sun

In-context Learning (ICL) empowers large language models (LLMs) to swiftly adapt to unseen tasks at inference-time by prefixing a few demonstration examples before queries. Despite its versatility, ICL incurs substantial computational and…

Machine Learning · Computer Science 2025-02-26 Zhuowei Li , Zihao Xu , Ligong Han , Yunhe Gao , Song Wen , Di Liu , Hao Wang , Dimitris N. Metaxas

In safety-critical applications, autonomous agents may need to learn in an environment where mistakes can be very costly. In such settings, the agent needs to behave safely not only after but also while learning. To achieve this, existing…

Machine Learning · Computer Science 2021-01-22 Matteo Turchetta , Andrey Kolobov , Shital Shah , Andreas Krause , Alekh Agarwal

Agent skills are increasingly used to configure coding agents for software engineering (SE) tasks, yet current practice treats them as static, hand-crafted assets, or evolved on pass rate alone. This is insufficient: a skill can improve…

Software Engineering · Computer Science 2026-05-19 Jingzhi Gong , Ruizhen Gu , Zhiwei Fei , Yazhuo Cao , Lukas Twist , Alina Geiger , Shuo Han , Dominik Sobania , Federica Sarro , Jie M. Zhang

Large language model (LLM) agents deployed for multi-step tasks frequently fail in predictable ways: attempting actions with unmet preconditions, issuing redundant commands, or mishandling environment constraints. While retrieval-augmented…

Artificial Intelligence · Computer Science 2025-10-03 Humaid Ibrahim , Nikolai Rozanov , Marek Rei

The past years have seen Large Language Models (LLMs) strive not only as generative models but also as agents solving textual sequential decision-making tasks. When facing complex environments where their zero-shot abilities are…

Machine Learning · Computer Science 2026-01-30 Loris Gaven , Clement Romac , Thomas Carta , Sylvain Lamprier , Olivier Sigaud , Pierre-Yves Oudeyer

Reward-free, unsupervised discovery of skills is an attractive alternative to the bottleneck of hand-designing rewards in environments where task supervision is scarce or expensive. However, current skill pre-training methods, like many RL…

Machine Learning · Computer Science 2022-03-22 Nur Muhammad Shafiullah , Lerrel Pinto

Recent advances in batch (offline) reinforcement learning have shown promising results in learning from available offline data and proved offline reinforcement learning to be an essential toolkit in learning control policies in a model-free…

Machine Learning · Computer Science 2022-12-19 Ashish Kumar , Ilya Kuzovkin

In-Context Learning (ICL) empowers Large Language Models (LLMs) with the ability to learn from a few examples provided in the prompt, enabling downstream generalization without the requirement for gradient updates. Despite encouragingly…

Computation and Language · Computer Science 2025-01-28 Haitao Mao , Guangliang Liu , Yao Ma , Rongrong Wang , Kristen Johnson , Jiliang Tang

Large Language Models (LLMs) often struggle with mathematical reasoning tasks requiring precise, verifiable computation. While Reinforcement Learning (RL) from outcome-based rewards enhances text-based reasoning, understanding how agents…

Artificial Intelligence · Computer Science 2025-08-21 Xinji Mai , Haotian Xu , Zhong-Zhi Li , Xing W , Weinong Wang , Jian Hu , Yingying Zhang , Wenqiang Zhang

In-context reinforcement learning (ICRL) is an emerging RL paradigm where an agent, after pretraining, can adapt to out-of-distribution test tasks without any parameter updates, instead relying on an expanding context of interaction…

Machine Learning · Computer Science 2026-05-28 Amir Moeini , Minjae Kwon , Alper Kamil Bozkurt , Yuichi Motai , Rohan Chandra , Lu Feng , Shangtong Zhang

The dominant paradigm for improving mathematical reasoning in language models relies on Reinforcement Learning with verifiable rewards. Yet existing methods treat each problem instance in isolation without leveraging the reusable strategies…

Artificial Intelligence · Computer Science 2026-03-20 Yu Li , Rui Miao , Zhengling Qi , Tian Lan

Providing Reinforcement Learning agents with expert advice can dramatically improve various aspects of learning. Prior work has developed teaching protocols that enable agents to learn efficiently in complex environments; many of these…

Machine Learning · Computer Science 2017-01-17 David Abel , John Salvatier , Andreas Stuhlmüller , Owain Evans

Agentic reinforcement learning (RL) has proven effective for training LLM-based agents with external tool-use capabilities. However, we identify that agentic RL training induces increasing redundant tool calls and blurs the model's…

Computation and Language · Computer Science 2026-05-27 Dingwei Chen , Zefang Zong , Zhipeng Ma , Leo Luo , Yang Li , Chengming Li , Peng Chen , Jie Jiang

Hierarchical reinforcement learning (RL) can accelerate long-horizon decision-making by temporally abstracting a policy into multiple levels. Promising results in sparse reward environments have been seen with skills, i.e. sequences of…

Machine Learning · Computer Science 2024-07-15 Ce Hao , Catherine Weaver , Chen Tang , Kenta Kawamoto , Masayoshi Tomizuka , Wei Zhan

Practising and honing skills forms a fundamental component of how humans learn, yet artificial agents are rarely specifically trained to perform them. Instead, they are usually trained end-to-end, with the hope being that useful skills will…

Machine Learning · Computer Science 2022-08-17 Michael Matthews , Mikayel Samvelyan , Jack Parker-Holder , Edward Grefenstette , Tim Rocktäschel

Generalization and adaptation of learned skills to novel situations is a core requirement for intelligent autonomous robots. Although contextual reinforcement learning provides a principled framework for learning and generalization of…

Machine Learning · Computer Science 2019-10-08 Pascal Klink , Hany Abdulsamad , Boris Belousov , Jan Peters

We introduce a novel reinforcement learning framework of LLM agents named AGILE (AGent that Interacts and Learns from Environments) designed to perform complex conversational tasks with users, leveraging LLMs, memory, tools, and…

Machine Learning · Computer Science 2024-11-06 Peiyuan Feng , Yichen He , Guanhua Huang , Yuan Lin , Hanchong Zhang , Yuchen Zhang , Hang Li