English
Related papers

Related papers: Training Language Agents to Learn from Experience

200 papers

Large Language Models (LLMs) serve not only as chatbots but as key components in agent systems, where their common-sense knowledge significantly impacts performance as language-based planners for situated or embodied action. We assess LLMs'…

Computation and Language · Computer Science 2025-06-30 Jonathan Jordan , Sherzod Hakimov , David Schlangen

Learning models of artificial intelligence can nowadays perform very well on a large variety of tasks. However, in practice different task environments are best handled by different learning models, rather than a single, universal,…

Artificial Intelligence · Computer Science 2016-05-31 Adi Makmal , Alexey A. Melnikov , Vedran Dunjko , Hans J. Briegel

We introduce a new benchmark, LLF-Bench (Learning from Language Feedback Benchmark; pronounced as "elf-bench"), to evaluate the ability of AI agents to interactively learn from natural language feedback and instructions. Learning from…

Artificial Intelligence · Computer Science 2023-12-14 Ching-An Cheng , Andrey Kolobov , Dipendra Misra , Allen Nie , Adith Swaminathan

We introduce MetaICL (Meta-training for In-Context Learning), a new meta-training framework for few-shot learning where a pretrained language model is tuned to do in-context learning on a large set of training tasks. This meta-training…

Computation and Language · Computer Science 2022-05-04 Sewon Min , Mike Lewis , Luke Zettlemoyer , Hannaneh Hajishirzi

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

Imitation learning allows agents to learn complex behaviors from demonstrations. However, learning a complex vision-based task may require an impractical number of demonstrations. Meta-imitation learning is a promising approach towards…

Standard reinforcement learning (RL) for large language model (LLM) agents typically optimizes extrinsic rewards, prioritizing isolated task completion over continual adaptation. Consequently, agents often converge to suboptimal policies…

Artificial Intelligence · Computer Science 2026-03-31 Xiaoying Zhang , Zichen Liu , Yipeng Zhang , Xia Hu , Wenqi Shao

Many real-world tasks require language models (LMs) to reason over complex contexts that exceed their parametric knowledge. This calls for context learning, where LMs directly learn relevant knowledge from the given context. An intuitive…

In-context learning (ICL) with dynamically selected demonstrations combines the flexibility of prompting large language models (LLMs) with the ability to leverage training data to improve performance. While ICL has been highly successful…

Computation and Language · Computer Science 2025-06-17 Shivanshu Gupta , Sameer Singh , Ashish Sabharwal , Tushar Khot , Ben Bogin

Reinforcement Learning (RL) has traditionally focused on training specialized agents to optimize predefined reward functions within narrowly defined environments. However, the advent of powerful Large Language Models (LLMs) and increasingly…

Artificial Intelligence · Computer Science 2026-05-18 Fangming Cui , Ruixiao Zhu , Cheng Fang , Sunan Li , Jiahong Li

Reinforcement Learning (RL) in various decision-making tasks of machine learning provides effective results with an agent learning from a stand-alone reward function. However, it presents unique challenges with large amounts of environment…

Machine Learning · Computer Science 2020-03-10 Neda Navidi

Social learning is a key component of human and animal intelligence. By taking cues from the behavior of experts in their environment, social learners can acquire sophisticated behavior and rapidly adapt to new circumstances. This paper…

Machine Learning · Computer Science 2021-06-24 Kamal Ndousse , Douglas Eck , Sergey Levine , Natasha Jaques

Large language model (LLM) agents have been applied to sequential decision-making tasks such as web navigation, but without any environment-specific experiences, they often fail in these complex tasks. Moreover, current LLM agents are not…

Artificial Intelligence · Computer Science 2025-06-10 Yitao Liu , Chenglei Si , Karthik Narasimhan , Shunyu Yao

Traditionally, reinforcement learning (RL) agents learn to solve new tasks by updating their neural network parameters through interactions with the task environment. However, recent works demonstrate that some RL agents, after certain…

Machine Learning · Computer Science 2025-02-26 Jiuqi Wang , Ethan Blaser , Hadi Daneshmand , Shangtong Zhang

We consider an extended notion of reinforcement learning in which the environment can simulate the agent and base its outputs on the agent's hypothetical behavior. Since good performance usually requires paying attention to whatever things…

Artificial Intelligence · Computer Science 2022-07-21 Samuel Allen Alexander , Michael Castaneda , Kevin Compher , Oscar Martinez

Despite recent success of deep network-based Reinforcement Learning (RL), it remains elusive to achieve human-level efficiency in learning novel tasks. While previous efforts attempt to address this challenge using meta-learning strategies,…

Machine Learning · Computer Science 2022-05-03 Haozhe Wang , Jiale Zhou , Xuming He

A centerpiece of the ever-popular reinforcement learning from human feedback (RLHF) approach to fine-tuning autoregressive language models is the explicit training of a reward model to emulate human feedback, distinct from the language…

Computation and Language · Computer Science 2023-05-22 Wanqiao Xu , Shi Dong , Dilip Arumugam , Benjamin Van Roy

Recent work has described neural-network-based agents that are trained with reinforcement learning (RL) to execute language-like commands in simulated worlds, as a step towards an intelligent agent or robot that can be instructed by human…

Computation and Language · Computer Science 2020-05-20 Felix Hill , Sona Mokra , Nathaniel Wong , Tim Harley

Adapting one's thought process based on corrective feedback is an essential ability in human learning, particularly in collaborative settings. In contrast, the current large language model training paradigm relies heavily on modeling vast,…

Artificial Intelligence · Computer Science 2026-02-19 Martin Klissarov , Jonathan Cook , Diego Antognini , Hao Sun , Jingling Li , Natasha Jaques , Claudiu Musat , Edward Grefenstette

Whereas machine learning models typically learn language by directly training on language tasks (e.g., next-word prediction), language emerges in human children as a byproduct of solving non-language tasks (e.g., acquiring food). Motivated…

Computation and Language · Computer Science 2023-06-16 Evan Zheran Liu , Sahaana Suri , Tong Mu , Allan Zhou , Chelsea Finn