Related papers: Training LLM Agents for Spontaneous, Reward-Free S…

Evaluating instruction-guided image edits requires rewards that reflect subtle human preferences, yet current reward models typically depend on large-scale preference annotation and additional model training. This creates a data-efficiency…

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…

In the realm of sequential decision-making tasks, the exploration capability of a reinforcement learning (RL) agent is paramount for achieving high rewards through interactions with the environment. To enhance this crucial ability, we…

While current software agents powered by large language models (LLMs) and agentic reinforcement learning (RL) can boost programmer productivity, their training data (e.g., GitHub issues and pull requests) and environments (e.g.,…

Large Language Model (LLM) agents are increasingly deployed to automate complex workflows in mobile and desktop environments. However, current model-centric agent architectures struggle to self-evolve post-deployment: improving…

In the early stages of human life, babies develop their skills by exploring different scenarios motivated by their inherent satisfaction rather than by extrinsic rewards from the environment. This behavior, referred to as intrinsic…

Training large language model (LLM) agents to acquire necessary skills and perform diverse tasks within an environment is gaining interest as a means to enable open-endedness. However, creating the training dataset for their skill…

The challenge of developing powerful and general Reinforcement Learning (RL) agents has received increasing attention in recent years. Much of this effort has focused on the single-agent setting, in which an agent maximizes a predefined…

Recent advances in LLM agents enable systems that autonomously refine workflows, accumulate reusable skills, self-train their underlying models, and maintain persistent memory. However, we show that such self-evolution is often…

Reinforcement learning with verifiable rewards (RLVR) has become the mainstream technique for training LLM agents. However, RLVR highly depends on well-crafted task queries and corresponding ground-truth answers to provide accurate rewards,…

As more machine learning agents interact with humans, it is increasingly a prospect that an agent trained to perform a task optimally, using only a measure of task performance as feedback, can violate societal norms for acceptable behavior…

The emergence of large language model (LLM)-based agents has significantly advanced the development of autonomous machine learning (ML) engineering. However, the dominant prompt-based paradigm exhibits limitations: smaller models lack the…

We use model-free reinforcement learning, extensive simulation, and transfer learning to develop a continuous control algorithm that has good zero-shot performance in a real physical environment. We train a simulated agent to act optimally…

Reinforcement learning (RL) is an appealing paradigm for training intelligent agents, enabling policy acquisition from the agent's own autonomously acquired experience. However, the training process of RL is far from automatic, requiring…

The rapid advancement of large language models (LLMs) has significantly enhanced the capabilities of AI-driven agents across various tasks. However, existing agentic systems, whether based on fixed pipeline algorithms or pre-defined…

Self-play has enabled large language models to autonomously improve through self-generated challenges. However, existing self-play methods for vision-language models rely on passive interaction with static image collections, resulting in…

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…

LLM-based agents have seen promising advances, yet they are still limited in "hard-exploration" tasks requiring learning new knowledge through exploration. We present GLoW, a novel approach leveraging dual-scale world models, maintaining a…

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…

Reinforcement learning has enabled agents to solve challenging tasks in unknown environments. However, manually crafting reward functions can be time consuming, expensive, and error prone to human error. Competing objectives have been…