Related papers: Skill Set Optimization: Reinforcing Language Model…

Simultaneous speech translation (SST) generates translations while receiving partial speech input. Recent advances show that large language models (LLMs) can substantially improve SST quality, but at the cost of high computational overhead.…

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.,…

Optimization problems often require domain-specific expertise to design problem-dependent methodologies. Recently, several approaches have gained attention by integrating large language models (LLMs) into genetic algorithms. Building on…

Reinforcement Learning (RL) has shown great potential for autonomous decision-making in the cybersecurity domain, enabling agents to learn through direct environment interaction. However, RL agents in Autonomous Cyber Operations (ACO)…

The ability to autonomously explore and resolve tasks with minimal human guidance is crucial for the self-development of embodied intelligence. Although reinforcement learning methods can largely ease human effort, it's challenging to…

The ability to walk in new scenarios is a key milestone on the path toward real-world applications of legged robots. In this work, we introduce Meta Strategy Optimization, a meta-learning algorithm for training policies with latent variable…

The outstanding capabilities of large language models (LLMs) render them a crucial component in various autonomous agent systems. While traditional methods depend on the inherent knowledge of LLMs without fine-tuning, more recent approaches…

Human preference alignment is critical in building powerful and reliable large language models (LLMs). However, current methods either ignore the multi-dimensionality of human preferences (e.g. helpfulness and harmlessness) or struggle with…

Reinforcement learning (RL) has demonstrated notable success in post-training large language models (LLMs) as agents for tasks such as computer use, tool calling, and coding. However, exploration remains a central challenge in RL for LLM…

Adapting large language models to other languages typically employs supervised fine-tuning (SFT) as a standard approach. However, it often suffers from an overemphasis on English performance, a phenomenon that is especially pronounced in…

We investigate the task of learning to follow natural language instructions by jointly reasoning with visual observations and language inputs. In contrast to existing methods which start with learning from demonstrations (LfD) and then use…

Recent studies have uncovered the potential of Large Language Models (LLMs) in addressing complex sequential decision-making tasks through the provision of high-level instructions. However, LLM-based agents lack specialization in tackling…

Strategic decision-making in multi-agent settings is a key challenge for large language models (LLMs), particularly when coordination and negotiation must unfold over extended conversations. While recent work has explored the use of LLMs in…

Reinforcement learning with verifiable rewards has emerged as a powerful paradigm for training intelligent agents. However, existing methods typically employ binary rewards that fail to capture quality differences among trajectories…

Proximal Policy Optimization (PPO) is commonly used in Reinforcement Learning from Human Feedback to align large language models (LLMs) with downstream tasks. This paper investigates the feasibility of using PPO for direct reinforcement…

Large language model (LLM)--based agents have emerged as pivotal tools in assisting human experts across various fields by transforming complex tasks into more efficient workflows and providing actionable stakeholder insights. Despite their…

How have individuals of social animals in nature evolved to learn from each other, and what would be the optimal strategy for such learning in a specific environment? Here, we address both problems by employing a deep reinforcement learning…

Large language model (LLM) agents increasingly rely on reusable skills: capability packages that combine instructions, control flow, constraints, and tool calls. In current agent systems, however, skills are still represented by text-heavy…

Large Language Models (LLMs) are increasingly acting as autonomous agents, but their continuous interaction with the environment can lead to in-context reward hacking (ICRH), a phenomenon where LLMs iteratively optimize their behavior to…

Post-training processes are essential phases in grounding pre-trained language models to real-world tasks, with learning from demonstrations or preference signals playing a crucial role in this adaptation. We present a unified theoretical…