Related papers: Reinforcement Learning for Self-Improving Agent wi…

Skill-based reinforcement learning (RL) has emerged as a promising strategy to leverage prior knowledge for accelerated robot learning. Skills are typically extracted from expert demonstrations and are embedded into a latent space from…

Reinforcement learning (RL) is the dominant paradigm for sharpening strategic tool use capabilities of LLMs on long-horizon, sparsely-rewarded agent tasks, yet it faces a fundamental challenge of exploration-exploitation trade-off. Existing…

Recent advances in large language models (LLMs) have demonstrated remarkable capabilities in reasoning and tool utilization. However, the generalization of tool-augmented reinforcement learning (RL) across diverse domains remains a…

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…

Large Language Models (LLMs) have shown impressive capabilities across various tasks but remain vulnerable to meticulously crafted jailbreak attacks. In this paper, we identify a critical safety gap: while LLMs are adept at detecting…

The recent advancements of Large Language Models (LLMs) have spurred considerable research interest in extending their linguistic capabilities beyond text to other modalities, which leads to emergence of speech-based LLMs (SpeechLMs) with…

A persistent skill library allows language model agents to reuse successful strategies across tasks. Maintaining such a library requires three coupled capabilities. The agent selects a relevant skill, utilizes it during execution, and…

Large language models (LLMs) can generate syntactically valid optimization programs, yet often struggle to reliably choose an effective modeling strategy, leading to incorrect formulations and inefficient solver behavior. We propose SAGE, a…

Large language models (LLMs) have proven to work well in question-answering scenarios, but real-world applications often require access to tools for live information or actuation. For this, LLMs can be extended with tools, which are often…

We propose a generic reward shaping approach for improving the rate of convergence in reinforcement learning (RL), called Self Improvement Based REwards, or SIBRE. The approach is designed for use in conjunction with any existing RL…

Multi-agent reinforcement learning (MARL) faces two critical bottlenecks distinct from single-agent RL: credit assignment in cooperative tasks and partial observability of environmental states. We propose LERO, a framework integrating Large…

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…

The advent of large language models (LLMs) has transformed information access and reasoning through open-ended natural language interaction. However, LLMs remain limited by static knowledge, factual hallucinations, and the inability to…

Knowledge extrapolation is the process of inferring novel information by combining and extending existing knowledge that is explicitly available. It is essential for solving complex questions in specialized domains where retrieving…

Reinforcement learning (RL) has proven effective for fine-tuning large language models (LLMs), significantly enhancing their reasoning abilities in domains such as mathematics and code generation. A crucial factor influencing RL fine-tuning…

Large Language Model (LLM) Agents, often trained with Reinforcement Learning (RL), are constrained by a dependency on human-curated data, limiting scalability and tethering AI to human knowledge. Existing self-evolution frameworks offer an…

Agent-based models (ABMs) stand as an essential paradigm for proposing and validating hypothetical solutions or policies aimed at addressing challenges posed by complex systems and achieving various objectives. This process demands…

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…

Reinforcement Learning (RL) has emerged as a powerful paradigm for sequential decision-making and has attracted growing interest across various domains, particularly following the advent of Deep Reinforcement Learning (DRL) in 2015.…

Experience-driven self-evolving agents aim to overcome the static nature of large language models by distilling reusable experience from past interactions, thus enabling adaptation to novel tasks at deployment time. This process places…