Related papers: CoEvolve: Training LLM Agents via Agent-Data Mutua…

Recent advancements in large language models (LLMs) have brought significant changes to various domains, especially through LLM-driven autonomous agents. A representative scenario is in software development, where LLM agents demonstrate…

In recent years, instruction fine-tuning (IFT) on large language models (LLMs) has garnered considerable attention to enhance model performance on unseen tasks. Attempts have been made on automatic construction and effective selection for…

Agent self-improvement, where the backbone Large Language Model (LLM) of the agent are trained on trajectories sampled autonomously based on their own policies, has emerged as a promising approach for enhancing performance. Recent…

Training capable Large Language Model (LLM) agents is critically bottlenecked by the high cost and static nature of real-world interaction data. We address this by introducing GenEnv, a framework that establishes a difficulty-aligned…

A central challenge in building continually improving agents is that training environments are typically static or manually constructed. This restricts continual learning and generalization beyond the training distribution. We address this…

Reinforcement Learning (RL) has demonstrated significant potential in enhancing the reasoning capabilities of large language models (LLMs). However, the success of RL for LLMs heavily relies on human-curated datasets and verifiable rewards,…

Self-evolution is a central research topic in enabling large language model (LLM)-based agents to continually improve their capabilities after pretraining. Recent research has witnessed a transition from reinforcement learning (RL)-free to…

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…

Self-evolving memory systems are unprecedentedly reshaping the evolutionary paradigm of large language model (LLM)-based agents. Prior work has predominantly relied on manually engineered memory architectures to store trajectories, distill…

Autonomous agents powered by large language models (LLMs) have the potential to significantly enhance human productivity by reasoning, using tools, and executing complex tasks in diverse environments. However, current approaches to…

Large language model (LLM) agents such as OpenClaw rely on reusable skills to perform complex tasks, yet these skills remain largely static after deployment. As a result, similar workflows, tool usage patterns, and failure modes are…

Autonomous agents powered by large language models (LLMs) have the potential to enhance human capabilities, assisting with digital tasks from sending emails to performing data analysis. The abilities of existing LLMs at such tasks are often…

Online question-and-answer (Q\&A) systems based on the Large Language Model (LLM) have progressively diverged from recreational to professional use. This paper proposed a Multi-Agent framework with environmentally reinforcement learning…

LLM-powered tool-calling agents fulfill user requests by interacting with environments, querying data, and invoking tools in a multi-turn process. Yet, most existing benchmarks evaluate these systems under static environment interfaces,…

LLM-based multi-agent systems (MAS) have emerged as an effective paradigm for complex and long-horizon tasks. However, in real-world tasks, MAS often exhibit various failures during execution and such failures are difficult to eliminate…

Most agents today ``self-evolve'' by following rewards and rules defined by humans. However, this process remains fundamentally dependent on external supervision; without human guidance, the evolution stops. In this work, we train agents to…

Recent advances have enabled large language model (LLM) agents to solve complex tasks by orchestrating external tools. However, these agents often struggle in specialized, tool-intensive domains that demand long-horizon execution, tight…

Large language models (LLMs) possess extensive knowledge bases and strong reasoning capabilities, making them promising tools for complex, multi-agent planning in embodied environments. However, despite LLMs' advanced abilities and the…

Reinforcement learning (RL) has emerged as a pivotal technique for fine-tuning large language models (LLMs) on specific tasks. However, prevailing RL fine-tuning methods predominantly rely on PPO and its variants. Though these algorithms…

Current Large Language Model (LLM) agents show strong performance in tool use, but lack the crucial capability to systematically learn from their own experiences. While existing frameworks mainly focus on mitigating external knowledge gaps,…