Related papers: SkillOS: Learning Skill Curation for Self-Evolving…

We study whether self-learning can scale LLM-based agents without relying on human-curated datasets or predefined rule-based rewards. Through controlled experiments in a search-agent setting, we identify two key determinants of scalable…

Large language model (LLM) powered AI agents have emerged as a promising paradigm for autonomous problem-solving, yet they continue to struggle with complex, multi-step real-world tasks that demand domain-specific procedural knowledge.…

Traditional language-conditioned manipulation agent sequential adaptation to new manipulation skills leads to catastrophic forgetting of old skills, limiting dynamic scene practical deployment. In this paper, we propose SkillsCrafter, a…

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…

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…

As artificial intelligence engineering paradigms shift from single-agent Prompt and Context Engineering toward multi-agent \textbf{Coordination Engineering}, the ability to codify and systematically improve how multiple agents collaborate…

Reinforcement learning (RL) agents improve through trial-and-error, but when reward is sparse and the agent cannot discover successful action sequences, learning stagnates. This has been a notable problem in training deep RL agents to…

Teaching language models to use search tools is not only a question of whether they search, but also of whether they issue good queries. This is especially important in open-domain question answering, where broad or copied queries often…

Agentic RL can benefit substantially from reusable experience, yet existing skill-based methods mainly extract trajectory-level guidance and often lack principled mechanisms for maintaining an evolving skill memory. We propose D2Skill, a…

We propose BOSS, an approach that automatically learns to solve new long-horizon, complex, and meaningful tasks by growing a learned skill library with minimal supervision. Prior work in reinforcement learning require expert supervision, in…

Recent advances in multi-agent reinforcement learning (MARL) allow agents to coordinate their behaviors in complex environments. However, common MARL algorithms still suffer from scalability and sparse reward issues. One promising approach…

In social dilemma situations, individual rationality leads to sub-optimal group outcomes. Several human engagements can be modeled as a sequential (multi-step) social dilemmas. However, in contrast to humans, Deep Reinforcement Learning…

Hierarchical reinforcement learning (RL) can accelerate long-horizon decision-making by temporally abstracting a policy into multiple levels. Promising results in sparse reward environments have been seen with skills, i.e. sequences of…

The fundamental limitation of the behavioral cloning (BC) approach to imitation learning is that it only teaches an agent what the expert did at states the expert visited. This means that when a BC agent makes a mistake which takes them out…

As LLM agents are increasingly deployed with large libraries of reusable skills, selecting the right skill for a user request has become a critical systems challenge. In small libraries, users may invoke skills explicitly by name, but this…

Compound AI systems promise capabilities beyond those of individual models, yet their success depends critically on effective orchestration. Existing routing approaches face two limitations: (1) input-level routers make coarse query-level…

Curriculum learning plays a crucial role in enhancing the training efficiency of large language models (LLMs) on reasoning tasks. However, existing methods often fail to adequately account for variations in prompt difficulty or rely on…

Agent skills extend LLM agents with reusable instructions, tool interfaces, and executable code, and users increasingly install third-party skills from marketplaces, repositories, and community channels. Because a skill exposes both…

Self-supervised skill learning aims to acquire useful behaviors that leverage the underlying dynamics of the environment. Latent variable models, based on mutual information maximization, have been successful in this task but still struggle…

Reusable skills play a key role in improving LLM-based agents, but existing skill-evolution methods often fail to ensure that evolved skills both cover the knowledge required by the task and remain aligned with the target task. As a result,…