Related papers: CODE-SHARP: Continuous Open-ended Discovery and Ev…

Long-horizon precision manipulation in laboratory automation, such as pipette tip attachment and liquid transfer, requires policies that respect strict procedural logic while operating in continuous, high-dimensional state spaces. However,…

Test-time skill evolving is regarded as a new paradigm for enhancing deployed agentic systems. Existing works mainly focus on hard-coded skill evolving strategies or parametric learning that rely on expensive parameter updates in the…

Current reinforcement learning from human feedback (RLHF) pipelines for large language model (LLM) alignment typically assign scalar rewards to sequences, using the final token as a surrogate indicator for the quality of the entire…

Reinforcement learning provides an automated framework for learning behaviors from high-level reward specifications, but in practice the choice of reward function can be crucial for good results -- while in principle the reward only needs…

"Code-as-Policy" considers how executable code can complement data-intensive Vision-Language-Action (VLA) methods, yet their effectiveness as autonomous controllers for embodied manipulation remains underexplored. We present CaP-X, an…

We introduce \emph{Memento-Skills}, a generalist, continually-learnable LLM agent system that functions as an \emph{agent-designing agent}: it autonomously constructs, adapts, and improves task-specific agents through experience. The system…

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…

LM-based agents excel when given high-level action APIs but struggle to ground language into low-level control. Prior work has LLMs generate skills or reward functions for RL, but these one-shot approaches lack feedback to correct…

Sparse rewards and long time horizons remain challenging for reinforcement learning algorithms. Exploration bonuses can help in sparse reward settings by encouraging agents to explore the state space, while hierarchical approaches can…

The ability to transfer skills across tasks has the potential to scale up reinforcement learning (RL) agents to environments currently out of reach. Recently, a framework based on two ideas, successor features (SFs) and generalised policy…

Reward models (RMs) have become essential for aligning large language models (LLMs), serving as scalable proxies for human evaluation in both training and inference. However, existing RMs struggle on knowledge-intensive and long-form tasks,…

Most LLM-based agent frameworks adopt a top-down philosophy: humans decompose tasks, define workflows, and assign agents to execute each step. While effective on benchmark-style tasks, such systems rely on designer updates and overlook…

Large language model (LLM)-based agents that reason, plan, and act through tools, memory, and structured interaction are emerging as a promising paradigm for automating complex workflows. Recent systems such as OpenClaw and Claude Code…

Reward-free, unsupervised discovery of skills is an attractive alternative to the bottleneck of hand-designing rewards in environments where task supervision is scarce or expensive. However, current skill pre-training methods, like many RL…

The objective of lifelong reinforcement learning (RL) is to optimize agents which can continuously adapt and interact in changing environments. However, current RL approaches fail drastically when environments are non-stationary and…

Open-ended AI agents need to be able to learn efficiently goals of increasing complexity, abstraction and heterogeneity over their lifetime. Beyond sampling efficiently their own goals, autotelic agents specifically need to be able to keep…

Practising and honing skills forms a fundamental component of how humans learn, yet artificial agents are rarely specifically trained to perform them. Instead, they are usually trained end-to-end, with the hope being that useful skills will…

Reinforcement learning has been successful in training autonomous agents to accomplish goals in complex environments. Although this has been adapted to multiple settings, including robotics and computer games, human players often find it…

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…

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…