Related papers: ScaleEnv: Scaling Environment Synthesis from Scrat…

Terminal agents have demonstrated strong potential for autonomous command-line execution, yet their training remains constrained by the scarcity of high-quality and diverse execution trajectories. Existing approaches mitigate this…

Reusable skills are becoming a common interface for extending large language model agents, packaging procedural guidance with access to files, tools, memory, and execution environments. However, this modularity introduces attack surfaces…

Multi-agent embodied systems hold promise for complex collaborative manipulation, yet face critical challenges in spatial coordination, temporal reasoning, and shared workspace awareness. Inspired by human collaboration where cognitive…

Agent skills today are static artifact: authored once -- by human curation or one-shot generation from parametric knowledge -- and then consumed unchanged, with no mechanism to improve from real use. We propose \textbf{SkillEvolver}, a…

When assessing the quality of coding agents, predominant benchmarks focus on solving single issues on GitHub, such as SWE-Bench. In contrast, in real use, these agents solve more various and complex tasks that involve other skills such as…

We introduce Reinforcement Learning (RL) with Adaptive Verifiable Environments (RLVE), an approach using verifiable environments that procedurally generate problems and provide algorithmically verifiable rewards, to scale up RL for language…

Building generalist agents that can handle diverse tasks and evolve themselves across different environments is a long-term goal in the AI community. Large language models (LLMs) are considered a promising foundation to build such agents…

In this work we create agents that can perform well beyond a single, individual task, that exhibit much wider generalisation of behaviour to a massive, rich space of challenges. We define a universe of tasks within an environment domain and…

Generalization to unseen real-world scenarios for robot manipulation requires exposure to diverse datasets during training. However, collecting large real-world datasets is intractable due to high operational costs. For robot learning to…

Learning from experience is critical for building capable large language model (LLM) agents, yet prevailing self-evolving paradigms remain inefficient: agents learn in isolation, repeatedly rediscover similar behaviors from limited…

LLM-based agents have shown promising capabilities in a growing range of software engineering (SWE) tasks. However, advancing this field faces two critical challenges. First, high-quality training data is scarce, especially data that…

Agentic coding requires agents to effectively interact with runtime environments, e.g., command line interfaces (CLI), so as to complete tasks like resolving dependency issues, fixing system problems, etc. But it remains underexplored how…

With the advent of AI agents, automatic scientific discovery has become a tenable goal. Many recent works scaffold agentic systems that can perform machine learning research, but don't offer a principled way to train such agents -- and…

We introduce Procgen Benchmark, a suite of 16 procedurally generated game-like environments designed to benchmark both sample efficiency and generalization in reinforcement learning. We believe that the community will benefit from increased…

The pursuit of robot generalists, agents capable of performing diverse tasks across diverse environments, demands rigorous and scalable evaluation. Yet real-world testing of robot policies remains fundamentally constrained: it is…

Synthetic data offers a scalable solution for vision-language pre-training, yet current state-of-the-art methods typically rely on scaling up a single generative backbone, which introduces generator-specific spectral biases and limits…

Post-Training Multimodal Large Language Models (MLLMs) to build interactive agents holds promise across domains such as computer-use, web navigation, and robotics. A key challenge in scaling such post-training is lack of high-quality…

The development of embodied agents for complex commercial environments is hindered by a critical gap in existing robotics datasets and benchmarks, which primarily focus on household or tabletop settings with short-horizon tasks. To address…

We propose SWE-Universe, a scalable and efficient framework for automatically constructing real-world software engineering (SWE) verifiable environments from GitHub pull requests (PRs). To overcome the prevalent challenges of automatic…

The advancement of general-purpose intelligent agents is intrinsically linked to the environments in which they are trained. While scaling models and datasets has yielded remarkable capabilities, scaling the complexity, diversity, and…