Related papers: WebGym: Scaling Training Environments for Visual W…

Agent systems powered by large language models (LLMs) have demonstrated impressive performance on repository-level code-generation tasks. However, for tasks such as website codebase generation, which depend heavily on visual effects and…

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…

We introduce MedAgentGym, a scalable and interactive training environment designed to enhance coding-based biomedical reasoning capabilities in large language model (LLM) agents. MedAgentGym comprises 72,413 task instances across 129…

While recent vision-language models (VLMs) demonstrate strong image understanding, their ability to "think with images", i.e., to reason through multi-step visual interactions, remains limited. We introduce VISTA-Gym, a scalable training…

We present SWE-Gym, the first environment for training real-world software engineering (SWE) agents. SWE-Gym contains 2,438 real-world Python task instances, each comprising a codebase with an executable runtime environment, unit tests, and…

In order to practically implement the door opening task, a policy ought to be robust to a wide distribution of door types and environment settings. Reinforcement Learning (RL) with Domain Randomization (DR) is a promising technique to…

We introduce VectorGym, a comprehensive benchmark suite for Scalable Vector Graphics (SVG) that spans generation from text and sketches, complex editing, and visual understanding. VectorGym addresses the lack of realistic, challenging…

Memory is a central capability for LLM agents operating across long-horizon tasks. Existing memory benchmarks predominantly evaluate retention of personalized information in multi-turn chat scenarios, overlooking the dynamic memory…

Effective visual representation learning is crucial for reinforcement learning (RL) agents to extract task-relevant information from raw sensory inputs and generalize across diverse environments. However, existing RL benchmarks lack the…

Evaluating robot control policies is difficult: real-world testing is costly, and handcrafted simulators require manual effort to improve in realism and generality. We propose a world-model-based policy evaluation environment (WorldGym), an…

As agentic systems increasingly rely on reinforcement learning from verifiable rewards, standardized ``gym'' infrastructure has become essential for rapid iteration, reproducibility, and fair comparison. Vision agents lack such…

Reinforcement Learning (RL) is a promising solution, allowing Unmanned Underwater Vehicles (UUVs) to learn optimal behaviors through trial and error. However, existing simulators lack efficient integration with RL methods, limiting training…

GUI agents that interact with graphical interfaces on behalf of users represent a promising direction for practical AI assistants. However, training such agents is hindered by the scarcity of suitable environments. We present InfiniteWeb, a…

Despite promising progress in reinforcement learning (RL), developing algorithms for autonomous driving (AD) remains challenging: one of the critical issues being the absence of an open-source platform capable of training and effectively…

Vision language models (VLMs) achieve strong performance on general image understanding but struggle to think with medical images, especially when performing multi-step reasoning through iterative visual interaction. Medical VLMs often rely…

Recently, there has been a surge of vision-based GUI agents designed to automate everyday mobile and web tasks. These agents interpret raw GUI screenshots and autonomously decide where to click, scroll, or type, which bypasses handcrafted…

Interactive multimodal agents must convert raw visual observations into coherent sequences of language-conditioned actions -- a capability that current vision-language models (VLMs) still lack. Earlier reinforcement-learning (RL) efforts…

We propose VRGym, a virtual reality testbed for realistic human-robot interaction. Different from existing toolkits and virtual reality environments, the VRGym emphasizes on building and training both physical and interactive agents for…

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…

The rapid advancement of large language models (LLMs) has led to a new era marked by the development of autonomous applications in real-world scenarios, which drives innovation in creating advanced web agents. Existing web agents typically…