Related papers: SWE-MiniSandbox: Container-Free Reinforcement Lear…
Safety comes first in many real-world applications involving autonomous agents. Despite a large number of reinforcement learning (RL) methods focusing on safety-critical tasks, there is still a lack of high-quality evaluation of those…
Software Engineering Agents (SWE-Agents) have proven effective for traditional software engineering tasks with accessible codebases, but their performance for embodied tasks requiring well-designed information discovery remains unexplored.…
In this technical report, we present SWE-Master, an open-source and fully reproducible post-training framework for building effective software engineering agents. SWE-Master systematically explores the complete agent development pipeline,…
Model-free reinforcement learning algorithms have exhibited great potential in solving single-task sequential decision-making problems with high-dimensional observations and long horizons, but are known to be hard to generalize across…
Agentic intelligence in large language models (LLMs) requires not only model intrinsic capabilities but also interactions with external environments. Equipping LLMs with computers now represents a prevailing trend. However, the computer…
In the past decade, model-free reinforcement learning (RL) has provided solutions to challenging domains such as robotics. Model-based RL shows the prospect of being more sample-efficient than model-free methods in terms of…
Improving open-source models on real-world SWE tasks (solving GITHUB issues) faces two key challenges: 1) scalable curation of execution environments to train these models, and, 2) optimal scaling of test-time compute. We introduce…
Agent skills, structured procedural knowledge packages injected at inference time, are increasingly used to augment LLM agents on software engineering tasks. However, their real utility in end-to-end development settings remains unclear. We…
While large language model agents have advanced software engineering tasks, the unscalable nature of existing test-based supervision is limiting the potential improvement of data scaling. The reason is twofold: (1) building and running test…
This paper studies the container lifting phase of a waste-container recycling task in urban environments, performed by a hydraulic loader crane equipped with an underactuated discharge unit, and proposes a residual reinforcement learning…
An important goal of research in Deep Reinforcement Learning in mobile robotics is to train agents capable of solving complex tasks, which require a high level of scene understanding and reasoning from an egocentric perspective. When…
Recent advancements in software engineering agents have demonstrated promising capabilities in automating program improvements. However, their reliance on closed-source or resource-intensive models introduces significant deployment…
Creating large-scale verifiable training datasets for issue-resolving tasks is a critical yet notoriously difficult challenge. Existing methods on automating the Gym environment setup process for real-world issues suffer from low success…
Optimizing the performance of large-scale software repositories demands expertise in code reasoning and software engineering (SWE) to reduce runtime while preserving program correctness. However, most benchmarks emphasize what to fix rather…
Offline reinforcement learning (RL) enables learning control policies by utilizing only prior experience, without any online interaction. This can allow robots to acquire generalizable skills from large and diverse datasets, without any…
We study building multi-task agents in open-world environments. Without human demonstrations, learning to accomplish long-horizon tasks in a large open-world environment with reinforcement learning (RL) is extremely inefficient. To tackle…
Control certificates based on barrier functions have been a powerful tool to generate probably safe control policies for dynamical systems. However, existing methods based on barrier certificates are normally for white-box systems with…
Natural agents can effectively learn from multiple data sources that differ in size, quality, and types of measurements. We study this heterogeneity in the context of offline reinforcement learning (RL) by introducing a new, practically…
While Reinforcement Learning (RL) has achieved remarkable success in language modeling, its triumph hasn't yet fully translated to visuomotor agents. A primary challenge in RL models is their tendency to overfit specific tasks or…
Recent advancements in large language models (LLMs) have significantly advanced the automation of software development tasks, including code synthesis, program repair, and test generation. More recently, researchers and industry…