Related papers: Training Versatile Coding Agents in Synthetic Envi…
Web agents struggle to adapt to new websites due to the scarcity of environment specific tasks and demonstrations. Recent works have explored synthetic data generation to address this challenge, however, they suffer from data quality issues…
Understanding and reasoning about entire software repositories is an essential capability for intelligent software engineering tools. While existing benchmarks such as CoSQA and CodeQA have advanced the field, they predominantly focus on…
Mobile agents powered by vision-language models have demonstrated impressive capabilities in automating mobile tasks, with recent leading models achieving a marked performance leap, e.g., nearly 70% success on AndroidWorld. However, these…
World models are central to building agents that can reason, plan, and generalize beyond their training data. However, research on world models is currently fragmented, with disparate codebases, data pipelines, and evaluation protocols…
Reinforcement Learning methods are capable of solving complex problems, but resulting policies might perform poorly in environments that are even slightly different. In robotics especially, training and deployment conditions often vary and…
We introduce AgentSynth, a scalable and cost-efficient pipeline for automatically synthesizing high-quality tasks and trajectory datasets for generalist computer-use agents. Leveraging information asymmetry, AgentSynth constructs subtasks…
The rapid development of deep learning techniques, improved computational power, and the availability of vast training data have led to significant advancements in pre-trained models and large language models (LLMs). Pre-trained models…
The development of robot control programs is a complex task. Many robots are different in their electrical and mechanical structure which is also reflected in the software. Specific robot software environments support the program…
Turning ideas into full software projects from scratch has become a popular use case for language models. Agents are being deployed to seed, maintain, and grow codebases over extended periods with minimal human oversight. Such settings…
Conducting reinforcement learning (RL) in simulated environments offers a cost-effective and highly scalable way to enhance language-based agents. However, previous work has been limited to semi-automated environment synthesis or tasks…
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…
This paper aims to introduce a robust singing voice synthesis (SVS) system to produce very natural and realistic singing voices efficiently by leveraging the adversarial training strategy. On one hand, we designed simple but generic random…
Coordination behavior in robot swarms is inherently multi-modal in nature. That is, there are numerous ways in which a swarm of robots can avoid inter-agent collisions and reach their respective goals. However, the problem of generating…
Software engineers are responsible for developing, maintaining, and innovating software. To hire software engineers, organizations employ a tech hiring pipeline. This process typically consists of a series of steps to evaluate the extent to…
The dominant paradigm for AI agents is an "on-the-fly" loop in which agents synthesize plans and execute actions within seconds or minutes in response to user prompts. We argue that this paradigm short-circuits disciplined software…
Open-ended learning frames intelligence as emerging from continual interaction with an ever-expanding space of environments. While recent advances have utilized foundation models to programmatically generate diverse environments, these…
SLEDGE is the first generative simulator for vehicle motion planning trained on real-world driving logs. Its core component is a learned model that is able to generate agent bounding boxes and lane graphs. The model's outputs serve as an…
The increasing deployment of Large Language Model (LLM) agents for complex software engineering tasks has created a need to understand their problem-solving behaviours beyond simple success metrics. While these agents demonstrate impressive…
Language Models (LLMs), such as transformer-based neural networks trained on billions of parameters, have become increasingly prevalent in software engineering (SE). These models, trained on extensive datasets that include code…
Satisfactory software performance is essential for the adoption and the success of a product. In organizations that follow traditional software development models (e.g., waterfall), Software Performance Engineering (SPE) involves…