Related papers: ScaleEnv: Scaling Environment Synthesis from Scrat…

Recent SOTA approaches for embodied learning via interaction directly employ large language models (LLMs) as agents to determine the next steps in an environment. Due to their world knowledge and reasoning capabilities, LLM agents achieve…

Large language model-based web agents have demonstrated strong performance on realistic web interaction tasks. However, existing evaluations are predominantly conducted under relatively stable and well-behaved interaction conditions, which…

Reinforcement Learning (RL) has emerged as a powerful training paradigm for LLM-based agents. However, scaling agentic RL for deep research remains constrained by two coupled challenges: hand-crafted synthetic data fails to elicit genuine…

We present SynthTextEval, a toolkit for conducting comprehensive evaluations of synthetic text. The fluency of large language model (LLM) outputs has made synthetic text potentially viable for numerous applications, such as reducing the…

The rapid advancement of multimodal large language models has enabled agents to operate mobile devices by directly interacting with graphical user interfaces, opening new possibilities for mobile automation. However, real-world mobile tasks…

We introduce Meta Agents Research Environments (ARE), a research platform for scalable creation of environments, integration of synthetic or real applications, and execution of agentic orchestrations. ARE provides simple abstractions to…

Multi-dataset training provides a viable solution for exploiting heterogeneous large-scale datasets without extra annotation cost. In this work, we propose a scalable multi-dataset detector (ScaleDet) that can scale up its generalization…

Modeling of command-line interface (CLI) interaction has enabled flexible, execution-free output presentation. However, current approaches struggle to model inputs with complex compositions and inputs whose execution behavior depends on…

Realizing scaling laws in embodied AI has become a focus. However, previous work has been scattered across diverse simulation platforms, with assets and models lacking unified interfaces, which has led to inefficiencies in research. To…

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…

We present ShuttleEnv, an interactive and data-driven simulation environment for badminton, designed to support reinforcement learning and strategic behavior analysis in fast-paced adversarial sports. The environment is grounded in…

Most existing spatial reasoning benchmarks focus on static or globally observable environments, failing to capture the challenges of long-horizon reasoning and memory utilization under partial observability and dynamic changes. We introduce…

Simulation plays a crucial role in the development of autonomous vehicles (AVs) due to the potential risks associated with real-world testing. Although significant progress has been made in the visual aspects of simulators, generating…

Recent advancements in Vision Language Models (VLMs) have expanded their capabilities to interactive agent tasks, yet existing benchmarks remain limited to single-agent or text-only environments. In contrast, real-world scenarios often…

Self-supervised learning and data augmentation have significantly reduced the performance gap between state and image-based reinforcement learning agents in continuous control tasks. However, it is still unclear whether current techniques…

This paper studies the next major bottleneck in agentic AI as system scaling, not only model scaling: the design of auditable, persistent, modular, and verifiable architectures around foundation models. We refer to this shift as scaling the…

Vision-Language-Action (VLA) models have emerged as a generalist robotic agent. However, existing VLAs are hindered by excessive parameter scales, prohibitive pre-training requirements, and limited applicability to diverse embodiments. To…

Software vulnerabilities continue to grow in volume and remain difficult to detect in practice. Although learning-based vulnerability detection has progressed, existing benchmarks are largely function-centric and fail to capture realistic,…

General-purpose computer-use agents have shown impressive performance across diverse digital environments. However, our new benchmark, OSExpert-Eval, indicates they remain far less helpful than human experts. Although inference-time scaling…

Large Language Models (LLMs) struggle with long-context reasoning, not only due to the quadratic scaling of computational complexity with sequence length but also because of the scarcity and expense of annotating long-context data. There…