相关论文: Synthetic Computers at Scale for Long-Horizon Prod…

Large language models (LLMs) have shown remarkable advancements in enabling language agents to tackle simple tasks. However, applying them for complex, multi-step, long-horizon tasks remains a challenge. Recent work have found success by…

We propose a data-driven approach for context-aware person image generation. Specifically, we attempt to generate a person image such that the synthesized instance can blend into a complex scene. In our method, the position, scale, and…

Skills are a promising way to improve LLM agent capabilities without retraining, while keeping the added procedure reusable and controllable. However, high-quality skills are still largely written by hand. We introduce SkillGen, a…

Computer use agents (CUAs) can operate real-world digital interfaces but remain difficult to train due to the high cost of graphical user interface (GUI) interaction and the scarcity of high-quality trajectory data. Existing datasets rely…

Edge computing breaks with traditional autoscaling due to strict resource constraints, thus, motivating more flexible scaling behaviors using multiple elasticity dimensions. This work introduces an agent-based autoscaling framework that…

Successfully solving long-horizon manipulation tasks remains a fundamental challenge. These tasks involve extended action sequences and complex object interactions, presenting a critical gap between high-level symbolic planning and…

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…

Deep research agents extend the role of search engines from retrieving keyword-matched pages to synthesizing knowledge, fundamentally changing how humans interact with information. However, frontier systems remain proprietary, while…

One of the key challenges for multi-agent learning is scalability. In this paper, we introduce a technique for speeding up multi-agent learning by exploiting concurrent and incremental experience sharing. This solution adaptively identifies…

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…

Tool-augmented large language models (LLMs), hereafter LLM agents, leverage external tools to solve diverse tasks and interface with the real world. However, current training practices largely rely on supervised fine-tuning (SFT) over…

Evaluating AI systems that interact with humans requires understanding their behavior across diverse user populations, but collecting representative human data is often expensive or infeasible, particularly for novel technologies or…

Scientific reasoning inherently demands integrating sophisticated toolkits to navigate domain-specific knowledge. Yet, current benchmarks largely overlook agents' ability to orchestrate tools for such rigorous workflows. To bridge this gap,…

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…

Synthesis is the automated construction of a system from its specification. The system has to satisfy its specification in all possible environments. Modern systems often interact with other systems, or agents. Many times these agents have…

Test-time scaling has become a powerful way to improve large language models. However, existing methods are best suited to short, bounded outputs that can be directly compared, ranked or refined. Long-horizon coding agents violate this…

Autonomous agents operating in the real world must interact continuously with existing physical and semantic infrastructure, track delayed consequences, and verify outcomes over time. Everyday environments are rich in tangible control…

Recent advancements in generative models have unlocked the capabilities to render photo-realistic data in a controllable fashion. Trained on the real data, these generative models are capable of producing realistic samples with minimal to…

Quality control of assembly processes is essential in manufacturing to ensure not only the quality of individual components but also their proper integration into the final product. To assist in this matter, automated assembly control using…

Large language model (LLM)-based agents are increasingly used to solve complex tasks involving tool use, such as web browsing, code execution, and data analysis. However, current evaluation benchmarks do not adequately assess their ability…