Related papers: GTA-2: Benchmarking General Tool Agents from Atomi…
The paradigm of agentic AI is shifting from engineered complex workflows to post-training native models. However, existing agents are typically confined to static, predefined action spaces--such as exclusively using APIs, GUI events, or…
Large language models are redefining software engineering by implementing AI-powered techniques throughout the whole software development process, including requirement gathering, software architecture, code generation, testing, and…
Robot learning approaches such as behavior cloning and reinforcement learning have shown great promise in synthesizing robot skills from human demonstrations in specific environments. However, these approaches often require task-specific…
Large language model (LLM) agents are moving beyond prompting alone. ChatGPT marked the rise of general-purpose LLM assistants, DeepSeek showed that on-policy reinforcement learning with verifiable rewards can improve reasoning and tool…
As LLMs are increasingly deployed as agents, agentic reasoning - the ability to combine tool use, especially search, and reasoning - becomes a critical skill. However, it is hard to disentangle agentic reasoning when evaluated in complex…
As web agents rapidly evolve, an increasing body of work has moved beyond conventional atomic browser interactions and explored tool use as a higher-level action paradigm. Although prior studies have shown the promise of tools, their…
With the growing adoption of Large Language Models (LLMs) in automating complex, multi-agent workflows, organizations face mounting risks from errors, emergent behaviors, and systemic failures that current evaluation methods fail to…
Office automation significantly enhances human productivity by automatically finishing routine tasks in the workflow. Beyond the basic information extraction studied in much of the prior document AI literature, the office automation…
Large language model based multi-agent systems have demonstrated significant potential in social simulation and complex task resolution domains. However, current frameworks face critical challenges in system architecture design,…
LLM agents increasingly act on external systems, yet tool effects are immediate. Under failures, speculation, or contention, losing branches can leak unintended side effects with no safe rollback. We introduce Atomix, a runtime that…
Despite their broad applicability, transformer-based models still fall short in System~2 reasoning, lacking the generality and adaptivity needed for human--AI alignment. We examine weaknesses on ARC-AGI tasks, revealing gaps in…
The integration of Large Language Models (LLMs) into Geographic Information Systems (GIS) marks a paradigm shift toward autonomous spatial analysis. However, evaluating these LLM-based agents remains challenging due to the complex,…
The rise of agentic AI systems, where agents collaborate to perform diverse tasks, poses new challenges with observing, analyzing and optimizing their behavior. Traditional evaluation and benchmarking approaches struggle to handle the…
The integration of tool use into large language models (LLMs) enables agentic systems with real-world impact. In the meantime, unlike standalone LLMs, compromised agents can execute malicious workflows with more consequential impact,…
The rapid advancements in artificial intelligence (AI) are catalyzing transformative changes in atomic modeling, simulation, and design. AI-driven potential energy models have demonstrated the capability to conduct large-scale,…
Computer-use agents provide a promising path toward general software automation because they can interact directly with arbitrary graphical user interfaces instead of relying on brittle, application-specific integrations. Despite recent…
Modern information systems require autonomous agents capable of navigating complex workflows, yet current methodologies often struggle with the transition from structured metadata parsing to general environmental perception. While the…
Generative AI is being leveraged to solve a variety of computer-use tasks involving desktop applications. State-of-the-art systems have focused solely on improving accuracy on leading benchmarks. However, these systems are practically…
Large language models (LLMs) and agentic systems have recently demonstrated potential for automating scientific workflows, including atomistic simulations. However, their deployment in high-performance computing (HPC) environments remains…
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…