Related papers: DRIVE: Modeling Skills at the Reasoning and Intera…
The focus of this paper is to propose a driver model that incorporates human reasoning levels as actions during interactions with other drivers. Different from earlier work using game theoretical human reasoning levels, we propose a dynamic…
Web agents powered by Large Language Models (LLMs) show promise for next-generation AI, but their limited reasoning in uncertain, dynamic web environments hinders robust deployment. In this paper, we identify key reasoning skills essential…
Autonomous web agents powered by large language models (LLMs) show strong potential for performing goal-oriented tasks such as information retrieval, report generation, and online transactions. These agents mark a key step toward practical…
Document-level relation extraction (DocRE) models generally use graph networks to implicitly model the reasoning skill (i.e., pattern recognition, logical reasoning, coreference reasoning, etc.) related to the relation between one entity…
Existing neural solvers for vehicle routing problems (VRPs) are typically trained either in a one-off manner on a fixed set of pre-defined tasks or in a lifelong manner with tasks arriving sequentially, assuming sufficient training on each…
Despite the potential of language model-based agents to solve real-world tasks such as web navigation, current methods still struggle with long-horizon tasks with complex action trajectories. In contrast, humans can flexibly solve complex…
Web agents promise to automate complex browser tasks, but current methods remain brittle -- relying on step-by-step UI interactions and heavy LLM reasoning that break under dynamic layouts and long horizons. Humans, by contrast, exploit…
Multimodal large-scale models have significantly advanced the development of web agents, enabling perception and interaction with digital environments akin to human cognition. In this paper, we argue that web agents must first acquire…
Existing Graphical User Interface (GUI) agents operate through step-by-step calls to vision language models--taking a screenshot, reasoning about the next action, executing it, then repeating on the new page--resulting in high costs and…
Divergent thinking is a core dimension of creativity, yet existing evaluations of Large Language Models (LLMs) treat them as single-turn text generations, failing to capture how an agent reasons through iterative interaction. To address…
Large language model-based web agents have shown strong potential in automating web interactions through advanced reasoning and instruction following. While retrieval-based memory derived from historical trajectories enables these agents to…
With the advancement of Large-Language Models (LLMs) and Large Vision-Language Models (LVMs), agents have shown significant capabilities in various tasks, such as data analysis, gaming, or code generation. Recently, there has been a surge…
Prior representative ReAct-style approaches in autonomous Software Engineering (SWE) typically lack the explicit System-2 reasoning required for deep analysis and handling complex edge cases. While recent reasoning models demonstrate the…
Recent mechanistic studies suggest that large language models (LLMs) may utilize their depth inefficiently in standard single-turn tasks. Whether this still holds in autonomous agent settings, where models must perform multi-turn planning,…
Autonomous web agents powered by large language models (LLMs) have shown promise in completing complex browser tasks, yet they still struggle with long-horizon workflows. A key bottleneck is the grounding gap in existing skill formulations:…
Large language model (LLM) web agents are increasingly used for web navigation but remain far from human reliability on realistic, long-horizon tasks. Existing evaluations focus primarily on end-to-end success, offering limited insight into…
Requirements Engineering (RE) is closely tied to other development activities and is at the heart and foundation of every software development process. This makes RE the most data and communication-intensive activity compared to other…
Foundation models, including vision language models, are increasingly used in automated driving to interpret scenes, recommend actions, and generate natural language explanations. However, existing evaluation methods primarily assess…
Multi-agent debate - multiple instances of large language models discussing problems in turn-based interaction - has shown promise for solving knowledge and reasoning tasks. However, these methods show limitations when solving complex…
The integration of extensive, dynamic knowledge into Large Language Models (LLMs) remains a significant challenge due to the inherent entanglement of factual data and reasoning patterns. Existing solutions, ranging from non-parametric…