Related papers: Revisiting Observation Reduction for Web Agents: C…
We present initial results of a forthcoming benchmark for evaluating LLM agents on white-collar tasks of economic value. We evaluate agents on real-world "messy" open-web research tasks of the type that are routine in finance and…
The development of LLM-based autonomous agents for end-to-end software development represents a significant paradigm shift in software engineering. However, the scientific evaluation of these systems is hampered by significant challenges,…
The application of large language models (LLMs) in the field of coding is evolving rapidly: from code assistants, to autonomous coding agents, and then to generating complete projects through natural language. Early LLM code benchmarks…
Existing web agent benchmarks have largely converged on short, single-site tasks that frontier models are approaching saturation on. However, real world web use consists of long-horizon, multi-site workflows. Common web navigation tasks,…
Recent progress in large language models (LLMs) has enabled the development of autonomous web agents capable of navigating and interacting with real websites. However, evaluating such agents remains challenging due to the instability and…
Large vision-language model (LVLM)-based web agents are emerging as powerful tools for automating complex online tasks. However, when deployed in real-world environments, they face serious security risks, motivating the design of security…
The adoption of large language models (LLMs) for structured information extraction from financial documents has accelerated rapidly, yet production deployments face fundamental architectural decisions with limited empirical guidance. We…
Several data warehouse and database providers have recently introduced extensions to SQL called AI Queries, enabling users to specify functions and conditions in SQL that are evaluated by LLMs, thereby broadening significantly the kinds of…
Feature selection aims to preprocess the target dataset, find an optimal and most streamlined feature subset, and enhance the downstream machine learning task. Among filter, wrapper, and embedded-based approaches, the reinforcement learning…
As language models (LMs) are used to build autonomous agents in real environments, ensuring their adversarial robustness becomes a critical challenge. Unlike chatbots, agents are compound systems with multiple components taking actions,…
Multi-turn agent systems based on Large Language Models (LLMs) have become increasingly popular for software engineering tasks. While LLM agents demonstrate promising effectiveness, the high computational cost of input tokens due to…
Event-based multimodal large language models (MLLMs) enable robust perception in high-speed and low-light scenarios, addressing key limitations of frame-based MLLMs. However, current event-based MLLMs often rely on dense image-like…
State-of-the-art multimodal web agents, powered by Multimodal Large Language Models (MLLMs), can autonomously execute many web tasks by processing user instructions and interacting with graphical user interfaces (GUIs). Current strategies…
LLM agents are increasingly deployed as executable systems that use tools, modify workspaces, and produce concrete artifacts. In such workflows, performance depends not only on the base model, but also on the harness: the system layer that…
Recent advances in browser-based LLM agents have shown promise for automating tasks ranging from simple form filling to hotel booking or online shopping. Current benchmarks measure agent performance in controlled environments, such as…
Efficiently leveraging of the capabilities of contemporary large language models (LLMs) is increasingly challenging, particularly when direct fine-tuning is expensive and often impractical. Existing training-free methods, including manually…
Most recent web agent research has focused on navigation and transaction tasks, with little emphasis on extracting structured data at scale. We present WebLists, a benchmark of 200 data-extraction tasks across four common business and…
Recent advances in code generation models have unlocked unprecedented opportunities for automating feature engineering, yet their adoption in real-world ML teams remains constrained by critical challenges: (i) the scarcity of datasets…
Multimodal large language models (MLLMs) have enabled LLM-based agents to directly interact with application user interfaces (UIs), enhancing agents' performance in complex tasks. However, these agents often suffer from high latency and low…
The predominant approach for training web navigation agents is to gather human demonstrations for a set of popular websites and hand-written tasks, but it is becoming clear that human data is an inefficient resource. We develop a pipeline…