Related papers: Recovering Policy-Induced Errors: Benchmarking and…

Graphical User Interface (GUI) agents have demonstrated remarkable progress in automating complex user interface interactions through reinforcement learning. However, current approaches face a fundamental dilemma: offline RL enables stable…

Tool-use language agents are evaluated on benchmarks that assume clean inputs, unambiguous tool registries, and reliable APIs. Real deployments violate all these assumptions: user typos propagate into hallucinated tool names, a…

Large Language Models (LLMs) are increasingly used to generate natural-language explanations in recommender systems, acting as explanation agents that reason over user behavior histories. While prior work has focused on explanation fluency…

We present a simple and efficient method to leverage emerging text-to-image generative models in creating large-scale synthetic supervision for the task of damage assessment from aerial images. While significant recent advances have…

This technical report details a novel approach to combining reasoning and retrieval augmented generation (RAG) within a single, lean language model architecture. While existing RAG systems typically rely on large-scale models and external…

A widely adopted strategy for model enhancement is to use synthetic data generated by a stronger model for supervised fine-tuning (SFT). However, for emerging reasoning models like Qwen3-8B, this approach often fails to improve reasoning…

High-quality structured data with rich annotations are critical components in intelligent vehicle systems dealing with road scenes. However, data curation and annotation require intensive investments and yield low-diversity scenarios. The…

Training deep research agents requires long-horizon trajectories that interleave search, evidence aggregation, and multi-step reasoning. However, existing data collection pipelines typically rely on proprietary web APIs, making large-scale…

Context. Multiple automated techniques have been proposed and developed for mobile application GUI testing aiming to improve effectiveness, efficiency, and practicality. The effectiveness, efficiency, and practicality are 3 fundamental…

In this paper, we aim to enhance the robustness of Universal Information Extraction (UIE) by introducing a new benchmark dataset, a comprehensive evaluation, and a feasible solution. Existing robust benchmark datasets have two key…

Retrieval-augmented generation (RAG) enhances large language models (LLMs) by integrating external knowledge retrieved from a knowledge base. However, its effectiveness is fundamentally constrained by the reliability of both the retriever…

Generative AI systems achieve impressive performance on standard benchmarks yet fail to deliver real-world utility, a disconnect we identify across 28 deployment cases spanning education, healthcare, software engineering, and law. We argue…

Despite significant progress having been made in question answering on tabular data (Table QA), it's unclear whether, and to what extent existing Table QA models are robust to task-specific perturbations, e.g., replacing key question…

Benefiting from the development of deep learning, text-to-speech (TTS) techniques using clean speech have achieved significant performance improvements. The data collected from real scenes often contains noise and generally needs to be…

Agentic Test-Time Scaling (TTS) has delivered state-of-the-art (SOTA) performance on complex software engineering tasks such as code generation and bug fixing. However, its practical adoption remains limited due to significant computational…

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…

Modern AI agents execute real-world side effects through tool calls such as file operations, shell commands, HTTP requests, and database queries. A single unsafe action, including accidental deletion, credential exposure, or data…

AI agents that interact with graphical user interfaces (GUIs) require effective observation representations for reliable grounding. The accessibility tree is a commonly used text-based format that encodes UI element attributes, but it…

While Multimodal Large Language Models (MLLMs) have advanced GUI navigation agents, current approaches face limitations in cross-domain generalization and effective history utilization. We present a reasoning-enhanced framework that…

Research on self-evolving language agents has accelerated, drawing increasing attention to their ability to create, adapt, and maintain tools from task requirements. However, existing benchmarks predominantly rely on predefined…