Related papers: ORBIT: Guided Agentic Orchestration for Autonomous…
We aim to investigate the performance of current OCR systems on low resource languages and low resource scripts. We introduce and make publicly available a novel benchmark, OCR4MT, consisting of real and synthetic data, enriched with noise,…
Task scheduling is critical for embodied AI, enabling agents to follow natural language instructions and execute actions efficiently in 3D physical worlds. However, existing datasets often simplify task planning by ignoring operations…
Rust is a modern programming language that guarantees memory safety and the absence of data races with a strong type system. We present RustyDL, a program logic for Rust, as a foundation for an auto-interactive, deductive verification tool…
Over the years, automatic MT metrics have hillclimbed benchmarks and presented strong and sometimes human-level agreement with human ratings. Yet they remain black-box, offering little insight into their decision-making and often failing…
The development of high-quality datasets is crucial for benchmarking and advancing research in Graphical User Interface (GUI) agents. Despite their importance, existing datasets are often constructed under idealized conditions, overlooking…
Open-vocabulary object detection (OVOD) enables novel category detection via vision-language alignment, but massive model sizes hinder deployment on resource-constrained devices. While quantization offers practical compression, we reveal…
Recent work has shown that inference-time reasoning and reflection can improve text-to-image generation without retraining. However, existing approaches often rely on implicit, holistic critiques or unconstrained prompt rewrites, making…
Multi-agent large language model (LLM) systems have shown strong potential in complex reasoning and collaborative decision-making tasks. However, most existing coordination schemes rely on static or full-context routing strategies, which…
Large language models (LLMs) have enabled powerful advances in natural language understanding and generation. Yet their application to complex, real-world scientific workflows remain limited by challenges in memory, planning, and tool…
Large Language Models (LLMs) have improved programming efficiency, but their performance degrades significantly as requirements scale; when faced with multi-modal documents containing hundreds of scenarios, LLMs often produce incorrect…
The surge in scientific publications challenges traditional review methods, demanding tools that integrate structured metadata with full-text analysis. Hybrid Retrieval Augmented Generation (RAG) systems, combining graph queries with vector…
Foundation models that incorporate language, vision, and more recently actions have revolutionized the ability to harness internet scale data to reason about useful tasks. However, one of the key challenges of training embodied foundation…
Large language models (LLMs) open new possibilities for agentic control in Open RAN, allowing operators to express intents in natural language while delegating low-level execution to autonomous agents. We present A1gent, an agentic RAN…
Learned classifiers deployed in agentic pipelines face a fundamental reliability problem: predictions are probabilistic inferences, not verified conclusions, and acting on them without grounding in observable evidence leads to compounding…
Attribute-controlled translation (ACT) is a subtask of machine translation that involves controlling stylistic or linguistic attributes (like formality and gender) of translation outputs. While ACT has garnered attention in recent years due…
Developing agents that can follow multimodal instructions remains a fundamental challenge in robotics and AI. Although large-scale pre-training on unlabeled datasets (no language instruction) has enabled agents to learn diverse behaviors,…
Recent vision-language models have strong perceptual ability but their implicit reasoning is hard to explain and easily generates hallucinations on complex queries. Compositional methods improve interpretability, but most rely on a single…
Modern code intelligence agents operate in contexts exceeding 1 million tokens--far beyond the scale where humans manually locate relevant files. Yet agents consistently fail to discover architecturally critical files when solving…
Autonomous agent frameworks still struggle to reconcile long-term experiential learning with real-time, context-sensitive decision-making. In practice, this gap appears as static cognition, rigid workflow dependence, and inefficient context…
This paper studies the black-box optimization task which aims to find the maxima of a black-box function using a static set of its observed input-output pairs. This is often achieved via learning and optimizing a surrogate function with…