Related papers: HATS: Hardness-Aware Trajectory Synthesis for GUI …
We introduce AgentSynth, a scalable and cost-efficient pipeline for automatically synthesizing high-quality tasks and trajectory datasets for generalist computer-use agents. Leveraging information asymmetry, AgentSynth constructs subtasks…
Industry practitioners and academic researchers regularly use multi-agent systems to accelerate their work, but the applications through which users operate these systems do not provide a simple, unified mechanism for scalably managing…
Although recent tool-augmented benchmarks involve complex requests, evaluation remains limited to answer matching, neglecting critical trajectory aspects like efficiency, hallucination, and adaptivity. The most straightforward method for…
Automatic Text Summarization (ATS), utilizing Natural Language Processing (NLP) algorithms, aims to create concise and accurate summaries, thereby significantly reducing the human effort required in processing large volumes of text. ATS has…
Existing work on vision and language navigation mainly relies on navigation-related losses to establish the connection between vision and language modalities, neglecting aspects of helping the navigation agent build a deep understanding of…
Hallucination, the generation of factually incorrect content, is a growing challenge in Large Language Models (LLMs). Existing detection and mitigation methods are often isolated and insufficient for domain-specific needs, lacking a…
In this paper, we investigate the impact of high-level semantics (evaluation of the environment) on Human-Robot Teams (HRT) and Human-Robot Interaction (HRI) in the context of mobile robot deployments. Although semantics has been widely…
Accurate perception of object hardness is essential for safe and dexterous contact-rich robotic manipulation. Here, we present TactEx, an explainable multimodal robotic interaction framework that unifies vision, touch, and language for…
Recent advancements in Large Language Models (LLMs) have led to significant breakthroughs in various natural language processing tasks. However, generating factually consistent responses in knowledge-intensive scenarios remains a challenge…
Large Language models (LLMs) have exhibited remarkable abilities in understanding complex texts, offering a promising path towards human-like translation performance. However, this study reveals the misalignment between the…
How can "weak teacher models" such as average human annotators or existing AI systems, effectively supervise LLMs to improve performance on hard reasoning tasks, especially those that challenge and requires expertise or daily practice from…
Machine translation has long been a central task in natural language processing. With the rapid advancement of large language models (LLMs), there has been remarkable progress in translation quality. However, fully realizing the translation…
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…
Agentic systems operating over large tool ecosystems must plan and execute long-horizon workflows under weak or non-verifiable supervision. While frontier models mitigate these challenges through scale and large context budgets, small…
Recent advancements in Large Language Models (LLMs) have sparked interest in their application to Static Application Security Testing (SAST), primarily due to their superior contextual reasoning capabilities compared to traditional symbolic…
Reliable real-time trajectory generation is essential for future autonomous spacecraft. While recent progress in nonconvex guidance and control is paving the way for onboard autonomous trajectory optimization, these methods still rely on…
Recent work on activation and latent steering has demonstrated that modifying internal representations can effectively guide large language models (LLMs) toward improved reasoning and efficiency without additional training. However, most…
Nowadays, large-scale foundation models are being increasingly integrated into numerous safety-critical applications, including human-autonomy teaming (HAT) within transportation, medical, and defence domains. Consequently, the inherent…
The fundamental challenge of using Large Language Models (LLMs) for reliable, enterprise-grade analytics, such as sentiment prediction, is the conflict between the LLMs' inherent stochasticity (generative, non-deterministic nature) and the…
Recent advances in large language models (LLMs) have sparked growing interest in building fully autonomous agents. However, fully autonomous LLM-based agents still face significant challenges, including limited reliability due to…