Related papers: TermiGen: High-Fidelity Environment and Robust Tra…

As terminal agents scale to long-horizon, multi-turn workflows, a key bottleneck is not merely limited context length, but the accumulation of noisy terminal observations in the interaction history. Retaining raw observations preserves…

The scarcity of high-quality public log datasets has become a critical bottleneck in advancing log-based anomaly detection techniques. Current datasets exhibit three fundamental limitations: (1) incomplete event coverage, (2) artificial…

Large language models (LLMs) enable state-of-the-art semantic capabilities to be added to software systems such as semantic search of unstructured documents and text generation. However, these models are computationally expensive. At scale,…

Woven fabric materials are widely used in rendering applications, yet designing realistic examples typically involves multiple stages, requiring expertise in weaving principles and texture authoring. Recent advances have explored diffusion…

Recent breakthroughs in large multimodal models (LMMs), such as the impressive GPT-4o-Native, have demonstrated remarkable proficiency in following general-purpose instructions for image generation. However, current benchmarks often lack…

Realistic and diverse simulation scenarios with reactive and feasible agent behaviors can be used for validation and verification of self-driving system performance without relying on expensive and time-consuming real-world testing.…

The scarcity of data depicting dangerous situations presents a major obstacle to training AI systems for safety-critical applications, such as construction safety, where ethical and logistical barriers hinder real-world data collection.…

Large language models (LLMs) excel in many natural language tasks, yet they struggle with complex mathemat-ical problem-solving, particularly in symbolic reasoning and maintaining consistent output. This study evalu-ates 10 LLMs with 7 to 8…

Terminal agents have demonstrated strong potential for autonomous command-line execution, yet their training remains constrained by the scarcity of high-quality and diverse execution trajectories. Existing approaches mitigate this…

Safety-critical task planning in robotic systems remains challenging: classical planners suffer from poor scalability, Reinforcement Learning (RL)-based methods generalize poorly, and base Large Language Models (LLMs) cannot guarantee…

Synthetic data generation has emerged as an invaluable solution in scenarios where real-world data collection and usage are limited by cost and scarcity. Large language models (LLMs) have demonstrated remarkable capabilities in producing…

Tool-calling agents are increasingly deployed in real-world customer-facing workflows. Yet most studies on tool-calling agents focus on idealized settings with general, fixed, and well-specified tasks. In real-world applications, user…

Large language models (LLMs) excel at many NLP tasks but struggle to sustain long-term interactions due to limited attention over extended dialogue histories. Retrieval-augmented generation (RAG) mitigates this issue but lacks reliable…

LLMs are vulnerable to hallucinations, and thus their outputs generally require laborious human verification for high-stakes applications. To this end, we propose symbolically grounded generation (SymGen) as a simple approach for enabling…

Large language models (LLMs) have shown impressive promise in code generation, yet their progress remains limited by the shortage of large-scale datasets that are both diverse and well-aligned with human reasoning. Most existing resources…

Terminal-agent benchmarks have become a primary signal for measuring the coding and system-administration capabilities of large language models. As the market for evaluation environments grows, so does the pressure to ship tasks quickly,…

LLMs have been shown to perform well in machine translation (MT) with the use of in-context learning (ICL), rivaling supervised models when translating into high-resource languages (HRLs). However, they lag behind when translating into…

Large Language Models (LLMs) have demonstrated remarkable capabilities across various domains, with code generation emerging as a key area of focus. While numerous benchmarks have been proposed to evaluate their code generation abilities,…

We introduce OSVBench, a new benchmark for evaluating Large Language Models (LLMs) on the task of generating complete formal specifications for verifying the functional correctness of operating system kernels. This benchmark is built upon a…

Despite their remarkable capabilities, Large Language Models (LLMs) struggle to effectively leverage historical interaction information in dynamic and complex environments. Memory systems enable LLMs to move beyond stateless interactions by…