#Research & Development

Articles (9)

• 🇺🇸 The Art of Building Verifiers for Computer Use Agents — 09/04/2026 [USA]

  arXiv:2604.06240v1 Announce Type: cross Abstract: Verifying the success of computer use agent (CUA) trajectories is a critical challenge: without reliable verification, neither evaluation nor trainin...

  Related: #Artificial Intelligence, #Software Verification
• 🇺🇸 Evaluating LLM-Based 0-to-1 Software Generation in End-to-End CLI Tool Scenarios — 09/04/2026 [USA]

  arXiv:2604.06742v1 Announce Type: cross Abstract: Large Language Models (LLMs) are driving a shift towards intent-driven development, where agents build complete software from scratch. However, exist...

  Related: #Artificial Intelligence, #Software Engineering
• 🇺🇸 WRAP++: Web discoveRy Amplified Pretraining — 09/04/2026 [USA]

  arXiv:2604.06829v1 Announce Type: cross Abstract: Synthetic data rephrasing has emerged as a powerful technique for enhancing knowledge acquisition during large language model (LLM) pretraining. Howe...

  Related: #Artificial Intelligence, #Machine Learning
• 🇺🇸 MedDialBench: Benchmarking LLM Diagnostic Robustness under Parametric Adversarial Patient Behaviors — 09/04/2026 [USA]

  arXiv:2604.06846v1 Announce Type: cross Abstract: Interactive medical dialogue benchmarks have shown that LLM diagnostic accuracy degrades significantly when interacting with non-cooperative patients...

  Related: #Artificial Intelligence, #Healthcare Technology
• 🇺🇸 TeamLLM: A Human-Like Team-Oriented Collaboration Framework for Multi-Step Contextualized Tasks — 09/04/2026 [USA]

  arXiv:2604.06765v1 Announce Type: cross Abstract: Recently, multi-Large Language Model (LLM) frameworks have been proposed to solve contextualized tasks. However, these frameworks do not explicitly e...

  Related: #Artificial Intelligence, #LLM Collaboration
• 🇺🇸 SHAPE: Stage-aware Hierarchical Advantage via Potential Estimation for LLM Reasoning — 09/04/2026 [USA]

  arXiv:2604.06636v1 Announce Type: cross Abstract: Process supervision has emerged as a promising approach for enhancing LLM reasoning, yet existing methods fail to distinguish meaningful progress fro...

  Related: #Artificial Intelligence, #Machine Learning
• 🇺🇸 CubeGraph: Efficient Retrieval-Augmented Generation for Spatial and Temporal Data — 09/04/2026 [USA]

  arXiv:2604.06616v1 Announce Type: cross Abstract: Hybrid queries combining high-dimensional vector similarity search with spatio-temporal filters are increasingly critical for modern retrieval-augmen...

  Related: #Artificial Intelligence, #Data Systems
• 🇺🇸 Neural Computers — 09/04/2026 [USA]

  arXiv:2604.06425v1 Announce Type: cross Abstract: We propose a new frontier: Neural Computers (NCs) -- an emerging machine form that unifies computation, memory, and I/O in a learned runtime state. U...

  Related: #Artificial Intelligence, #Computer Architecture
• 🇺🇸 WebSP-Eval: Evaluating Web Agents on Website Security and Privacy Tasks — 09/04/2026 [USA]

  arXiv:2604.06367v1 Announce Type: cross Abstract: Web agents automate browser tasks, ranging from simple form completion to complex workflows like ordering groceries. While current benchmarks evaluat...

  Related: #Artificial Intelligence, #Cybersecurity