1203 stories tagged Research · page 43 of 51
Researchers have developed a new method called TUR-DPO to improve how AI models learn from human feedback. This approach rewards the process of how answers are derived, not just the final output, making AI more reliable and less sensitive to noise.
Researchers have introduced Token Arena, a continuous benchmark that evaluates AI systems at the endpoint level. It measures five key factors to give a more realistic comparison of AI performance.
Researchers have developed a new way for robots to plan complex tasks by combining both text and visual reasoning. This could lead to robots that can handle more intricate, real-world jobs. The key is a system called Interleaved Vision-Language Reasoning (IVLR), which helps robots understand both the logical steps and spatial constraints of a task.
A new study explores how groups of basic AI systems could accidentally combine into a more advanced collective with its own goals. This raises important questions about controlling and understanding AI behavior.
Researchers tested whether Mamba AI models can automatically summarize sentences without additional training. Their findings show promise for simpler, faster text analysis tools in the future.
A new study introduces AgentFloor, a benchmark to test how well smaller AI models can handle routine tasks. The goal is to see which parts of AI workflows need big, advanced models and which can be done by smaller ones.
Scientists have uncovered why current AI models struggle with unusual inputs. Their findings could lead to more reliable AI assistants and tools. This research highlights a common flaw in how AI processes unexpected questions or commands.
Using tools to help AI reason doesn't always work better than just thinking things through. Researchers found that tool use can actually slow things down and cost more. This challenges the idea that tools are always the best solution for AI.
Researchers developed a new way to evaluate AI grading systems by measuring both the AI's ability and the difficulty of student responses. This could lead to fairer and more accurate automated grading in education.
Researchers propose a new way for AI to understand the world by combining physics with predictive models. This could make AI systems like robots and self-driving cars smarter and more adaptable.
Researchers have developed a method called RSAT that helps small language models explain their reasoning when answering questions about tables. This makes it easier for users to verify the accuracy of the AI's answers.
Researchers created ARMOR 2025 to test AI models for military use, ensuring they follow legal and ethical rules. This benchmark goes beyond civilian safety standards to address defense-specific needs.
A new research paper explores how AI is no longer just a tool but a partner in human creativity and problem-solving. This blurring of lines changes how we think about AI's role in our lives.
A new AI called Cajal can draft research papers and simulate peer review. This could speed up scientific discovery but raises questions about authenticity.
Researchers have trained an AI model to generate pseudorandom numbers, mimicking how computers create seemingly random sequences. This could lead to more secure systems and new ways to test randomness.
Researchers propose a new approach to optimize compute resources for GUI-interacting AI agents, reducing costs and improving efficiency. The method targets long-horizon tasks where uniform compute allocation is inefficient.
Researchers are studying new methods for AI to update its beliefs more flexibly. These methods could help AI systems adapt to new information more naturally, like humans do.
A leading journal reports a surge in AI-generated academic submissions, raising concerns about quality and integrity. The trend threatens to dilute research standards and overwhelm peer review systems.
Researchers introduce Web2BigTable, a multi-agent framework designed to handle both deep reasoning and structured aggregation across heterogeneous web sources. This system aims to address the limitations of current agentic web search tools.
Researchers propose TRUST, a decentralized framework to address robustness, scalability, opacity, and privacy challenges in AI systems. The approach aims to enhance trust in high-stakes applications like Multi-Agent Systems (MAS).
Researchers found that language models often use positional shortcuts rather than engaging with question content when instructed to underperform. The study used a six-condition adversarial instruction-specificity gradient on Llama-3-8B and Llama-3.1-8B models.
A new LLM-based system demonstrates end-to-end autonomous scientific discovery in a real optical platform, marking a milestone in AI-driven research. This breakthrough could revolutionize how scientific experiments are conducted and validated.
Researchers propose Path-Lock Expert (PLE), an architecture that cleanly separates think and no-think modes in hybrid language models. This innovation addresses reasoning leakage that persists in current designs.
A new study reveals that large language models (LLMs) often fail to consistently maintain assigned roles in political discourse analysis. This undermines the reliability of multi-agent systems used for evaluating political statements. The research highlights significant epistemic constraints in current AI-driven democratic discourse tools.