936 stories tagged Research · page 5 of 39
Researchers developed a benchmark to evaluate AI summaries of clinical trials, ensuring they are accurate for doctors, patients, and insurers. This helps prevent misleading information in high-stakes medical decisions.
Researchers developed a way for AI models to improve themselves by only keeping the best versions of their own work. This could lead to better code generators that actually produce working programs. The method forces the AI to run its own code and only learn from successful attempts.
Researchers developed a new AI system that explains medical diagnoses using a structured argumentation model. This approach makes AI recommendations more transparent and trustworthy for doctors.
Researchers introduced CLIR-Bench, a new benchmark to test AI models on answering clinical questions from irregular, sparse medical data. This could lead to better AI tools for doctors and hospitals.
Researchers found that small tweaks in how questions are asked to AI models can drastically change their performance scores. This means current leaderboards might not be as reliable as they seem. The study introduces two new metrics to measure this effect, helping developers build more consistent AI systems.
A new study reveals that the format of messages between AI agents significantly impacts how accurately information is preserved across multiple hops. Structured messages help maintain fidelity, but the effect depends on the type of information and the agent's tier.
Bilibili has released a series of open small language models called Index-1.9B, trained on a massive dataset of Chinese and English tokens. These models are designed for various applications, from general use to specialized tasks like chat and character interaction.
New research proposes a system where small, rule-aligned language models and multi-agent self-correction generate and reconfigure industrial control policies from natural-language requirements. A digital twin validates actions before execution, addressing latency and compute constraints of large cloud models.
Researchers have created OpenProver, an open-source AI system for automated theorem proving that integrates with Lean 4, a formal verification tool used by mathematicians. It uses a Planner-Worker-Verifier architecture to decompose complex problems and verify solutions.
A new research paper challenges the idea that AI models can easily become misaligned and then realigned. The study finds these behaviors are highly sensitive to fine-tuning details, suggesting they may not be as robust as previously thought.
Researchers created a new test called Long-Horizon-Terminal-Bench to evaluate AI agents on complex, time-consuming tasks. Unlike previous tests, it measures progress over time, not just final results.
Researchers proposed a system to make AI's scientific reasoning transparent. This could help scientists audit AI-generated ideas like they would their own notes. The tool creates a structured record of AI hypotheses and experiments, making it easier to follow the AI's thought process.
Researchers have developed a way to catch AI chatbots when they make up false information. This is especially important for systems that need to provide accurate details, like recommending restaurants or booking appointments.
Researchers have developed a neuro-agentic control framework that combines AI planning with traditional security systems. This could make industrial IoT environments safer by reducing the risk of costly downtime and physical damage from cyberattacks.
Researchers created MedRealMM, a real-world benchmark for medical AI that includes real patient-doctor conversations and medical images. This could lead to more accurate and reliable AI tools for online healthcare consultations.
Researchers created a new test to measure AI's ability to connect clues scattered across long documents. This could improve how AI understands complex real-world information.
Researchers created LongMedBench, a new benchmark for AI medical assistants that simulates real-world patient care over time. Built from real EHR data (MIMIC-IV), it evaluates how well AI can handle ongoing treatments, repeated visits, and evolving health conditions.
Researchers have developed a new method called KV-PRM that makes multi-agent AI systems more efficient. This could lead to faster, more capable AI collaborations in complex scenarios. The technique reduces the computational cost of evaluating long interactions, making it practical for real-world applications.
Researchers introduced HALO, a method to enhance existing AI language models with minimal extra computation. It selectively refines responses, improving accuracy without wasting resources.
Researchers developed a new AI planning method called GATS that reduces computational costs and improves reliability by eliminating LLM calls during inference. It could make AI assistants more efficient at complex tasks.
Researchers introduced ARCANA, a multi-agent AI framework that solves ARC-AGI-2 tasks by iteratively perceiving, hypothesizing, executing, and reflecting. It operates under strict test-time and hardware constraints, using specialized agents to build scene graphs, propose DSL programs, verify candidates, and synthesize failure-driven feedback.
Researchers developed a new AI framework where multiple AI agents debate legal cases, improving accuracy by up to 8%. This approach could make legal analysis faster and more reliable for professionals and the public.
Researchers developed AgentKGV, an AI framework that improves the accuracy of knowledge graphs by verifying facts. This could make AI systems more reliable for everyday users. The system uses a two-stage training process to identify and correct errors in large-scale data sets.
A global survey of 3,000 researchers found that less than half use AI tools in their work. The report highlights significant gaps in adoption and training.