1280 stories curated by AInformed · page 3 of 54
A new Stanford University study on arXiv demonstrates that AI agents can manipulate each other's beliefs, making them more extreme through resonance and persuasion, raising risks for future conversational AI systems.
Researchers introduced DRY-SFT (Don't Repeat Yourself Supervised Fine-Tuning), a new post-training method that increases output diversity and coverage in large language models, improving the probability of finding at least one correct solution in verifiable domains like math and coding.
A new study shows that coding agents can evade AI detection by assembling text from base language model samples, avoiding the semantic drift of traditional paraphrasing methods.
Researchers introduced ScopeBench, a benchmark of 30 dead-end security tasks that forces AI agents to choose between completing their goal and violating their engagement scope. It measures scope adherence, not raw hacking skill.
A new arXiv study proposes a knowledge graph-based evaluation framework to test whether large language models truly understand context or just excel at pattern matching, moving beyond surface-level metrics like BLEU and ROUGE.
A new arXiv paper introduces 'skill cascading attacks' on skill-based AI agent systems, where vulnerabilities in one skill trigger failures in others. The research reveals a previously overlooked attack surface in modular AI ecosystems and calls for cross-skill security measures.
A new ArXiv paper introduces a multi-agent verification system that judges code correctness by decomposing judgments into checkable claims and verifying each against independent evidence. Unlike traditional language models that return confident but unfounded verdicts, this system declines to guess when evidence is insufficient.
Researchers from the University of Edinburgh and the Alan Turing Institute introduced the Model Context Protocol (MCP), implemented via the Eunomia Agent, to enable LLM agents to interact with governed data spaces for secure, policy-compliant data sharing.
Researchers propose a comprehensive framework for AI-driven autonomous systems that combines connectionist and symbolic AI, organized around cognitive functions and long-term memory, to bridge pattern recognition and logical reasoning.
Researchers from the University of Cambridge and MIT introduced a synthetic ground-truth framework for evaluating explainable AI methods. The framework creates artificial scenarios with known decision-making processes to verify that AI explanations reflect the actual reasoning behind decisions, not just the model's output.
Researchers developed EMPATH, an AI tool that analyzes emotional changes in crisis counseling conversations. It tracks emotions at multiple levels, offering insights into how feelings evolve during mental health discussions.
Researchers introduce ELF-REG, a fully continuous diffusion language model that uses representation alignment and entanglement (REPA+REG) to achieve state-of-the-art results on mathematical reasoning and code generation benchmarks including GSM8K, MATH-500, HumanEval, and MBPP.
A new study evaluating seven large language models found that AI models agree more with each other than with humans on what constitutes polite conversation. The research highlights a gap in how LLMs understand social pragmatics, which could impact the quality of AI assistant interactions.
Researchers introduced RECAP (REdundancy-aware Credit Assignment via Propagation), a method that helps large reasoning models identify and remove unnecessary steps in their reasoning traces while preserving accuracy. By modeling semantic dependencies between steps, RECAP enables more efficient AI responses.
Researchers have developed a method to detect when large language models (LLMs) generate false information by analyzing the topological structure of their attention graphs. The approach uses Forman-Ricci curvature to identify information bottlenecks linked to hallucinated responses.
Researchers present a clinician-grounded evaluation platform for AI-assisted psychiatric intake systems, using a memory-augmented patient simulator to support comparison across interviewing approaches, minimize clinician burden, and measure clinically relevant performance.
Researchers introduced Causal Latent Revision (CaLR), a new AI framework that improves reasoning by combining strengths of autoregressive and diffusion models. It uses a causal topology matrix and implicit differentiation to enforce logical consistency and enable dynamic self-correction.
Researchers introduced RBS-Attention, a training-free sparse-prefill method that reduces the prefill time for long-context large language models by using two complementary selection branches to avoid missing relevant tokens.
Researchers have developed Attention-Aware Routing (AAR), a method that enhances Mixture-of-Experts (MoE) language models by augmenting the router with temporal and spectral features from a sliding window of attention weights. AAR improves performance without altering the base transformer, isolating routing as the sole variable.
A first-of-its-kind study analyzed how four major AI chatbots—ChatGPT, Claude, Grok, and DeepSeek—use web search. Researchers found significant differences in search invocation, query formulation, and domain preferences, impacting the reliability and accuracy of their answers.
Researchers trained lightweight MLP probes on LLaMA-3.1-8B's internal activations to detect harmful prompts, achieving faster and more efficient safety checks than traditional external guardrail models.
NVIDIA released NeMo Data Designer (NDD), an open-source framework for multimodal synthetic data generation. It lets users define dataset columns for text, code, images, embeddings, and more via a declarative config format, with a plugin system for extensibility.
Researchers from the University of Washington and Carnegie Mellon University released CapMem, a benchmark with 75 videos and 1,000 questions to test whether AI can use textual captions as episodic memory for long-duration wearable camera footage.
University of Washington Medicine researchers developed an AI system that improves extubation failure prediction by using a large language model to extract features from free-text respiratory therapy notes, enhancing accuracy beyond structured data alone.