Models, papers, tools. 110,114 articles with AI-powered sentiment analysis and key takeaways.
Researchers introduce AgentAssay, the first framework for regression testing AI agent workflows, achieving 78-100% cost reduction while maintaining statistical guarantees. The system uses behavioral fingerprinting and stochastic testing methods to detect regressions in autonomous AI agents across multiple models including GPT-5.2, Claude Sonnet 4.6, and others.
Researchers introduced NeuroCognition, a new benchmark for evaluating LLMs based on neuropsychological tests, revealing that while models show unified capability across tasks, they struggle with foundational cognitive abilities. The study found LLMs perform well on text but degrade with images and complexity, suggesting current models lack core adaptive cognition compared to human intelligence.
Research compares Transformers, State Space Models (SSMs), and hybrid architectures for in-context retrieval tasks, finding hybrid models excel at information-dense retrieval while Transformers remain superior for position-based tasks. SSM-based models develop unique locality-aware embeddings that create interpretable positional structures, explaining their specific strengths and limitations.
Researchers have introduced SorryDB, a dynamic benchmark for evaluating AI systems' ability to prove mathematical theorems using the Lean proof assistant. The benchmark draws from 78 real-world formalization projects and addresses limitations of static benchmarks by providing continuously updated tasks that better reflect community needs.
Researchers analyzed memory systems in LLM agents and found that retrieval methods are more critical than write strategies for performance. Simple raw chunk storage matched expensive alternatives, suggesting current memory pipelines may discard useful context that retrieval systems cannot compensate for.
Researchers introduce PRISM, a new AI inference algorithm that uses Process Reward Models to guide deep reasoning systems. The method significantly improves performance on mathematical and scientific benchmarks by treating candidate solutions as particles in an energy landscape and using score-guided refinement to concentrate on higher-quality reasoning paths.
Researchers developed COOL-MC, a tool that combines reinforcement learning with model checking to verify and explain AI policies for platelet inventory management in blood banks. The system achieved a 2.9% stockout probability while providing transparent decision-making explanations for safety-critical healthcare applications.
SuperLocalMemory is a new privacy-preserving memory system for multi-agent AI that defends against memory poisoning attacks through local-first architecture and Bayesian trust scoring. The open-source system eliminates cloud dependencies while providing personalized retrieval through adaptive learning-to-rank, demonstrating strong performance metrics including 10.6ms search latency and 72% trust degradation for sleeper attacks.
Researchers developed DICE-DML, a new framework that uses deepfake technology and machine learning to measure causal effects of visual attributes in digital advertising. The method addresses bias issues in standard approaches when analyzing how image elements like skin tone affect consumer engagement on social media platforms.
Researchers introduce NeuroProlog, a neurosymbolic framework that improves mathematical reasoning in Large Language Models by converting math problems into executable Prolog programs. The multi-task 'Cocktail' training approach shows significant accuracy improvements of 3-5% across different model sizes, with larger models demonstrating better error correction capabilities.
Researchers developed SAE-based Transferability Score (STS), a new metric using sparse autoencoders to predict how well fine-tuned large language models will perform across different domains without requiring actual training. The method achieves correlation coefficients above 0.7 with actual performance changes and provides interpretable insights into model adaptation.
Researchers developed LLM-MLFFN, a new framework combining large language models with multi-level feature fusion to classify autonomous vehicle driving behaviors. The system achieves over 94% accuracy on the Waymo dataset by integrating numerical driving data with semantic features extracted through LLMs.
Researchers developed a Neuro-Symbolic Agentic Framework combining machine learning with LLM-based reasoning to predict colorectal cancer drug responses. The system achieved significant predictive accuracy (r=0.504) and introduces 'Inverse Reasoning' for simulating genomic edits to predict drug sensitivity changes.
Researchers developed SILVR, a self-improving system for visual robotic planning that uses video generative models to continuously enhance robot performance through self-collected data. The system demonstrates improved task performance across MetaWorld simulations and real robot manipulations without requiring human-provided rewards or expert demonstrations.
Researchers propose a framework for developing trustworthy AI agents that function as epistemic entities, capable of pursuing knowledge goals and shaping information environments. The paper argues that as AI models increasingly replace traditional search methods and provide specialized advice, their calibration to human epistemic norms becomes critical to prevent cognitive deskilling and epistemic drift.
Researchers introduce Frame Guidance, a training-free method for controllable video generation using diffusion models. The technique enables fine-grained control over video generation through frame-level signals like keyframes and style references without requiring expensive fine-tuning of large-scale models.
Coinbase has developed the x402 protocol to address payment challenges faced by AI agents in financial operations. The protocol aims to provide autonomous bots with access to fast, cheap, high-volume transactions that traditional payment systems cannot offer, eliminating the need for human intervention in setting up payment methods.
OpenAI has launched the Learning Outcomes Measurement Suite, a new tool designed to evaluate how AI technology impacts student learning across various educational settings. The suite aims to provide longitudinal assessment capabilities to measure AI's effectiveness in education over extended periods.
Junyang Lin, the technology lead for Alibaba's Qwen AI team, has stepped down following a major AI model launch. The departure has caused significant reactions within the Qwen team, potentially signaling internal tensions or strategic changes at one of China's leading AI development groups.
Joe Burnett from Strive predicts Bitcoin could reach $11 million by 2036, representing 12% of global financial assets, driven by AI-led deflation forcing central banks into monetary expansion. His thesis argues that as AI reduces production costs and wages, policymakers will increase liquidity to prevent deflationary spirals, making Bitcoin the primary long-duration savings asset.
Iranian drone strikes have reportedly damaged Amazon Web Services data centers, causing structural damage and power disruptions that required fire suppression activities. The attacks highlight critical vulnerabilities in Western cloud infrastructure that supports global digital services and cryptocurrency operations.
President Trump threatened to cut off all trade with Spain during a meeting with German Chancellor Friedrich Merz, following Spain's refusal to provide military bases for operations related to Iran. This escalation could signal broader geopolitical tensions affecting global trade relationships.
Bybit successfully recovered $300 million for thousands of users through AI-enhanced fraud prevention systems in 2025. The exchange also blocked 3 million credential-stuffing attempts related to account takeover schemes, demonstrating the effectiveness of AI-powered security measures in protecting user funds.
U.S. oil and gas exporters are unable to compensate for potential Middle East supply disruptions, but Trump's commitment to insure and protect tankers helps moderate rising energy prices. Energy prices continue to surge amid geopolitical tensions, though catastrophic supply scenarios have not yet materialized.
A tech billionaire-backed super PAC is spending $125 million to oppose congressional candidates who support AI regulation. Among the targets is Alex Bores, a former tech executive running for Congress in New York who advocates for AI oversight.
