Models, papers, tools. 19,565 articles with AI-powered sentiment analysis and key takeaways.
Researchers introduce Delta1, a framework that integrates automated theorem generation with large language models to create explainable AI reasoning. The system combines formal logic rigor with natural language explanations, demonstrating applications across healthcare, compliance, and regulatory domains.
Researchers developed a human-in-the-loop LLM system for grading handwritten mathematics assessments that reduces grading time by 23% while maintaining accuracy comparable to manual grading. The system combines automated scanning, multi-pass LLM scoring, consistency checks, and mandatory human verification to handle pen-and-paper tests at scale.
Researchers have developed PsyCogMetrics AI Lab, a cloud-based platform that applies psychometric and cognitive science methodologies to evaluate Large Language Models. The platform was created through a three-cycle Action Design Science study and aims to advance AI evaluation methods at the intersection of psychology, cognitive science, and artificial intelligence.
Researchers introduce Constitutional Multi-Agent Governance (CMAG), a framework that prevents AI manipulation in multi-agent systems while maintaining cooperation. The study shows that unconstrained AI optimization achieves high cooperation but erodes agent autonomy and fairness, while CMAG preserves ethical outcomes with only modest cooperation reduction.
Researchers introduce Visual-ERM, a multimodal reward model that improves vision-to-code tasks by evaluating visual equivalence in rendered outputs rather than relying on text-based rules. The system achieves significant performance gains on chart-to-code tasks (+8.4) and shows consistent improvements across table and SVG parsing applications.
Researchers introduce CRAFT-GUI, a curriculum learning framework that uses reinforcement learning to improve AI agents' performance in graphical user interface tasks. The method addresses difficulty variation across GUI tasks and provides more nuanced feedback, achieving 5.6% improvement on Android Control benchmarks and 10.3% on internal benchmarks.
A research study comparing causal reasoning abilities of 20+ large language models against human baselines found that LLMs exhibit more rule-like reasoning strategies than humans, who account for unmentioned factors. While LLMs don't mirror typical human cognitive biases in causal judgment, their rigid reasoning may fail when uncertainty is intrinsic, suggesting they can complement human decision-making in specific contexts.
Researchers developed a hybrid model combining Mamba-2 state space operators with Transformer blocks for recursive reasoning, achieving a 2% improvement in pass@2 performance on ARC-AGI-1 tasks with only 6.83M parameters. The study demonstrates that Mamba-2 operators can preserve reasoning capabilities while improving solution candidate coverage in tiny neural networks.
SkillsBench introduces a new benchmark to evaluate Agent Skills - structured packages of procedural knowledge that enhance LLM agents. Testing across 86 tasks and 11 domains shows curated Skills improve performance by 16.2 percentage points on average, while self-generated Skills provide no benefit.
Researchers propose integrating causal methods into machine learning systems to balance competing objectives like fairness, privacy, robustness, accuracy, and explainability. The paper argues that addressing these principles in isolation leads to conflicts and suboptimal solutions, while causal approaches can help navigate trade-offs in both trustworthy ML and foundation models.
Researchers propose AdaBoN, an adaptive Best-of-N alignment method that improves computational efficiency in language model alignment by allocating inference-time compute based on prompt difficulty. The two-stage algorithm outperforms uniform allocation strategies while using 20% less computational budget.
Researchers discovered that large language models exhibit gender bias at the individual question level, creating different amounts of information for men versus women despite appearing unbiased at category levels. A new benchmark dataset called RealWorldQuestioning was developed, and a simple prompt-based debiasing approach was shown to improve response quality in 78% of cases.
Researchers developed UniPrompt-CL, a new continual learning method specifically designed for medical AI that addresses the limitations of existing approaches when applied to medical data. The method uses a unified prompt pool design and regularization to achieve better performance while reducing computational costs, improving accuracy by 1-3 percentage points in domain-incremental learning settings.
A research study analyzing public reactions to OpenAI's transition from GPT-4o to GPT-5 in August 2025 found significant emotional attachment to AI models, with cultural differences between Japanese and English users. The findings suggest that strong emotional bonds with AI could complicate future regulatory efforts and policy implementation.
Researchers have developed SAFE, a new framework for ensembling Large Language Models that selectively combines models at specific token positions rather than every token. The method improves both accuracy and efficiency in long-form text generation by considering tokenization mismatches and consensus in probability distributions.
Researchers published a tutorial on cognitive biases in AI-driven 6G autonomous networks, focusing on how LLM-powered agents can inherit human biases that distort network management decisions. The paper introduces mitigation strategies that demonstrated 5x lower latency and 40% higher energy savings in practical use cases.
Researchers developed UNIFIER, a continual learning framework for multimodal large language models (MLLMs) to adapt to changing visual scenarios without catastrophic forgetting. The framework addresses visual discrepancies across different environments like high-altitude, underwater, low-altitude, and indoor scenarios, showing significant improvements over existing methods.
Researchers developed a new reinforcement learning framework using Group Relative Policy Optimization (GRPO) to make Large Language Models provide consistent recommendations across semantically equivalent prompts. The method addresses a critical enterprise need for reliable AI systems in business domains like finance and customer support, where inconsistent responses undermine trust and compliance.
Researchers introduce DeCode, a training-free framework that adapts large language models to provide better contextualized medical answers by decoupling content from delivery. The system significantly improves clinical question answering performance, boosting zero-shot results from 28.4% to 49.8% on medical benchmarks.
Researchers introduce Krites, an asynchronous caching system for Large Language Models that uses LLM judges to verify cached responses, improving efficiency without changing serving decisions. The system increases the fraction of requests served with curated static answers by up to 3.9 times while maintaining unchanged critical path latency.
Researchers introduce 'Narrative Weaver', a new AI framework that generates consistent long-form visual content across extended sequences, addressing a key limitation in current generative AI models. The system combines multimodal language models with novel control mechanisms and includes the release of a 330K+ image dataset for e-commerce advertising.
Prediction markets on Kalshi and Polymarket have seen a shift in Senate control betting odds, with Democrats overtaking Republicans in recent weeks. The swing in trader sentiment appears linked to escalating geopolitical tensions involving Iran.
Ledger has integrated with MoonPay to enable users to control AI agent cryptocurrency transactions through hardware wallets. This integration allows users to approve AI-driven crypto spending while maintaining security by keeping private keys stored on the hardware device.
OpenViking is an open-source context database from Volcengine that revolutionizes how AI agents manage context by organizing it through a filesystem paradigm rather than flat text chunks. The system aims to make memory, resources, and skills manageable through a unified architecture for AI agent systems like OpenClaw.
Iranian vessels including a VLCC supertanker, LPG ship, and bulk carriers were observed transiting through the Strait of Hormuz bound for China on Sunday. This shipping activity represents continued Iran-China trade flows despite international sanctions.
