12,874 AI articles curated from 50+ sources with AI-powered sentiment analysis, importance scoring, and key takeaways.
Researchers have developed ToolTree, a new Monte Carlo tree search-based planning system for LLM agents that improves tool selection and usage through dual-feedback evaluation and bidirectional pruning. The system achieves approximately 10% performance gains over existing methods while maintaining high efficiency across multiple 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 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 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 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 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 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 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.
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.
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 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.
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.
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 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 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 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 propose a new "structure-faithful" framework for machine unlearning that preserves semantic relationships in AI models while removing specific data. The method uses semantic anchors to maintain knowledge structure, showing significant performance improvements of 19-33% across image classification, retrieval, and face recognition tasks.
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 introduce Cheers, a unified multimodal AI model that combines visual comprehension and generation by decoupling patch details from semantic representations. The model achieves 4x token compression and outperforms existing models like Tar-1.5B while using only 20% of the training cost.
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 propose Eye2Eye, a new framework that uses first-person perspective to improve human-AI collaboration by addressing communication and understanding gaps. The AR prototype integrates joint attention coordination, revisable memory, and reflective feedback, showing significant improvements in task completion time and user trust in studies.
Researchers propose MetaKE, a new framework for knowledge editing in Large Language Models that addresses the 'Semantic-Execution Disconnect' through bi-level optimization. The method treats edit targets as learnable parameters and uses a Structural Gradient Proxy to align edits with the model's feasible manifold, showing significant improvements over existing approaches.
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.
This comprehensive survey examines continual learning methodologies for large language models, focusing on three core training stages and methods to mitigate catastrophic forgetting. The research reveals that while current approaches show promise in specific domains, fundamental challenges remain in achieving seamless knowledge integration across diverse tasks and temporal scales.
