22,940 AI articles curated from 50+ sources with AI-powered sentiment analysis, importance scoring, and key takeaways.
AIBearisharXiv – CS AI · May 297/10
🧠Researchers introduce BioRefusalAudit, a framework using sparse autoencoders to evaluate the structural integrity of language model biosecurity refusals. The study reveals that five tested models fail to cleanly distinguish hazardous from benign biology, with refusals often disappearing under prompt formatting changes or output constraints, and some models refusing based on legality rather than actual biological hazard.
🧠 Llama
AIBullisharXiv – CS AI · May 297/10
🧠Researchers introduce Metacognitive Memory Policy Optimization (MMPO), a novel training method that improves how AI language model agents manage memory across long-horizon tasks. The approach uses Belief Entropy—a self-supervised metric measuring uncertainty about task state—to provide fine-grained supervision during memory summarization, enabling agents to maintain 97.1% performance even with 1.75M-token contexts.
AIBullisharXiv – CS AI · May 297/10
🧠Researchers introduce CFGzip, a token space compression technique that dramatically accelerates constrained decoding for large language models using context-free grammars. The method achieves up to 100x latency reduction and 7.5x total speedup, making complex grammar-constrained generation feasible at scale.
AIBullisharXiv – CS AI · May 297/10
🧠Researchers have developed AutoformBot, a multi-agent AI system that automatically translates informal mathematics textbooks into machine-verified formal proofs in Lean 4. The team successfully formalized 26 open-access textbooks into a library called Atlas containing over 45,000 declarations and 500,000 lines of verified code, demonstrating that large-scale automated mathematics formalization is now economically viable.
AIBullisharXiv – CS AI · May 297/10
🧠Researchers introduced Compass, an LLM agent framework that extracts marine lead data from 230,000+ academic papers without fine-tuning, successfully creating the largest integrated marine lead database with 3,751 previously uncatalogued records and 92% accuracy. The expert-guided approach demonstrates how domain-specific knowledge can overcome LLM hallucinations in high-stakes scientific applications.
AIBullisharXiv – CS AI · May 297/10
🧠Researchers introduce Moment-KV, a momentum-based compression technique that optimizes Key-Value cache usage during LLM decoding phases. The method improves long-generation task performance by 2.3-3.2% while maintaining latency by dynamically tracking token importance through temporal attention patterns rather than static heuristics.
AIBullisharXiv – CS AI · May 297/10
🧠Researchers introduce MEMENTO, a framework that treats web exploration as a learning signal for AI agents operating in data-scarce domains. By combining iterative web search with dual-channel memory systems, MEMENTO achieves 25-36% performance improvements over baseline models in professional applications like sales automation and legal research without requiring additional model training.
AIBullisharXiv – CS AI · May 297/10
🧠Researchers introduce AgentDoG 1.5, a lightweight AI safety framework designed to protect open-world agents like OpenClaw from emerging security risks. The framework uses only ~1k training samples to create efficient models (0.8B-8B parameters) that match closed-source alternatives while reducing deployment overhead by 100x, with all resources released openly.
🧠 GPT-5
AIBullisharXiv – CS AI · May 297/10
🧠SkillsInjector introduces a dynamic method for optimizing how large language model agents access and utilize skill libraries. Rather than treating skill selection as static, the approach adaptively determines which skills to include, how many to present, and how to describe them based on task requirements, achieving measurable performance improvements across multiple benchmarks.
AIBearisharXiv – CS AI · May 297/10
🧠A comprehensive audit of three major AI models reveals that personalized user contexts significantly reshape brand recommendations in commercial AI assistants, with mid-market brands experiencing up to 75% recommendation volatility while category leaders maintain 80% consistency across personas. The study demonstrates that AI recommendation bias is strongly correlated with model architecture and retrieval strategies, with implications for fair evaluation and brand perception measurement.
🏢 OpenAI🏢 Anthropic
AINeutralarXiv – CS AI · May 297/10
🧠Researchers introduce PRAIB, a benchmark framework that evaluates how Large Language Models perform peer review compared to human reviewers. Analysis of 11,000 LLM-generated reviews across major AI conferences reveals significant behavioral divergences: LLM ratings show less variability, positive bias, overconfidence, and frequently miss atomic weaknesses that human reviewers catch.
AIBullisharXiv – CS AI · May 297/10
🧠Researchers introduce Logit-aware Final-block Quantization (LFQ), a technique that improves low-bit quantization of large language models by optimizing the final transformer block to preserve token probability distributions. This advancement addresses quality degradation in generative tasks while maintaining efficiency gains critical for deploying scaled LLMs.
AIBullisharXiv – CS AI · May 297/10
🧠Researchers introduce polynomial representations as a quantitative measure of neural network simplicity, demonstrating that the effective degree of these representations predicts generalization better than existing metrics. The approach yields a differentiable regularizer that improves performance across image classification, text tasks, vision-language models, and reinforcement learning.
AIBullisharXiv – CS AI · May 297/10
🧠Researchers introduce Croissant Tasks, a machine-readable metadata format designed to improve reproducibility in machine learning research by abstracting implementation details into high-level specifications. The format enables autonomous AI agents to generate independent implementations of ML experiments, addressing critical reproducibility challenges that plague modern AI research.
AIBullisharXiv – CS AI · May 297/10
🧠Researchers introduce VikingMem, a memory management system for long-term LLM interactions that addresses context window limitations through selective memory extraction, stateful evolution, and temporal weighting. The system demonstrates 30% improvements in memory retrieval effectiveness while maintaining low latency, offering a generalizable solution across diverse applications beyond traditional chatbots.
AIBullisharXiv – CS AI · May 297/10
🧠Researchers used large language models and evolutionary search to create the first domain-independent heuristics for symbolic AI planning that surpass hand-engineered baselines. These evolved heuristics, written in C++, solve more planning tasks than existing state-of-the-art approaches and maintain the soundness guarantees of traditional planners.
AIBullisharXiv – CS AI · May 297/10
🧠Researchers introduce Mind-Omni, a unified framework that consolidates seven brain-computer interface tasks through discrete diffusion modeling, using a novel Brain Tokenizer to convert continuous neural signals into standardized tokens. The multi-task approach demonstrates competitive or superior performance compared to specialized models while enabling cross-modal interactions between brain, vision, and language data.
AIBullisharXiv – CS AI · May 297/10
🧠Researchers introduce GRASP, a method for improving large language model agents through controlled skill library updates that prevent performance regression. Tested across five base models on clinical benchmarks, GRASP achieves dramatic improvements (40.6% to 88.8% on MedAgentBench) while maintaining stability, outperforming existing self-improvement approaches by significant margins.
🧠 GPT-4🧠 GPT-5🧠 Gemini
AIBullisharXiv – CS AI · May 297/10
🧠Researchers introduce TRACE, a novel metric for evaluating the reasoning quality of large language models' Chain-of-Thought outputs by analyzing argument structure rather than just final answers. The method combines Toulmin's argumentation theory with metacognitive frameworks and demonstrates strong correlation with benchmark accuracy while improving reinforcement learning performance.
AIBullisharXiv – CS AI · May 297/10
🧠Researchers introduce BitTP, a quantization technique that compresses LLM-based trajectory prediction models to 1.58-bit weights while maintaining full-precision activations, enabling deployment on resource-constrained edge devices. The approach not only reduces memory and latency but actually improves prediction accuracy by 14-21% compared to full-precision baselines, demonstrating that strategic quantization can serve as an effective regularizer.
AIBearisharXiv – CS AI · May 297/10
🧠Researchers introduced FinVerBench, a benchmark for evaluating how well large language models verify financial statement accuracy using real SEC 10-K filings. Testing 14 contemporary LLMs revealed critical limitations: most models produced 95-100% false positives on clean statements, while performance varied dramatically based on how financial data was rendered, suggesting financial verification requires calibrated judgment beyond arithmetic detection.
🧠 Gemini
AIBullisharXiv – CS AI · May 297/10
🧠Researchers introduce ViewSuite, a benchmark revealing that Vision Language Models struggle to plan multi-step camera movements in 3D environments despite understanding individual view transformations. A self-exploration framework with view graph distillation dramatically improves planning capability, boosting Qwen2.5-VL-7B performance from 2.5% to 47.8% accuracy.
🧠 GPT-5🧠 Gemini
AINeutralarXiv – CS AI · May 297/10
🧠Researchers introduce BeliefTrack, a benchmark for evaluating how large language models manage contextual information over long interactions—deciding when to update beliefs, preserve state, or ignore noise. The study reveals vanilla LLMs fail significantly at this task, while reinforcement learning with belief-state rewards reduces failures by 71% on average.
AIBullisharXiv – CS AI · May 297/10
🧠DeepTool is a new AI framework that enhances large language models' ability to reason through tool use by implementing process-supervised reinforcement learning. The system dramatically improves performance on mathematical benchmarks like AIME24 (3.2% to 40.4%) while maintaining token efficiency through interleaved thinking and action.
AINeutralarXiv – CS AI · May 297/10
🧠Researchers introduce DistractionIF, a benchmark revealing that larger language models are paradoxically less robust to instruction-like noise in reference text, with performance degrading up to 30 points as scale increases. The study demonstrates that reinforcement learning via Group Relative Policy Optimization can restore robustness by 15.5% while maintaining instruction-following capability.
🏢 Perplexity
