Paper Reviews, Security News & Technical Analysis
27 August 2026
A multi-agent LLM framework conducts controlled simulation experiments for pharmaceutical process design, outperforming language-only reasoning on specificity a
LLM AgentsMulti-Agent SystemsScientific AISimulationProcess Optimization27 August 2026
RENDER shows that how memory evidence is formatted for LLMs changes accuracy by up to 73 points, exposing a critical uncontrolled variable in RAG evaluation.
LLM EvaluationRAGMemory SystemsBenchmarkingNLP27 August 2026
A pre-training data statistic, bigram conditional entropy, predicts transformer weight-scale growth via a power-law relation with R²=0.941 across 23 training ru
TransformersTraining DynamicsInformation TheoryWeight AnalysisML Theory26 August 2026
New research shows agentic feedback loops systematically increase sycophantic behaviour in LLMs, causing a mean 6.3pp accuracy drop across six frontier models.
LLM SafetySycophancyAgentic AIAI AlignmentNLP Research26 August 2026
KVBoost achieves 4.49x faster LLM prefill by reusing KV cache chunks at arbitrary prompt positions, outperforming vLLM prefix caching by 16% with no quality los
LLM InferenceKV CacheTransformer OptimizationSystems ML26 August 2026
A systematic review of model collapse in generative AI, covering causes, observable signals, and mitigation strategies for self-consuming training loops.
Generative AIModel CollapseSynthetic DataLLMsDiffusion Models25 August 2026
BF1 achieves 10.91x prefill speedup at 32K tokens via dyadic sparse attention, with better perplexity than dense continued training after selective retrofit.
Efficient TransformersSparse AttentionLong ContextInference OptimizationNLP25 August 2026
New research characterises positional retrieval bias in clinical EHR processing and introduces QCCS, a lightweight query-conditioned context selection method th
Clinical NLPLLMsRetrieval-Augmented GenerationEHRLong-Context25 August 2026
New research shows LLM safety alignment fails against semantic camouflage attacks, but early-layer probing detects harmful intent with 20-50% better accuracy.
AI SafetyLLMAdversarial MLMechanistic InterpretabilityResearch Review24 August 2026
Slovakia's NBU found SMS-triggered backdoors in Russian-made traffic cameras. A technical breakdown of the vulnerabilities and supply chain security implication
CybersecurityIoT SecuritySupply ChainCritical InfrastructureEastern Europe23 August 2026
A critical analysis of the English-to-Claudish translator tool, examining what it reveals about Claude's refusal behaviours, alignment mechanisms, and the broad
AI SafetyLLM ResearchAnthropicPrompt EngineeringAI Alignment23 August 2026
Prime Intellect ran 153 autonomous agent runs across 18 frontier models on the nanoGPT optimizer speedrun. Here is a technical breakdown of what the results rev
AI AgentsBenchmarkingLLM ResearchAutonomous SystemsMachine Learning