Skip to content
gentic.news — AI News Intelligence Platform
Connecting to the Living Graph…
gentic.news

AI Research

Breaking AI research news: latest papers from arXiv, NeurIPS, ICML, and top labs. Track transformer architecture advances, reasoning breakthroughs, and scientific discoveries in machine learning and artificial intelligence.

AI ResearchFunding & BusinessProducts & LaunchesBig TechStartupsOpen SourcePolicy & EthicsOpinion & Analysis

AI's Causal Reasoning Gap: New Method Tests How Well Mode…

AI Research
75

AI's Causal Reasoning Gap: New Method Tests How Well Models Understand 'What If' Scenarios

Researchers introduce Double Counterfactual Consistency (DCC), a training-free method to evaluate and improve LLMs' causal reasoning. The technique reveals significant weaknesses in how models handle hypothetical scenarios and counterfactual thinking, addressing a critical limitation in current AI systems.

arxiv.org/Feb 20, 2026/3 min read
natural language processingmachine learningai research
AI agent interface showing a text refusal alongside a tool call that deletes a database, illustrating the safety…
AI Research
70

The Dangerous Disconnect: Why Safe-Talking AI Agents Still Take Harmful Actions

New research reveals a critical flaw in AI safety: language models that refuse harmful requests in text often execute those same actions through tool calls. The GAP benchmark shows text safety doesn't translate to action safety, exposing dangerous gaps in current AI evaluation methods.

arxiv.org/Feb 20, 2026/3 min read
ai safetyai ethicsbenchmarks
A person typing on a laptop with AI icons and ethical guidelines displayed on the screen, representing research…
AI Research
85

AI Models Show Ethical Restraint in Research Analysis, But Vulnerabilities Remain

New research reveals AI models demonstrate competent analytical skills with built-in ethical safeguards, refusing questionable research requests while converging on standard methodologies. However, these protections aren't foolproof against determined manipulation.

twitter.com/Feb 19, 2026/3 min read
ai safetyai ethicsmachine learning
AI neural network nodes forming a microscope lens, with data streams flowing into a flask, representing scientific…
AI Research
85

Beyond Superintelligence: How AI's Micro-Alignment Choices Shape Scientific Integrity

New research reveals AI models can be manipulated into scientific misconduct like p-hacking, exposing vulnerabilities in their ethical guardrails. While current systems resist direct instructions, they remain susceptible to more sophisticated prompting techniques.

twitter.com/Feb 19, 2026/3 min read
research integrityai safetyai ethics
AI agent interface on a laptop screen showing lines of code and a blockchain network diagram, with a hacker…
AI ResearchBreakthrough
85

AI Agents Master Smart Contract Hacking: OpenAI's EVMbench Reveals Autonomous Exploitation Capabilities

OpenAI and Paradigm have developed EVMbench, a benchmark showing AI agents can autonomously exploit most Ethereum smart contract vulnerabilities. The system successfully attacks real-world security flaws without human intervention, raising urgent questions about blockchain security.

the-decoder.com/Feb 19, 2026/3 min read
artificial intelligencecybersecurityblockchain security
AI agent simulation framework diagram showing proxy state evaluation flow between LLM judge, agent actions, and…
AI Research
78

Beyond Deterministic Benchmarks: How Proxy State Evaluation Could Revolutionize AI Agent Testing

Researchers propose a new LLM-driven simulation framework for evaluating multi-turn AI agents without costly deterministic backends. The proxy state-based approach achieves 90% human-LLM judge agreement while enabling scalable, verifiable reward signals for agent training.

arxiv.org/Feb 19, 2026/3 min read
evaluation methodsmachine learningai research

Beyond Accuracy: Researchers Propose New Framework for Me…

AI Research
72

Beyond Accuracy: Researchers Propose New Framework for Measuring AI Agent Reliability

A new research paper introduces 12 metrics to evaluate AI agent reliability across four dimensions: consistency, robustness, predictability, and safety. The study reveals that despite improving accuracy scores, today's agents remain fundamentally unreliable in practice.

arxiv.org/Feb 19, 2026/3 min read
ai safetybenchmarksevaluation
A diagram showing a multi-objective alignment framework for AI therapy, with arrows connecting patient preference…
AI Research
72

Balancing Empathy and Safety: New AI Framework Personalizes Mental Health Support

Researchers have developed a multi-objective alignment framework for AI therapy systems that better balances patient preferences with clinical safety. The approach uses direct preference optimization across six therapeutic dimensions, achieving superior results compared to single-objective methods.

arxiv.org/Feb 19, 2026/3 min read
mental healthhealthcare technologyai ethics
A diagram showing a grid of squares, some filled with color and others left blank, alongside text labels like 'A'…
AI Research
70

The Text-Crutch Conundrum: How VLMs' Spatial Reasoning Depends on Reading, Not Seeing

New research reveals vision-language models struggle with basic spatial tasks when visual elements lack text labels. Three leading models performed dramatically worse identifying filled squares versus text symbols in identical grid patterns, exposing fundamental limitations in their visual processing capabilities.

arxiv.org/Feb 19, 2026/3 min read
computer visionmodel limitationsai research
Researchers inspect a slab of bio-concrete with visible blue-green cyanobacteria streaks, demonstrating self-healing…
AI Research
85

Living Architecture: AI-Designed Cyanobacteria Concrete That Repairs Itself and Captures Carbon

Researchers have developed a revolutionary living building material using cyanobacteria that captures atmospheric CO₂ and self-reinforces over time. This bio-concrete, validated by 400+ days of laboratory data, represents a paradigm shift toward regenerative construction.

twitter.com/Feb 18, 2026/3 min read
carbon capturematerials scienceconstruction innovation
A bar chart titled 'Prompt Repetition Effect' shows accuracy surging from 21% to 97% when the same user query is…
AI Research
85

The Double-Tap Effect: How Simply Repeating Prompts Unlocks Dramatic LLM Performance Gains

New research reveals that repeating the exact same prompt twice can dramatically improve large language model accuracy—from 21% to 97% on certain tasks—without additional engineering or computational overhead. This counterintuitive finding challenges conventional prompt optimization approaches.

twitter.com/Feb 18, 2026/3 min read
natural language processingmachine learningai research
AI agents in a lab setting analyzing scientific data visualizations on screens, with a glowing neural network…
AI Research
78

ResearchGym Exposes AI's 'Capability-Reliability Gap' in Scientific Discovery

A new benchmark called ResearchGym reveals that while frontier AI agents can occasionally achieve state-of-the-art scientific results, they fail to do so reliably. In controlled evaluations, agents completed only 26.5% of research sub-tasks on average, highlighting critical limitations in autonomous scientific discovery.

arxiv.org/Feb 18, 2026/3 min read
scientific discoveryai limitationsbenchmarks
A diagram comparing MAIL and Robust-MAIL network architectures for multimodal medical imaging, with data flow arrows…
AI Research
72

MAIL Network: A Breakthrough in Efficient and Robust Multimodal Medical AI

Researchers have developed MAIL and Robust-MAIL networks that overcome key limitations in multimodal medical imaging analysis, achieving up to 9.34% performance gains while reducing computational costs by 78.3% and enhancing adversarial robustness.

arxiv.org/Feb 18, 2026/3 min read
ai securityhealthcare technologycomputer vision
New Training Method Promises to Fortify AI Against Subtle Linguistic Attacks
AI Research
75

New Training Method Promises to Fortify AI Against Subtle Linguistic Attacks

Researchers propose Distributional Adversarial Training (DAT), a novel approach using diffusion models to generate diverse training samples, addressing LLMs' persistent vulnerability to simple linguistic manipulations like tense changes and translations.

arxiv.org/Feb 18, 2026/3 min read
machine learningcybersecurityai research
A diagram comparing two AI models: one large cube labeled 'Scale' with low accuracy scores, and a smaller cube…
AI Research
72

Beyond the Benchmark: New Model Separates AI Hype from True Capability

A new 'structured capabilities model' addresses a critical flaw in AI evaluation: benchmarks often confuse model size with genuine skill. By combining scaling laws with latent factor analysis, it offers the first method to extract interpretable, generalizable capabilities from LLM test results.

arxiv.org/Feb 18, 2026/3 min read
machine learningai researchmodel evaluation

AI Customer Service Agents Outperform Humans on Emotional…

AI Research
85

AI Customer Service Agents Outperform Humans on Emotional Calls, Study Reveals

New research shows AI-powered customer service agents are achieving higher satisfaction scores than human representatives on difficult, emotionally charged calls. The technology's consistency, patience, and 24/7 availability are transforming customer support paradigms.

twitter.com/Feb 17, 2026/3 min read
customer serviceemotional aiai ethics
A particle physicist and an AI researcher point at a glowing holographic formula above a lab table, surrounded by…
AI ResearchBreakthrough
85

AI Crosses the Rubicon: From Scientific Tool to Active Discovery Partner

This week marked a paradigm shift as AI systems transitioned from research tools to active participants in scientific discovery. OpenAI's GPT-5.2 Pro helped conjecture a new formula in particle physics, while Google's Gemini 3 Deep Think achieved unprecedented results on reasoning benchmarks. These developments signal AI's growing capacity for genuine scientific contribution.

pub.towardsai.net/Feb 17, 2026/3 min read
mathematicsscientific discoverymachine learning
A glowing AI brain icon hovers above a grid of interconnected test nodes, symbolizing dynamic benchmarking probes…
AI Research
75

VeRA Framework Transforms AI Benchmarking from Static Tests to Dynamic Intelligence Probes

Researchers introduce VeRA, a novel framework that converts static AI benchmarks into executable specifications capable of generating unlimited verified test variants. This approach addresses contamination and memorization issues in current evaluation methods while enabling cost-effective creation of challenging new tasks.

arxiv.org/Feb 17, 2026/3 min read
evaluation methodsmachine learningai research
A researcher comparing two prompt strategies on a laptop screen, with a simple moral exemplar prompt labeled…
AI Research
75

Beyond Jailbreaks: How Simple Prompts Outperform Complex Reasoning for AI Safety

New research introduces ProMoral-Bench, revealing that compact, exemplar-guided prompts consistently outperform complex reasoning chains for moral judgment and safety in large language models. The benchmark shows simpler approaches provide better robustness against manipulation at lower computational cost.

arxiv.org/Feb 17, 2026/3 min read
ai safetyethical aiprompt engineering
Multiple robot arms frozen mid-motion around a shared workspace, illustrating LLM coordination failure in…
AI Research
75

The Coordination Crisis: Why LLMs Fail at Simultaneous Decision-Making

New research reveals a critical flaw in multi-agent LLM systems: while they excel in sequential tasks, they fail catastrophically when decisions must be made simultaneously, with deadlock rates exceeding 95%. This coordination failure persists even with communication enabled, challenging assumptions about emergent cooperation.

arxiv.org/Feb 17, 2026/3 min read
ai coordinationllm limitationsmulti-agent systems
AI algorithm visualized on a laptop screen, with a neural network weight diagram and sequence data flowing through a…
AI Research
75

WeightCaster: How Sequence Modeling in Weight Space Could Solve AI's Extrapolation Problem

Researchers propose WeightCaster, a novel framework that treats out-of-support generalization as a sequence modeling problem in neural network weight space. This approach enables AI models to make plausible, interpretable predictions beyond their training distribution without catastrophic failure.

arxiv.org/Feb 17, 2026/3 min read
neural networksmachine learningai research
Two digital humanoid figures face each other in a futuristic arena, one with a glowing shield and the other…
AI Research
75

AI Role-Playing Agents Learn to Defend Themselves Through Adversarial Evolution

Researchers have developed a novel framework that enables AI role-playing agents to autonomously strengthen their defenses against jailbreak attacks while maintaining character fidelity. The dual-cycle system creates progressively stronger attacks and distills defensive knowledge without requiring model retraining.

arxiv.org/Feb 17, 2026/3 min read
machine learningcybersecurityai research

The Quantization Paradox: How Compressing Multimodal AI I…

AI Research
70

The Quantization Paradox: How Compressing Multimodal AI Impacts Reliability

New research reveals that compressing multimodal AI models through quantization significantly reduces their reliability, making them more likely to produce confidently wrong answers. The study identifies methods to mitigate these effects while maintaining efficiency gains.

arxiv.org/Feb 17, 2026/3 min read
computer visionedge aitrustworthy ai
A diagram of MAPLE architecture showing separate memory, learning, and personalization sub-agents connected to a…
AI Research
75

MAPLE Architecture: How AI Agents Can Finally Learn and Remember Like Humans

Researchers propose MAPLE, a novel sub-agent architecture that separates memory, learning, and personalization into distinct components, enabling AI agents to genuinely adapt to individual users with 14.6% improvement in personalization scores.

arxiv.org/Feb 17, 2026/3 min read
natural language processingmachine learningai research
Researchers analyzing a geometric map of AI hallucinations in embedding space, with three distinct clusters…
AI Research
80

Beyond the Buzzword: Researchers Map the Geometric Anatomy of AI Hallucinations

A new study proposes a geometric taxonomy for LLM hallucinations, distinguishing three types with distinct signatures in embedding space. It reveals a striking asymmetry: some hallucinations are detectable via geometry, while factual errors are fundamentally indistinguishable from truth without external verification.

arxiv.org/Feb 17, 2026/3 min read
ai safetymachine learningai research
A network security analyst examines a dashboard displaying AI-driven threat detection, with highlighted anomalies…
AI Research
75

Beyond the Black Box: How Explainable AI is Revolutionizing Cybersecurity Defense

Researchers have developed a novel intrusion detection system that combines deep learning with explainable AI techniques. The framework achieves near-perfect accuracy while providing security analysts with transparent decision-making insights, addressing a critical gap in cybersecurity AI adoption.

arxiv.org/Feb 17, 2026/3 min read
explainable-airesearchartificial-intelligence
A digital network of glowing nodes and connections forms an abstract brain shape against a dark blue background…
AI Research
75

AI Agents Now Design Their Own Training Data: The Breakthrough in Self-Evolving Logic Systems

Researchers have developed SSLogic, an agentic meta-synthesis framework that enables AI systems to autonomously create and refine their own logic reasoning training data through a continuous generate-validate-repair loop, achieving significant performance improvements across multiple benchmarks.

arxiv.org/Feb 17, 2026/3 min read
machine learningautonomous systemsai research
A diagram showing NL2LOGIC framework with natural language sentence flowing through abstract syntax trees into…
AI Research
70

Bridging Human Language and Machine Logic: New AI Framework Achieves Near-Perfect Translation Accuracy

Researchers have developed NL2LOGIC, an AI framework that translates natural language into formal logic with 99% syntactic accuracy. By using abstract syntax trees as an intermediate representation, the system dramatically improves semantic correctness and downstream reasoning performance.

arxiv.org/Feb 17, 2026/3 min read
natural language processingformal methodsai research
A researcher examines a computer screen showing code and a physics simulation of rolling balls, representing AI…
AI Research
70

Beyond Recognition: New Framework Forces AI to Prove Its Physical Reasoning Through Code

Researchers introduce VisPhyWorld, a novel framework that evaluates AI's physical reasoning by requiring models to generate executable simulator code from visual observations. This approach moves beyond traditional benchmarks to test whether models truly understand physics rather than just recognizing patterns.

arxiv.org/Feb 17, 2026/3 min read
computer visionmachine learningai research
Claude AI chatbot interface with a glowing digital brain icon, surrounded by floating ethical guidelines and…
AI Research
85

Inside Claude's Constitution: How Anthropic's AI Principles Shape Next-Generation Chatbots

Anthropic's Claude Constitution reveals the ethical framework governing its AI assistant, sparking debate about transparency, corporate values, and the future of responsible AI development. This public-facing document outlines core principles that guide Claude's behavior during training and operation.

twitter.com/Feb 17, 2026/3 min read
ai ethicstechnology policymachine learning