Making LLMs Say What They Think: Measuring and Improving CoT-Interpretability Alignment
Research
Research News
New papers, breakthroughs and academic AI research
A 3GPP-Compliant Benchmark Dataset for RIS-Aided Beyond 5G Networks
Research
ReTaCo: Residual-Target Control for On-Policy Distillation
Research
Approval Laundering: Systematizing Approval--Execution Binding Failures in AI Coding-Agent Harnesses
Research
Can Agents Trust Their Skills? Uncovering Unsafe Chains of Trust in Skill-Based LLM Agents
Research
Compression Footprints as Security Signals for Model-Poisoning Defense in Federated Learning
Research
DrivingBench: Can Vision-Language Models Drive a Toyota Corolla?
Research
APTInvestBench: Evaluating Autonomous APT Investigation under Varying Telemetry
Research
Structure vs. Chain-of-Thought: Evaluating LLM Criteria Extraction for Depression Severity
Research
SimEX: Simulation-Integrated Robotics AutoResearch
Research
From Verification Failures to Reusable Guidance for Coding Agents
Research
The Invisible Language Tax: Token Premiums of French and Regional Languages in 2026 LLM Tokenizers, and a French-Optimized Prototype
Research